> ## Documentation Index
> Fetch the complete documentation index at: https://docs.useorgx.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# MCP Tools Reference

> Profile-specific reference for OrgX MCP operations and human widget callbacks.

The default ChatGPT and v2 profiles expose **41 model operations**
and **7 human widget callbacks**. Human callbacks run through the widget after a user action.

This reference covers **155 source definitions**, including additional extended-profile
operations and preserved legacy or internal contracts. Each entry identifies its profiles and availability.
The **19 migration aliases** appear separately below.

> [!NOTE]
>
> This reference is auto-generated from the MCP server source code and the
> profile-specific contracts used by MCP clients.
> To regenerate: `pnpm docs:generate-mdx`

## Tool Catalog Overview

| Category | Tools | Description |
| - | - | - |
| Workflow Operations | 56 | `orgx_activate_work`, `orgx_archive_work`, `orgx_attach_artifact`, ... |
| Portable Work Receipts | 5 | `orgx_get_receipt_review_queue`, `orgx_get_work_receipt`, `orgx_list_work_receipts`, ... |
| Human Widget Operations | 3 | `orgx_widget_approve_artifact`, `orgx_widget_request_artifact_changes`, `orgx_widget_select_workspace` |
| Legacy and internal: Recommended Entry Points | 4 | `approve_agent_work`, `delegate_agent_task`, `recall_memory`, ... |
| Decisions | 6 | `approve_decision`, `get_decision_history`, `get_pending_decisions`, ... |
| Legacy and internal: Agents | 4 | `get_agent_status`, `handoff_task`, `recommend_next_action`, ... |
| Legacy and internal: Initiative Monitoring | 1 | `get_initiative_pulse` |
| Legacy and internal: Entity Management | 6 | `batch_create_entities`, `batch_delete_entities`, `comment_on_entity`, ... |
| Legacy and internal: Organization | 1 | `get_org_snapshot` |
| Legacy and internal: Planning | 5 | `complete_plan`, `get_active_sessions`, `improve_plan`, ... |
| Legacy and internal: Scoring & Queue | 1 | `get_scoring_signals` |
| Legacy and internal: Streams | 2 | `get_initiative_stream_state`, `update_stream_progress` |
| Legacy and internal: Client Integration | 9 | `check_spawn_guard`, `classify_task_model`, `consolidate_pr`, ... |
| Legacy and internal: Workspace | 1 | `workspace` |
| Legacy and internal: Onboarding | 1 | `configure_org` |
| Legacy and internal: Stats | 1 | `stats` |
| Legacy and internal: Intelligence Flywheel | 6 | `get_morning_brief`, `get_my_trust_context`, `get_relevant_learnings`, ... |
| Legacy and internal: Billing | 3 | `account_status`, `account_upgrade`, `account_usage_report` |
| Legacy and internal: MCP v2 Public Surface | 10 | `orgx_act`, `orgx_attach`, `orgx_bootstrap`, ... |
| Other | 27 | `check_execution_readiness`, `configure_outcome_type`, `get_operator_chronicle`, ... |
| Legacy and internal: Proof Runtime v1 | 3 | `orgx_complete_work`, `orgx_create_work`, `orgx_events_tail` |

***

## Workflow Operations

56 tools for workflow operations operations.

### orgx\_activate\_work

Activate a playbook through the exact supported playbook transition.

**type** `string` *required*

Options: `playbook`.

**id** `string` *required*

Target entity UUID or short ID prefix (8+ hex chars).

**note** `string`

Strongly recommended for destructive or blocking actions (block, flag\_risk, decline, supersede, cancel, delete). Free-text rationale shown in audit history and downstream agent context.

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**session\_id** `string`

Optional OrgX conversation-session context.

**Required Scopes**: `initiatives:write`

**Profiles**: extended

**Availability**: Extended profile model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_activate_work",
  "args": {
      "type": "playbook",
      "id": "<id>"
  }
}
```

***

### orgx\_archive\_work

Archive an existing initiative, objective, or playbook through its exact supported transition.

**type** `string` *required*

Options: `initiative`, `objective`, `playbook`.

**id** `string` *required*

Target entity UUID or short ID prefix (8+ hex chars).

**note** `string`

Strongly recommended for destructive or blocking actions (block, flag\_risk, decline, supersede, cancel, delete). Free-text rationale shown in audit history and downstream agent context.

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**session\_id** `string`

Optional OrgX conversation-session context.

**Required Scopes**: `initiatives:write`

**Profiles**: extended

**Availability**: Extended profile model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_archive_work",
  "args": {
      "type": "initiative",
      "id": "<id>"
  }
}
```

***

### orgx\_attach\_artifact

Register a named deliverable and provenance on an OrgX work target. A durable artifact URL is required. May trigger automatic evaluation using external model providers and incur model costs. Registered proof awaits review; attaching does not approve or complete work.

**type** `string` *required*

Options: `initiative`, `workstream`, `milestone`, `task`.

**id** `string` *required*

Target entity UUID or short ID prefix

**name** `string` *required*

Artifact title

**artifact\_type** `string` *required*

Artifact type code. Preferred founder/team examples: orchestration.next\_initiative, eng.pull\_request, eng.deploy\_proof, eng.structured\_blocker, sales.strategy, sales.icp\_offer\_sequence, sales.send\_plan, sales.conversion\_gates, marketing.launch\_asset, marketing.channel\_hypothesis, marketing.positioning\_brief, marketing.proof\_distribution\_plan, marketing.interview\_pr\_plan, product.customer\_discovery, product.prd, product.pricing\_hypothesis, product.decision\_record, design.audit, design.component\_spec, design.token\_package, ops.operator\_brief, ops.runbook, ops.budget\_envelope, ops.incident\_status, proof.link. Custom codes remain accepted.

**description** `string`

Artifact description

**preview\_markdown** `string`

Optional markdown preview shown with the linked artifact. Does not replace artifact\_url/external\_url.

**agent\_type** `string`

Specialist domain, such as engineering, design, sales, marketing, or operations.

**company\_stage** `string`

Founder/team context this artifact is calibrated for. Stored under metadata.artifact\_contract. Options: `early_founder`, `founder_led_company`, `operating_team`.

**business\_outcome** `string`

Business outcome this artifact is meant to advance, such as ship a PR, start founder-led sales, unblock launch, reduce incident risk, or choose the next initiative. Stored under metadata.artifact\_contract.

**owner** `string`

Human or agent owner for the next review/action. Stored under metadata.artifact\_contract.

**review\_date** `string`

Date or cadence for the next review point. Stored under metadata.artifact\_contract.

**verification** `string[]`

Verification evidence or checks required before the artifact can count as done. Stored under metadata.artifact\_contract.

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**session\_id** `string`

Optional OrgX conversation-session context.

**location** `any` *required*

Durable internal or external artifact URL.

**Required Scopes**: `initiatives:write`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_attach_artifact",
  "args": {
      "type": "initiative",
      "id": "<id>",
      "name": "<name>",
      "artifact_type": "<artifact_type>",
      "location": {
          "artifact_url": "<artifact_url>"
      }
  }
}
```

***

### orgx\_block\_work

Mark a task or workstream blocked and retain its audit rationale.

**type** `string` *required*

Options: `task`, `workstream`.

**id** `string` *required*

Target entity UUID or short ID prefix (8+ hex chars).

**note** `string` *required*

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**session\_id** `string`

Optional OrgX conversation-session context.

**Required Scopes**: `initiatives:write`

**Profiles**: extended

**Availability**: Extended profile model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_block_work",
  "args": {
      "type": "task",
      "id": "<id>",
      "note": "<approval_note>"
  }
}
```

***

### orgx\_cancel\_work

Cancel a hierarchy node through OrgX lifecycle control, propagating to descendant work and stopping active runs. Does not mark work complete.

**level** `string` *required*

Which hierarchy node to act on Options: `initiative`, `workstream`, `milestone`, `task`, `run`.

**id** `string` *required*

UUID of the node

**Required Scopes**: `agents:write`, `initiatives:write`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_cancel_work",
  "args": {
      "level": "initiative",
      "id": "<id>"
  }
}
```

***

### orgx\_capture\_decision

Capture decision text, rationale, and context for human review. Returns its authoritative review state. Capturing a decision does not approve it or establish an accepted historical judgment.

**decision** `string` *required*

**title** `string`

Short title for the decision.

**summary** `string`

Optional one-line summary used in lists. Falls back to title when omitted.

**context** `string`

Background context / rationale that led to the decision. Recommended for action=create to capture provenance.

**initiative\_id** `string`

Initiative UUID used as the parent or scope for this operation.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**session\_id** `string`

Optional OrgX conversation-session context.

**Required Scopes**: `decisions:write`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_capture_decision",
  "args": {
      "decision": "<decision>"
  }
}
```

***

### orgx\_check\_agent\_delegation `read-only`

Read delegation eligibility, quality gates, and rate-limit context for a specialist. Does not dispatch work or consume a dispatch allowance.

**agent\_type** `string` *required*

Specialist domain, such as engineering, design, sales, marketing, or operations.

**task\_id** `string`

Existing task UUID.

**title** `string`

Task title.  Used as the human-readable label of the spawned task.

**instructions** `string`

Delegation instructions. When supplied for existing work, overrides its description for this request.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**Required Scopes**: `agents:read`

**Profiles**: extended

**Availability**: Extended profile model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_check_agent_delegation",
  "args": {
      "agent_type": "<agent_type>"
  }
}
```

***

### orgx\_check\_execution\_readiness `read-only`

Read whether the authorized workspace has execution credentials and configuration before dispatching agent work. Never dispatches a run.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**Required Scopes**: `initiatives:read`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_check_execution_readiness",
  "args": {}
}
```

***

### orgx\_classify\_agent\_task `read-only`

Read complexity classification and model routing for a proposed task. Does not create or dispatch work.

**title** `string` *required*

Display title for the new work record.

**instructions** `string`

Delegation instructions. When supplied for existing work, overrides its description for this request.

**agent\_type** `string`

Specialist domain, such as engineering, design, sales, marketing, or operations.

**model\_tier** `string`

Optional model tier override. Omit to let OrgX auto-route from task complexity. Legacy local/sonnet/opus are accepted for older clients. Options: `standard`, `balanced`, `precision`, `local`, `sonnet`, `opus`.

**provider** `string`

Optional provider preference. Use auto unless the user asks for a specific provider or a cost comparison selects one. Options: `auto`, `openai`, `anthropic`, `openrouter`, `groq`, `local`.

**budget\_mode** `string`

Optional budget posture. Use cheapest\_valid for controlled validation runs while reliability is being proven. Options: `cheapest_valid`, `balanced`, `highest_quality`.

**max\_cost\_usd** `number`

Optional hard cost ceiling in USD for this dispatch. If the estimate exceeds it, OrgX blocks, downgrades, or requests approval before dispatch.

**Required Scopes**: `agents:read`

**Profiles**: extended

**Availability**: Extended profile model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_classify_agent_task",
  "args": {
      "title": "<title>"
  }
}
```

***

### orgx\_complete\_entity

Apply the supported entity completion transition after OrgX completion gates. Does not attach new proof or supply human approval. Ledger command completion uses the separate orgx\_complete\_work runtime contract.

**type** `string` *required*

Options: `initiative`, `workstream`, `milestone`, `task`, `objective`.

**id** `string` *required*

Target entity UUID or short ID prefix (8+ hex chars).

**note** `string`

Strongly recommended for destructive or blocking actions (block, flag\_risk, decline, supersede, cancel, delete). Free-text rationale shown in audit history and downstream agent context.

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**session\_id** `string`

Optional OrgX conversation-session context.

**Required Scopes**: `initiatives:write`

**Profiles**: extended

**Availability**: Extended profile model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_complete_entity",
  "args": {
      "type": "initiative",
      "id": "<id>"
  }
}
```

***

### orgx\_complete\_plan

Save final markdown and complete the planning session only if its expected revision is current. Optionally attach the completed plan to typed work targets; attachment failures are reported separately after completion. Does not start execution. After an uncertain response, read the plan before repeating the completion.

**session\_id** `string` *required*

Plan session UUID or orgx://plan\_session/\<uuid> URI.

**plan\_content** `string` *required*

**expected\_version** `integer` *required*

Authoritative plan\_ref.version from the most recent read. Required to prevent overwriting another edit.

**attach\_to** `object[]`

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**Required Scopes**: `initiatives:write`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_complete_plan",
  "args": {
      "session_id": "<session_id>",
      "plan_content": "<plan_content>",
      "expected_version": 1
  }
}
```

***

### orgx\_complete\_work\_with\_proof

Register typed proof, verify completion requirements, and apply the allowed work completion transition. May return proof recorded with completion blocked or awaiting review. Verification and human acceptance remain separate facts.

**type** `string` *required*

Options: `initiative`, `workstream`, `milestone`, `task`.

**id** `string` *required*

**artifact** `object` *required*

**verification** `string[]`

Verification notes. A client with a cached schema can encode one producer modality\_proof as orgx:modality-proof:v1: followed by the same closed JSON envelope; OrgX validates it before recording.

**quality\_score** `number`

Quality score (0-5) attached to the action when used in proof/completion flows.

**note** `string`

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**session\_id** `string`

Optional OrgX conversation-session context.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**Required Scopes**: `initiatives:write`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_complete_work_with_proof",
  "args": {
      "type": "initiative",
      "id": "<id>",
      "artifact": {
          "artifact_type": "<artifact_type>"
      }
  }
}
```

***

### orgx\_create\_and\_launch\_initiative\_hierarchy

Create a rich hierarchy through the existing compatibility batch path and launch follow-up work. May generate missing hierarchy, publish a live link, incur model costs, and synchronize an explicitly configured external tracker. Preserves objectives, references, dependencies, assignments, and proof profiles until atomic OrgX creation has full parity.

**title** `string` *required*

Display title for the new work record.

**summary** `string`

**description** `string`

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**goal\_ids** `string[]`

**objective\_ids** `string[]`

**workstreams** `object[]`

**source\_evidence** `object`

**context** `object[]`

**coordination\_dependency** `object`

**owner\_id** `any`

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**continue\_on\_error** `boolean`

**concurrency** `integer`

**external\_sync** `object`

**Required Scopes**: `agents:write`, `initiatives:write`

**Profiles**: extended

**Availability**: Extended profile model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_create_and_launch_initiative_hierarchy",
  "args": {
      "title": "<title>"
  }
}
```

***

### orgx\_create\_and\_start\_agent\_task

Create an ad hoc delegated task and dispatch it in one compatibility operation. Can incur costs and interact with connected services under the declared constraints. Prefer separate creation and dispatch for reviewed work.

**title** `string` *required*

Display title for the new work record.

**initiative\_id** `string`

Initiative UUID used as the parent or scope for this operation.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**agent\_type** `string`

Specialist domain, such as engineering, design, sales, marketing, or operations.

**instructions** `string` *required*

Delegation instructions. When supplied for existing work, overrides its description for this request.

**model\_tier** `string`

Optional model tier override. Omit to let OrgX auto-route from task complexity. Legacy local/sonnet/opus are accepted for older clients. Options: `standard`, `balanced`, `precision`, `local`, `sonnet`, `opus`.

**model** `string`

Optional exact model identifier when the user explicitly selects one. Otherwise OrgX resolves the model from task, tier, provider, policy, and budget.

**provider** `string`

Optional provider preference. Use auto unless the user asks for a specific provider or a cost comparison selects one. Options: `auto`, `openai`, `anthropic`, `openrouter`, `groq`, `local`.

**runtime** `string`

Optional runtime OrgX runs the work on. Omit or auto to let OrgX choose. cloud\_claude / cloud\_openai: OrgX cloud on the Claude Agent SDK or OpenAI Responses. managed\_openai / managed\_anthropic: the OpenAI Agents API or Claude Managed Agents under OrgX governance. local: a paired local peer (Claude Code, Codex, OpenClaw) on the user machine. Options: `auto`, `cloud_claude`, `cloud_openai`, `managed_openai`, `managed_anthropic`, `local`.

**deadline** `string`

Optional ISO-8601 instant by which the work must finish (e.g. "2026-09-28T17:00:00Z"). Validated and recorded; free text is rejected because a constraint that cannot be evaluated is not a constraint.

**max\_cost\_usd** `number`

Optional hard cost ceiling in USD for this dispatch. If the estimate exceeds it, OrgX blocks, downgrades, or requests approval before dispatch.

**budget\_mode** `string`

Optional budget posture. Use cheapest\_valid for controlled validation runs while reliability is being proven. Options: `cheapest_valid`, `balanced`, `highest_quality`.

**max\_parallel** `integer`

Optional cap on concurrent workers for this dispatch. Work that shares a repository is usually integration-bound well below this: more workers add merge contention, not throughput.

**expected\_artifacts** `string[]`

Optional expected final-output labels. Declaring at least one adds an artifact contract to the run.

**effects** `object`

Optional declared effect scope for the work. Recorded on the run and shown in the receipt. Declaring an effect never grants it — the platform intersects it with the caller authority.

**acceptance** `object[]`

Optional acceptance checks that define what counts as done. Declared BEFORE the work and hashed at dispatch. A check that already passes on the pre-state is reported as non-discriminating and excluded from the verdict.

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**session\_id** `string`

Optional OrgX conversation-session context.

**Required Scopes**: `agents:write`

**Profiles**: extended

**Availability**: Extended profile model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_create_and_start_agent_task",
  "args": {
      "title": "<title>",
      "instructions": "<instructions>"
  }
}
```

***

### orgx\_create\_decision

Create a named decision with its text and rationale for human review. Does not approve the decision.

**title** `string` *required*

Display title for the new work record.

**decision** `string` *required*

**summary** `string`

Optional one-line summary used in lists. Falls back to title when omitted.

**context** `string`

Background context / rationale that led to the decision. Recommended for action=create to capture provenance.

**initiative\_id** `string`

Initiative UUID used as the parent or scope for this operation.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**session\_id** `string`

Optional OrgX conversation-session context.

**Required Scopes**: `decisions:write`

**Profiles**: extended

**Availability**: Extended profile model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_create_decision",
  "args": {
      "title": "<title>",
      "decision": "<decision>"
  }
}
```

***

### orgx\_create\_initiative

Create one initiative in its initial state without launching work or publishing a live link. Supply objectives when workspace policy requires them.

**title** `string` *required*

Display title for the new work record.

**summary** `string`

Short description shown in lists and previews. Recommended on create.

**description** `string`

Longer-form description used in detail views.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**goal\_ids** `string[]`

Objective UUIDs. Required when workspace policy enforces primary objectives.

**priority** `string`

Record urgency. Only low|medium|high|urgent are accepted here; do not send portfolio/live labels such as active, critical, maintenance, or hold. "urgent" is normalized to "high" server-side. Options: `low`, `medium`, `high`, `urgent`.

**metadata** `object`

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**session\_id** `string`

Optional OrgX conversation-session context.

**Required Scopes**: `initiatives:write`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_create_initiative",
  "args": {
      "title": "<title>"
  }
}
```

***

### orgx\_create\_initiative\_hierarchy

Atomically commit a deterministic initiative hierarchy in OrgX using a stable retry key. Creates work records without launching agents. Visibility defaults to private; source evidence is retained.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**plan** `object` *required*

Deterministic initiative hierarchy. Dependencies reference task titles or workstream names supported by OrgX.

**source\_evidence** `object`

**plan\_digest** `string`

**idempotency\_key** `string` *required*

**Required Scopes**: `initiatives:write`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_create_initiative_hierarchy",
  "args": {
      "plan": {
          "initiative": {
              "title": "<title>"
          },
          "workstreams": [
              {
                  "name": "<name>"
              }
          ]
      },
      "idempotency_key": "<idempotency_key>"
  }
}
```

***

### orgx\_create\_milestone

Create a milestone under a selected workstream. Does not start or complete work.

**title** `string` *required*

Display title for the new work record.

**summary** `string`

Short description shown in lists and previews. Recommended on create.

**description** `string`

Longer-form description used in detail views.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**goal\_ids** `string[]`

Objective UUIDs. Required when workspace policy enforces primary objectives.

**priority** `string`

Record urgency. Only low|medium|high|urgent are accepted here; do not send portfolio/live labels such as active, critical, maintenance, or hold. "urgent" is normalized to "high" server-side. Options: `low`, `medium`, `high`, `urgent`.

**metadata** `object`

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**session\_id** `string`

Optional OrgX conversation-session context.

**initiative\_id** `string`

Initiative UUID used as the parent or scope for this operation.

**workstream\_id** `string` *required*

Parent workstream UUID.

**due\_date** `string`

Due date in YYYY-MM-DD form for this supported work type.

**Required Scopes**: `initiatives:write`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_create_milestone",
  "args": {
      "title": "<title>",
      "workstream_id": "<workstream_id>"
  }
}
```

***

### orgx\_create\_task

Create one task under a selected workstream. Supply a milestone when workspace backlog policy requires one. Does not dispatch the task.

**title** `string` *required*

Display title for the new work record.

**summary** `string`

Short description shown in lists and previews. Recommended on create.

**description** `string`

Longer-form description used in detail views.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**goal\_ids** `string[]`

Objective UUIDs. Required when workspace policy enforces primary objectives.

**priority** `string`

Record urgency. Only low|medium|high|urgent are accepted here; do not send portfolio/live labels such as active, critical, maintenance, or hold. "urgent" is normalized to "high" server-side. Options: `low`, `medium`, `high`, `urgent`.

**metadata** `object`

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**session\_id** `string`

Optional OrgX conversation-session context.

**initiative\_id** `string`

Initiative UUID used as the parent or scope for this operation.

**workstream\_id** `string` *required*

Parent workstream UUID.

**milestone\_id** `string`

Parent milestone UUID. Required when workspace backlog policy requires an explicit milestone.

**due\_date** `string`

Due date in YYYY-MM-DD form for this supported work type.

**Required Scopes**: `initiatives:write`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_create_task",
  "args": {
      "title": "<title>",
      "workstream_id": "<workstream_id>"
  }
}
```

***

### orgx\_create\_workstream

Create a workstream under an existing initiative. Does not dispatch agents or start the workstream.

**title** `string` *required*

Display title for the new work record.

**summary** `string`

Short description shown in lists and previews. Recommended on create.

**description** `string`

Longer-form description used in detail views.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**goal\_ids** `string[]`

Objective UUIDs. Required when workspace policy enforces primary objectives.

**priority** `string`

Record urgency. Only low|medium|high|urgent are accepted here; do not send portfolio/live labels such as active, critical, maintenance, or hold. "urgent" is normalized to "high" server-side. Options: `low`, `medium`, `high`, `urgent`.

**metadata** `object`

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**session\_id** `string`

Optional OrgX conversation-session context.

**initiative\_id** `string` *required*

Initiative UUID used as the parent or scope for this operation.

**Required Scopes**: `initiatives:write`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_create_workstream",
  "args": {
      "title": "<title>",
      "initiative_id": "<initiative_id>"
  }
}
```

***

### orgx\_delete\_work

Permanently delete an authorized work record. Intended for an explicit administrative profile; dependent-record rules remain enforced by OrgX.

**type** `string` *required*

Options: `workspace`, `initiative`, `workstream`, `milestone`, `task`, `objective`, `playbook`.

**id** `string` *required*

Target entity UUID or short ID prefix (8+ hex chars).

**note** `string` *required*

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**session\_id** `string`

Optional OrgX conversation-session context.

**Required Scopes**: `initiatives:write`

**Profiles**: extended

**Availability**: Extended profile model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_delete_work",
  "args": {
      "type": "workspace",
      "id": "<id>",
      "note": "<approval_note>"
  }
}
```

***

### orgx\_estimate\_agent\_task `read-only`

Estimate routing and cost for an existing task or a proposed task. Never creates a task, consumes a dispatch allowance, or starts a run.

**task** `any` *required*

**initiative\_id** `string`

Initiative UUID used as the parent or scope for this operation.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**agent\_type** `string`

Specialist domain, such as engineering, design, sales, marketing, or operations.

**model\_tier** `string`

Optional model tier override. Omit to let OrgX auto-route from task complexity. Legacy local/sonnet/opus are accepted for older clients. Options: `standard`, `balanced`, `precision`, `local`, `sonnet`, `opus`.

**model** `string`

Optional exact model identifier when the user explicitly selects one. Otherwise OrgX resolves the model from task, tier, provider, policy, and budget.

**provider** `string`

Optional provider preference. Use auto unless the user asks for a specific provider or a cost comparison selects one. Options: `auto`, `openai`, `anthropic`, `openrouter`, `groq`, `local`.

**runtime** `string`

Optional runtime OrgX runs the work on. Omit or auto to let OrgX choose. cloud\_claude / cloud\_openai: OrgX cloud on the Claude Agent SDK or OpenAI Responses. managed\_openai / managed\_anthropic: the OpenAI Agents API or Claude Managed Agents under OrgX governance. local: a paired local peer (Claude Code, Codex, OpenClaw) on the user machine. Options: `auto`, `cloud_claude`, `cloud_openai`, `managed_openai`, `managed_anthropic`, `local`.

**budget\_mode** `string`

Optional budget posture. Use cheapest\_valid for controlled validation runs while reliability is being proven. Options: `cheapest_valid`, `balanced`, `highest_quality`.

**max\_cost\_usd** `number`

Optional hard cost ceiling in USD for this dispatch. If the estimate exceeds it, OrgX blocks, downgrades, or requests approval before dispatch.

**Required Scopes**: `agents:read`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_estimate_agent_task",
  "args": {
      "task": {
          "task_id": "<task_id>"
      }
  }
}
```

***

### orgx\_flag\_risk\_work

Flag a milestone at risk with an audit rationale. Does not pause active runs.

**type** `string` *required*

Options: `milestone`.

**id** `string` *required*

Target entity UUID or short ID prefix (8+ hex chars).

**note** `string` *required*

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**session\_id** `string`

Optional OrgX conversation-session context.

**Required Scopes**: `initiatives:write`

**Profiles**: extended

**Availability**: Extended profile model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_flag_risk_work",
  "args": {
      "type": "milestone",
      "id": "<id>",
      "note": "<approval_note>"
  }
}
```

***

### orgx\_get\_agent\_status

Read active and optionally idle agents in the workspace or initiative. Successful calls record metered MCP allowance usage without changing work records.

**agent\_id** `string`

Optional agent ID to inspect

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**initiative\_id** `string`

Initiative UUID used as the parent or scope for this operation.

**include\_idle** `boolean`

Include idle agents in the response

**Required Scopes**: `agents:read`

**Profiles**: v2, legacy, extended, chatgpt, read-only, memory, commander, planner, executor, observer

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_get_agent_status",
  "args": {}
}
```

***

### orgx\_get\_initiative\_progress

Read hierarchy progress, health, blockers, and review gates for one initiative. Successful calls record metered MCP allowance usage without changing work records.

**initiative\_id** `string` *required*

Initiative UUID.

**Required Scopes**: `initiatives:read`

**Profiles**: v2, legacy, extended, chatgpt, read-only, memory, commander, planner, executor, observer

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_get_initiative_progress",
  "args": {
      "initiative_id": "<initiative_id>"
  }
}
```

***

### orgx\_get\_next\_actions

Read actionable priorities and blockers for the selected work scope. The compatibility implementation records metered MCP allowance usage without changing work records.

**entity\_type** `string`

Recommendation scope type Options: `workspace`, `initiative`, `workstream`, `milestone`, `task`.

**entity\_id** `string`

Scoped entity ID

**initiative\_id** `string`

Initiative UUID used as the parent or scope for this operation.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**limit** `integer`

Maximum recommendations

**session\_id** `string`

Optional OrgX conversation-session context.

**Required Scopes**: `initiatives:read`

**Profiles**: v2, extended, chatgpt, read-only

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_get_next_actions",
  "args": {}
}
```

***

### orgx\_get\_operation\_status `read-only`

Read a durable work command, run, or decision. Prefer operation\_id returned by a prior operation; compatibility callers can supply kind and id together. Never starts or settles work.

**operation\_id** `string`

**kind** `string`

Options: `decision`, `run`, `command`.

**id** `string`

**Required Scopes**: `decisions:read`, `agents:read`, `initiatives:read`, `memory:read`

**Profiles**: v2, legacy, extended, chatgpt, read-only, memory, commander, planner, executor, observer

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_get_operation_status",
  "args": {}
}
```

***

### orgx\_get\_operator\_brief `read-only`

Read workspace reporting, decision chronology, progress, proof, priorities, and gaps for a day, week, or 30-day window.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**period** `string`

Reporting window. day=24h, week=7d, 30d=30 days. Options: `day`, `week`, `30d`.

**Required Scopes**: `initiatives:read`

**Profiles**: v2, legacy, extended, chatgpt, read-only, commander, observer

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_get_operator_brief",
  "args": {}
}
```

***

### orgx\_get\_workspace\_context `read-only`

Read the authorized workspace, optional initiative context, and typed references. Does not select a workspace or create a session.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**initiative\_id** `string`

**Required Scopes**: `initiatives:read`

**Profiles**: v2, legacy, extended, chatgpt, memory, commander, planner, executor, observer

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_get_workspace_context",
  "args": {}
}
```

***

### orgx\_handoff\_task

Reassign an existing task to a specialist through the canonical handoff and dispatch lifecycle. Can incur model costs and connected-service effects; requires agent and initiative write grants.

**task\_id** `string` *required*

Existing task UUID.

**initiative\_id** `string`

Initiative UUID used as the parent or scope for this operation.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**agent\_type** `string` *required*

Specialist domain receiving the task.

**instructions** `string`

Delegation instructions. When supplied for existing work, overrides its description for this request.

**model\_tier** `string`

Optional model tier override. Omit to let OrgX auto-route from task complexity. Legacy local/sonnet/opus are accepted for older clients. Options: `standard`, `balanced`, `precision`, `local`, `sonnet`, `opus`.

**model** `string`

Optional exact model identifier when the user explicitly selects one. Otherwise OrgX resolves the model from task, tier, provider, policy, and budget.

**provider** `string`

Optional provider preference. Use auto unless the user asks for a specific provider or a cost comparison selects one. Options: `auto`, `openai`, `anthropic`, `openrouter`, `groq`, `local`.

**runtime** `string`

Optional runtime OrgX runs the work on. Omit or auto to let OrgX choose. cloud\_claude / cloud\_openai: OrgX cloud on the Claude Agent SDK or OpenAI Responses. managed\_openai / managed\_anthropic: the OpenAI Agents API or Claude Managed Agents under OrgX governance. local: a paired local peer (Claude Code, Codex, OpenClaw) on the user machine. Options: `auto`, `cloud_claude`, `cloud_openai`, `managed_openai`, `managed_anthropic`, `local`.

**deadline** `string`

Optional ISO-8601 instant by which the work must finish (e.g. "2026-09-28T17:00:00Z"). Validated and recorded; free text is rejected because a constraint that cannot be evaluated is not a constraint.

**max\_cost\_usd** `number`

Optional hard cost ceiling in USD for this dispatch. If the estimate exceeds it, OrgX blocks, downgrades, or requests approval before dispatch.

**budget\_mode** `string`

Optional budget posture. Use cheapest\_valid for controlled validation runs while reliability is being proven. Options: `cheapest_valid`, `balanced`, `highest_quality`.

**max\_parallel** `integer`

Optional cap on concurrent workers for this dispatch. Work that shares a repository is usually integration-bound well below this: more workers add merge contention, not throughput.

**expected\_artifacts** `string[]`

Optional expected final-output labels. Declaring at least one adds an artifact contract to the run.

**effects** `object`

Optional declared effect scope for the work. Recorded on the run and shown in the receipt. Declaring an effect never grants it — the platform intersects it with the caller authority.

**acceptance** `object[]`

Optional acceptance checks that define what counts as done. Declared BEFORE the work and hashed at dispatch. A check that already passes on the pre-state is reported as non-discriminating and excluded from the verdict.

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**session\_id** `string`

Optional OrgX conversation-session context.

**Required Scopes**: `agents:write`, `initiatives:write`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_handoff_task",
  "args": {
      "task_id": "<task_id>",
      "agent_type": "<agent_type>"
  }
}
```

***

### orgx\_inspect `read-only`

Read the current state and linked context of one OrgX work record, decision, artifact, or plan session before acting. Returns its owners, decisions, acceptance checks, and proof where available. Related records are available through orgx\_search and priorities through orgx\_get\_next\_actions. Does not mutate the record.

**type** `string` *required*

Entity type to inspect Options: `workspace`, `project`, `initiative`, `milestone`, `workstream`, `task`, `objective`, `playbook`, `decision`, `artifact`, `run`, `blocker`, `workflow`, `agent`, `skill`, `plan_session`, `stream`, `studio_brand`, `studio_content`, `video_template`.

**id** `string` *required*

Entity UUID or accepted short ID prefix

**hydrate\_context** `boolean`

Include linked context where available; default true

**max\_chars** `integer`

Approximate maximum hydrated context characters

**session\_id** `string`

Optional bootstrap/session identifier

**Required Scopes**: `decisions:read`, `agents:read`, `initiatives:read`, `memory:read`

**Profiles**: v2, legacy, extended, chatgpt, claude-plugin, claude-code-legacy, read-only, memory, commander, planner, executor, observer

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_inspect",
  "args": {
      "type": "workspace",
      "id": "<id>"
  }
}
```

***

### orgx\_launch\_initiative

Launch an existing initiative after OrgX approval, budget, and readiness checks. May dispatch agents, incur model costs, and interact with connected services.

**initiative\_id** `string` *required*

Existing initiative UUID to launch.

**note** `string`

Strongly recommended for destructive or blocking actions (block, flag\_risk, decline, supersede, cancel, delete). Free-text rationale shown in audit history and downstream agent context.

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**session\_id** `string`

Optional OrgX conversation-session context.

**Required Scopes**: `agents:write`, `initiatives:write`

**Profiles**: v2, legacy, extended, chatgpt, commander, planner

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_launch_initiative",
  "args": {
      "initiative_id": "<initiative_id>"
  }
}
```

***

### orgx\_list\_pending\_decisions `read-only`

Read pending decisions awaiting human review in the selected workspace or initiative. Does not resolve decisions or dispatch work.

**initiative\_id** `string`

Initiative UUID used as the parent or scope for this operation.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**session\_id** `string`

Optional OrgX conversation-session context.

**Required Scopes**: `decisions:read`

**Profiles**: v2, legacy, extended, chatgpt, memory, commander, planner, observer

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_list_pending_decisions",
  "args": {}
}
```

***

### orgx\_open\_artifact\_review `read-only`

Read an artifact review packet and open the review widget. Supply an artifact ID, scope the next pending artifact to an entity, or use the authenticated workspace pending queue.

**artifact\_id** `string`

Specific artifact ID to review. Defaults to the next in\_review artifact.

**entity\_id** `string`

Scope to artifacts attached to this entity (initiative, workstream, milestone, or task).

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**Required Scopes**: `initiatives:read`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_open_artifact_review",
  "args": {}
}
```

***

### orgx\_open\_decision\_approval\_review `read-only`

Open human review for a decision with an approval intent. Does not submit an approval, save a rationale, or resume work. The person makes the final choice in the review surface.

**decision\_id** `string` *required*

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**session\_id** `string`

Optional OrgX conversation-session context.

**Required Scopes**: `decisions:write`

**Profiles**: extended

**Availability**: Extended profile model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_open_decision_approval_review",
  "args": {
      "decision_id": "<decision_id>"
  }
}
```

***

### orgx\_open\_decision\_rejection\_review `read-only`

Open human review with a rejection intent. A reason is required by the compatibility gate but is not persisted or submitted. The person enters the final rationale and makes the ruling in the review surface.

**decision\_id** `string` *required*

**reason** `string` *required*

Rationale required by the compatibility rejection-review gate. This opener does not persist or submit it.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**session\_id** `string`

Optional OrgX conversation-session context.

**Required Scopes**: `decisions:write`

**Profiles**: extended

**Availability**: Extended profile model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_open_decision_rejection_review",
  "args": {
      "decision_id": "<decision_id>",
      "reason": "<reason>"
  }
}
```

***

### orgx\_open\_decision\_review `read-only`

Open the complete human review surface for one pending decision. The person selects the ruling; this operation does not approve, reject, or resume work.

**decision\_id** `string` *required*

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**Required Scopes**: `decisions:read`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_open_decision_review",
  "args": {
      "decision_id": "<decision_id>"
  }
}
```

***

### orgx\_pause\_work

Pause a hierarchy node through OrgX lifecycle control, propagating to descendant work and stopping active runs. Does not mark work complete.

**level** `string` *required*

Which hierarchy node to act on Options: `initiative`, `workstream`, `milestone`, `task`, `run`.

**id** `string` *required*

UUID of the node

**Required Scopes**: `agents:write`, `initiatives:write`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_pause_work",
  "args": {
      "level": "initiative",
      "id": "<id>"
  }
}
```

***

### orgx\_read\_plan `read-only`

Read a planning draft by session UUID or plan URI. If omitted, read the most recent active plan in the authenticated workspace.

**session\_id** `string`

Plan session UUID or orgx://plan\_session/\<uuid> URI.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**Required Scopes**: `initiatives:read`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_read_plan",
  "args": {}
}
```

***

### orgx\_reassign\_streams\_work

Recompute or apply supported workstream agent assignments within an initiative through OrgX policy.

**type** `string` *required*

Options: `initiative`.

**id** `string` *required*

Target entity UUID or short ID prefix (8+ hex chars).

**note** `string`

Strongly recommended for destructive or blocking actions (block, flag\_risk, decline, supersede, cancel, delete). Free-text rationale shown in audit history and downstream agent context.

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**session\_id** `string`

Optional OrgX conversation-session context.

**Required Scopes**: `initiatives:write`

**Profiles**: extended

**Availability**: Extended profile model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_reassign_streams_work",
  "args": {
      "type": "initiative",
      "id": "<id>"
  }
}
```

***

### orgx\_record\_plan\_edit

Append a change or feedback summary to the durable plan history. This records guidance only; it does not replace the markdown content or complete the plan.

**session\_id** `string` *required*

Plan session UUID or orgx://plan\_session/\<uuid> URI.

**edit\_summary** `string` *required*

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**Required Scopes**: `initiatives:write`

**Profiles**: v2, legacy, extended, chatgpt, commander, planner, executor, observer

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_record_plan_edit",
  "args": {
      "session_id": "<session_id>",
      "edit_summary": "<edit_summary>"
  }
}
```

***

### orgx\_reopen\_work

Reopen a completed task through OrgX lifecycle validation.

**type** `string` *required*

Options: `task`.

**id** `string` *required*

Target entity UUID or short ID prefix (8+ hex chars).

**note** `string`

Strongly recommended for destructive or blocking actions (block, flag\_risk, decline, supersede, cancel, delete). Free-text rationale shown in audit history and downstream agent context.

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**session\_id** `string`

Optional OrgX conversation-session context.

**Required Scopes**: `initiatives:write`

**Profiles**: extended

**Availability**: Extended profile model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_reopen_work",
  "args": {
      "type": "task",
      "id": "<id>"
  }
}
```

***

### orgx\_request\_independent\_artifact\_review

Queue an independent evaluator for a completed artifact. OrgX chooses the evaluator and persists the assessment. May incur model costs or use external providers; the producing agent cannot choose the score.

**artifact\_id** `string` *required*

Completed work\_artifacts UUID to evaluate

**Required Scopes**: `initiatives:write`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_request_independent_artifact_review",
  "args": {
      "artifact_id": "<artifact_id>"
  }
}
```

***

### orgx\_request\_plan\_critique

Submit a markdown draft for OrgX critique and update the planning session. May invoke an external model and incur costs. Does not dispatch executable work.

**session\_id** `string` *required*

Plan session UUID or orgx://plan\_session/\<uuid> URI.

**plan\_content** `string` *required*

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**Required Scopes**: `initiatives:write`

**Profiles**: extended

**Availability**: Extended profile model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_request_plan_critique",
  "args": {
      "session_id": "<session_id>",
      "plan_content": "<plan_content>"
  }
}
```

***

### orgx\_resume\_work

Resume paused work through canonical OrgX recovery, preserving attempt lineage and redispatching where permitted. Can incur costs and connected-service effects.

**level** `string` *required*

Which hierarchy node to act on Options: `initiative`, `workstream`, `milestone`, `task`, `run`.

**id** `string` *required*

UUID of the node

**Required Scopes**: `agents:write`, `initiatives:write`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_resume_work",
  "args": {
      "level": "initiative",
      "id": "<id>"
  }
}
```

***

### orgx\_retry\_work

Retry eligible work through canonical OrgX recovery, preserving attempt lineage and redispatching where permitted. Can incur costs and connected-service effects.

**level** `string` *required*

Which hierarchy node to act on Options: `initiative`, `workstream`, `milestone`, `task`, `run`.

**id** `string` *required*

UUID of the node

**Required Scopes**: `agents:write`, `initiatives:write`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_retry_work",
  "args": {
      "level": "initiative",
      "id": "<id>"
  }
}
```

***

### orgx\_save\_plan

Save the full markdown draft in OrgX only if the required expected revision is current. Optionally record an edit summary. Does not complete planning or dispatch work.

**session\_id** `string` *required*

Plan session UUID or orgx://plan\_session/\<uuid> URI.

**plan\_content** `string` *required*

**title** `string`

Display title for the new work record.

**edit\_summary** `string`

**expected\_version** `integer` *required*

Authoritative plan\_ref.version from the most recent read. Required to prevent overwriting another edit.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**Required Scopes**: `initiatives:write`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_save_plan",
  "args": {
      "session_id": "<session_id>",
      "plan_content": "<plan_content>",
      "expected_version": 1
  }
}
```

***

### orgx\_search

Search authorized OrgX work, decisions, artifacts, memory, and plan sessions using typed filters and optional text. Mixed relevance searches record metered MCP allowance usage without changing work records. Follow next\_call for pagination. Full context is available through orgx\_inspect, priorities through orgx\_get\_next\_actions, and receipt ledger searches through orgx\_list\_work\_receipts.

**created\_from** `string`

Inclusive creation timestamp, ISO 8601 with a timezone. Applied before ranking/pagination.

**created\_to** `string`

Inclusive creation timestamp, ISO 8601 with a timezone. Retention rules still apply.

**query** `string`

Search query for memory or title/text matching

**type** `string`

Optional entity type filter, such as task, milestone, decision, artifact, or initiative. Omit with query for a mixed relevance search across memory-backed entity types. Options: `workspace`, `project`, `initiative`, `milestone`, `workstream`, `task`, `objective`, `playbook`, `decision`, `artifact`, `run`, `blocker`, `workflow`, `agent`, `skill`, `plan_session`, `stream`, `studio_brand`, `studio_content`, `video_template`.

**status** `string`

Optional status filter

**initiative\_id** `string`

Initiative UUID used as the parent or scope for this operation.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**limit** `integer`

Maximum records to return

**offset** `integer`

Typed-search pagination offset. Prefer cursor when next\_call returns one.

**cursor** `string`

Opaque typed-search cursor returned by pagination.next\_cursor or next\_call.

**fields** `string[]`

Optional compact field list

**session\_id** `string`

Optional OrgX conversation-session context.

**Required Scopes**: `decisions:read`, `agents:read`, `initiatives:read`, `memory:read`

**Profiles**: v2, legacy, extended, chatgpt, claude-plugin, claude-code-legacy, read-only, memory, commander, planner, executor, observer

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_search",
  "args": {}
}
```

***

### orgx\_ship\_batch\_work

Complete eligible milestone tasks using a shared typed proof artifact and OrgX proof-chain checks.

**type** `string` *required*

Options: `milestone`.

**id** `string` *required*

Target entity UUID or short ID prefix (8+ hex chars).

**note** `string`

Strongly recommended for destructive or blocking actions (block, flag\_risk, decline, supersede, cancel, delete). Free-text rationale shown in audit history and downstream agent context.

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**session\_id** `string`

Optional OrgX conversation-session context.

**artifact** `object` *required*

**verification** `string[]`

**quality\_score** `number`

**Required Scopes**: `initiatives:write`

**Profiles**: extended

**Availability**: Extended profile model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_ship_batch_work",
  "args": {
      "type": "milestone",
      "id": "<id>",
      "artifact": {
          "artifact_type": "<artifact_type>"
      }
  }
}
```

***

### orgx\_start\_agent\_task

Dispatch one existing OrgX task under budget, deadline, acceptance, eligibility, and permission policy. Can incur model costs and act on connected services within the declared effect constraints.

**task\_id** `string` *required*

Existing task UUID to dispatch.

**initiative\_id** `string`

Initiative UUID used as the parent or scope for this operation.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**agent\_type** `string`

Specialist domain, such as engineering, design, sales, marketing, or operations.

**instructions** `string`

Delegation instructions. When supplied for existing work, overrides its description for this request.

**model\_tier** `string`

Optional model tier override. Omit to let OrgX auto-route from task complexity. Legacy local/sonnet/opus are accepted for older clients. Options: `standard`, `balanced`, `precision`, `local`, `sonnet`, `opus`.

**model** `string`

Optional exact model identifier when the user explicitly selects one. Otherwise OrgX resolves the model from task, tier, provider, policy, and budget.

**provider** `string`

Optional provider preference. Use auto unless the user asks for a specific provider or a cost comparison selects one. Options: `auto`, `openai`, `anthropic`, `openrouter`, `groq`, `local`.

**runtime** `string`

Optional runtime OrgX runs the work on. Omit or auto to let OrgX choose. cloud\_claude / cloud\_openai: OrgX cloud on the Claude Agent SDK or OpenAI Responses. managed\_openai / managed\_anthropic: the OpenAI Agents API or Claude Managed Agents under OrgX governance. local: a paired local peer (Claude Code, Codex, OpenClaw) on the user machine. Options: `auto`, `cloud_claude`, `cloud_openai`, `managed_openai`, `managed_anthropic`, `local`.

**deadline** `string`

Optional ISO-8601 instant by which the work must finish (e.g. "2026-09-28T17:00:00Z"). Validated and recorded; free text is rejected because a constraint that cannot be evaluated is not a constraint.

**max\_cost\_usd** `number`

Optional hard cost ceiling in USD for this dispatch. If the estimate exceeds it, OrgX blocks, downgrades, or requests approval before dispatch.

**budget\_mode** `string`

Optional budget posture. Use cheapest\_valid for controlled validation runs while reliability is being proven. Options: `cheapest_valid`, `balanced`, `highest_quality`.

**max\_parallel** `integer`

Optional cap on concurrent workers for this dispatch. Work that shares a repository is usually integration-bound well below this: more workers add merge contention, not throughput.

**expected\_artifacts** `string[]`

Optional expected final-output labels. Declaring at least one adds an artifact contract to the run.

**effects** `object`

Optional declared effect scope for the work. Recorded on the run and shown in the receipt. Declaring an effect never grants it — the platform intersects it with the caller authority.

**acceptance** `object[]`

Optional acceptance checks that define what counts as done. Declared BEFORE the work and hashed at dispatch. A check that already passes on the pre-state is reported as non-discriminating and excluded from the verdict.

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**session\_id** `string`

Optional OrgX conversation-session context.

**Required Scopes**: `agents:write`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_start_agent_task",
  "args": {
      "task_id": "<task_id>"
  }
}
```

***

### orgx\_start\_plan

Create a durable planning draft with a title and optional initial markdown. An optional retry key replays the same unedited draft; conflicting content or a draft edited since creation returns a conflict. Does not create executable work or dispatch agents.

**title** `string` *required*

Display title for the new work record.

**initial\_plan** `string`

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**Required Scopes**: `initiatives:write`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_start_plan",
  "args": {
      "title": "<title>"
  }
}
```

***

### orgx\_start\_work

Start an existing task, milestone, or workstream using its exact supported state transition. Does not launch an initiative.

**type** `string` *required*

Options: `milestone`, `workstream`, `task`.

**id** `string` *required*

Target entity UUID or short ID prefix (8+ hex chars).

**note** `string`

Strongly recommended for destructive or blocking actions (block, flag\_risk, decline, supersede, cancel, delete). Free-text rationale shown in audit history and downstream agent context.

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**session\_id** `string`

Optional OrgX conversation-session context.

**Required Scopes**: `initiatives:write`

**Profiles**: extended

**Availability**: Extended profile model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_start_work",
  "args": {
      "type": "milestone",
      "id": "<id>"
  }
}
```

***

### orgx\_unblock\_work

Clear the supported blocked state of a task after its blocker is resolved.

**type** `string` *required*

Options: `task`.

**id** `string` *required*

Target entity UUID or short ID prefix (8+ hex chars).

**note** `string`

Strongly recommended for destructive or blocking actions (block, flag\_risk, decline, supersede, cancel, delete). Free-text rationale shown in audit history and downstream agent context.

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**session\_id** `string`

Optional OrgX conversation-session context.

**Required Scopes**: `initiatives:write`

**Profiles**: extended

**Availability**: Extended profile model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_unblock_work",
  "args": {
      "type": "task",
      "id": "<id>"
  }
}
```

***

### orgx\_update\_work

Apply a nonempty typed content patch to initiative, workstream, milestone, or task. Permits text, priority, dates, objectives, notes, and tags; cannot change workflow status, approvals, ownership authority, or execution policy.

**type** `string` *required*

Options: `initiative`, `workstream`, `milestone`, `task`.

**id** `string` *required*

**fields** `object` *required*

**idempotency\_key** `string`

Stable retry key for this request. Reuse it only with identical input.

**session\_id** `any`

**Required Scopes**: `initiatives:write`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_update_work",
  "args": {
      "type": "initiative",
      "id": "<id>",
      "fields": {}
  }
}
```

***

### orgx\_validate\_initiative\_plan `read-only`

Validate a deterministic hierarchy and source evidence in OrgX; return its digest and structural findings. Does not create records, launch agents, or invoke paid generation.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when unambiguous.

**plan** `object` *required*

Deterministic initiative hierarchy. Dependencies reference task titles or workstream names supported by OrgX.

**source\_evidence** `object`

**Required Scopes**: `initiatives:read`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_validate_initiative_plan",
  "args": {
      "plan": {
          "initiative": {
              "title": "<title>"
          },
          "workstreams": [
              {
                  "name": "<name>"
              }
          ]
      }
  }
}
```

***

### orgx\_validate\_studio\_content `read-only`

Check the required template and structured content of one studio video specification before rendering. Returns the OrgX validation result.

**id** `string` *required*

**spec** `object` *required*

**note** `string`

**Required Scopes**: `initiatives:write`

**Profiles**: extended

**Availability**: Extended profile model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_validate_studio_content",
  "args": {
      "id": "<id>",
      "spec": {
          "template": "<template>",
          "content": {}
      }
  }
}
```

***

## Portable Work Receipts

5 tools for portable work receipts operations.

### orgx\_get\_receipt\_review\_queue `read-only`

Read the workspace calls waiting for a person: outcome, work type, entity mapping, area, links and proposed criteria. Results are suggestions with confidence, not verified facts. Human outcome judgments and criterion confirmations are made in the OrgX review UI; this tool cannot resolve them.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated workspace.

**kind** `string`

Options: `mapping`, `area`, `link`, `work_type`, `outcome`, `criterion`.

**limit** `integer`

Default: `25`.

**Required Scopes**: `initiatives:read`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_get_receipt_review_queue",
  "args": {}
}
```

***

### orgx\_get\_work\_receipt `read-only`

Read a receipt by its ledger UUID or opaque producer receipt ID in one workspace. Returns bounded evidence and criteria, producer claims, the separately recorded human outcome, related workstream and uncertainty. Reading cannot verify or accept work. The full document remains in OrgX.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated workspace.

**receipt\_id** `string` *required*

**Required Scopes**: `initiatives:read`

**Profiles**: v2, legacy, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_get_work_receipt",
  "args": {
      "receipt_id": "<receipt_id>"
  }
}
```

***

### orgx\_list\_work\_receipts `read-only`

Read one bounded workspace ledger view: receipts (default), workstreams, or review. Receipt search accepts free text and exact filters: outcome, verification, accepted, type, area, repo, actor, ws, entity, initiative, pr, file, since, until, conf, unmet and status, within the 120-day window. Workstreams retain receipt rollups and confirmed mappings; review returns pending human calls and criterion proposals. Results distinguish producer claims from human judgments. Follow validated next\_calls; no view resolves judgments, runs model inference, or changes work.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated workspace.

**view** `string`

Read-only ledger projection. Existing calls default to receipt search. Options: `receipts`, `workstreams`, `review`. Default: `"receipts"`.

**query** `string`

Default: `""`.

**kind** `string`

Optional review kind, valid only with view=review. Options: `mapping`, `area`, `link`, `work_type`, `outcome`, `criterion`.

**limit** `integer`

Default: `25`.

**Required Scopes**: `initiatives:read`

**Profiles**: v2, legacy, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_list_work_receipts",
  "args": {}
}
```

***

### orgx\_submit\_work\_receipt

Import one portable Agent Work Receipt v0.1 or v0.2 into the authenticated workspace ledger. Preserves the full document, including identified criteria, evidence, provenance, lineage and review extensions. Producer outcome, verification and acceptance are claims; import does not verify, accept or complete work. The canonical import enforces document limits, reserved harness names, workspace quota and content-bound idempotency. Never falls back to a legacy write after rejection.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated workspace.

**receipt** `object` *required*

Complete portable Agent Work Receipt. Use v0.2 for identified criteria and evidence-linked results. Standard metadata and namespaced extensions carry producer data, never executable commands.

**idempotency\_key** `string`

Retry key bound to this document. Omit to use its content hash.

**Required Scopes**: `initiatives:write`

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_submit_work_receipt",
  "args": {
      "receipt": {
          "schema_version": "agent-work-receipt/v0.1",
          "receipt_id": "<receipt_id>",
          "intent": {
              "summary": "<summary>"
          },
          "actor": {
              "type": "agent",
              "id": "<id>"
          },
          "authority": {
              "mode": "explicit",
              "status": "granted",
              "scope": {
                  "actions": [],
                  "resources": []
              }
          },
          "actions": [
              {
                  "id": "<id>",
                  "type": "<type>",
                  "summary": "<summary>",
                  "status": "planned"
              }
          ],
          "artifacts": [],
          "evidence": [
              {
                  "id": "<id>",
                  "kind": "<kind>",
                  "summary": "<summary>",
                  "observed_at": "<observed_at>"
              }
          ],
          "outcome": {
              "status": "succeeded",
              "summary": "<summary>"
          },
          "verification": {
              "status": "unverified",
              "method": "<method>",
              "checks": [],
              "evidence_ids": []
          },
          "cost": {
              "currency": "<currency>",
              "total": 0
          },
          "lineage": {
              "parent_receipt_refs": [],
              "references": []
          },
          "human_interventions": [],
          "timestamps": {
              "started_at": "<started_at>",
              "completed_at": "<completed_at>",
              "issued_at": "<issued_at>"
          }
      }
  }
}
```

***

### orgx\_validate\_work\_receipt `read-only`

Check one portable Agent Work Receipt v0.1 or v0.2 for schema and reference conformance without storing it. Checks identified criteria, evidence references and known review extensions. Conformance validates the document, not whether its evidence is true or whether work was accepted. Import separately enforces hosted compatibility and admission policy.

**receipt** `object` *required*

**Authentication**: Account-free

**Profiles**: v2, extended, chatgpt

**Availability**: Default ChatGPT and v2 model operation.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_validate_work_receipt",
  "args": {
      "receipt": {
          "schema_version": "agent-work-receipt/v0.1",
          "receipt_id": "<receipt_id>",
          "intent": {
              "summary": "<summary>"
          },
          "actor": {
              "type": "agent",
              "id": "<id>"
          },
          "authority": {
              "mode": "explicit",
              "status": "granted",
              "scope": {
                  "actions": [],
                  "resources": []
              }
          },
          "actions": [
              {
                  "id": "<id>",
                  "type": "<type>",
                  "summary": "<summary>",
                  "status": "planned"
              }
          ],
          "artifacts": [],
          "evidence": [
              {
                  "id": "<id>",
                  "kind": "<kind>",
                  "summary": "<summary>",
                  "observed_at": "<observed_at>"
              }
          ],
          "outcome": {
              "status": "succeeded",
              "summary": "<summary>"
          },
          "verification": {
              "status": "unverified",
              "method": "<method>",
              "checks": [],
              "evidence_ids": []
          },
          "cost": {
              "currency": "<currency>",
              "total": 0
          },
          "lineage": {
              "parent_receipt_refs": [],
              "references": []
          },
          "human_interventions": [],
          "timestamps": {
              "started_at": "<started_at>",
              "completed_at": "<completed_at>",
              "issued_at": "<issued_at>"
          }
      }
  }
}
```

***

## Human Widget Operations

3 tools for human widget operations operations.

### orgx\_widget\_approve\_artifact

Widget-only: record a person’s approval of the displayed artifact using its hidden, version-bound capability. Refuses stale, foreign, missing, or replayed capabilities. Applies OrgX review and continuation rules.

**artifact\_id** `string` *required*

**workspace\_id** `string`

**approval\_token** `string` *required*

Capability from hidden widget metadata, supplied by a person’s click.

**expected\_version** `integer`

**note** `string`

**Required Scopes**: `initiatives:write`

**Profiles**: v2, legacy, extended, chatgpt

**Availability**: Human widget callback; unavailable to the model.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_widget_approve_artifact",
  "args": {
      "artifact_id": "<artifact_id>",
      "approval_token": "<approval_token>"
  }
}
```

***

### orgx\_widget\_request\_artifact\_changes

Widget-only: record a person’s requested changes to the displayed artifact using its hidden, version-bound capability and required feedback. Applies the canonical OrgX rework flow and may dispatch connected agent work.

**artifact\_id** `string` *required*

**workspace\_id** `string`

**approval\_token** `string` *required*

Capability from hidden widget metadata, supplied by a person’s click.

**expected\_version** `integer`

**note** `string` *required*

**Required Scopes**: `initiatives:write`

**Profiles**: v2, legacy, extended, chatgpt

**Availability**: Human widget callback; unavailable to the model.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_widget_request_artifact_changes",
  "args": {
      "artifact_id": "<artifact_id>",
      "approval_token": "<approval_token>",
      "note": "<approval_note>"
  }
}
```

***

### orgx\_widget\_select\_workspace

Widget-only: select the person’s authorized workspace for this connection. Updates private session continuity; does not create or change work.

**workspace\_id** `string` *required*

**Required Scopes**: `initiatives:read`

**Profiles**: v2, legacy, extended, chatgpt

**Availability**: Human widget callback; unavailable to the model.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_widget_select_workspace",
  "args": {
      "workspace_id": "<workspace_id>"
  }
}
```

***

## Legacy and internal: Recommended Entry Points

4 tools for recommended entry points operations.

### approve\_agent\_work

Use when agent work is paused waiting for a human yes — list pending decisions and open the human review surface. Listing may record usage or session state, so this tool is not read-only. Approval and rejection are human-session-only: those actions return a review URL and never resolve the item or resume work from MCP. Also known as: pending approvals, agent blocked, sign off, review decisions, approve AI work.

Per-action input requirements:
• action="list" (default when action omitted) → No required fields. Optional filters: limit, urgency\_filter, initiative\_id.
• action="approve" → REQUIRES decision\_id. Returns the human-session review URL; MCP does not self-approve.
• action="reject"  → REQUIRES decision\_id AND reason. Returns the human-session review URL; MCP does not self-reject.

**decision\_id** `string`

REQUIRED when action="approve" or action="reject". Decision UUID from the pending approvals list.

**action** `string`

Operation to perform. Defaults to "list" (returns pending approvals). "approve" and "reject" validate the request and return the human-session review URL without resolving the decision. Options: `list`, `approve`, `reject`.

**note** `string`

Optional compatibility field for action="approve". MCP does not persist it; enter the final rationale in the human review session.

**reason** `string`

REQUIRED for action="reject" before returning the human-session review URL. MCP does not persist or submit this reason.

**limit** `number`

Used only when action="list" (or omitted). Max pending decisions to return.

**urgency\_filter** `string`

Used only when action="list". Filters the returned pending decisions by urgency. Options: `all`, `critical`, `high`.

**initiative\_id** `string`

Used only when action="list". Scopes pending decisions to a specific initiative UUID.

**workspace\_id** `string`

Used only when action="list". Scopes pending decisions to a specific workspace UUID. Defaults to the MCP session workspace when omitted.

**Required Scopes**: `decisions:write`

**Profiles**: legacy

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "approve_agent_work",
  "args": {}
}
```

***

### delegate\_agent\_task

Use when the user says "delegate this and tell me when it's done" — assign work to a specialist AI agent that owns the task and reports back with results. Also known as: hand this off, spawn agent, assign task, delegate to agent, have an AI agent do it.

**agent** `string` *required*

Target agent identifier or alias

**task** `string` *required*

Task instructions for the target agent

**context** `string`

Optional supporting context or background for the task

**initiative\_id** `string`

Optional initiative UUID to associate with the spawned task

**initiative\_name** `string`

Optional initiative title to resolve automatically if ID is unknown

**style\_guidelines** `string`

Optional voice, format, or style constraints

**deadline** `string`

Optional ISO-8601 instant by which the work must finish (e.g. "2026-09-28T17:00:00Z"). Validated and recorded; free text is rejected because a constraint that cannot be evaluated is not a constraint.

**max\_cost\_usd** `number`

Optional hard cost ceiling in USD for this dispatch. If the estimate exceeds it, OrgX blocks, downgrades, or requests approval before dispatch.

**budget\_mode** `string`

Optional budget posture. Use cheapest\_valid for controlled validation runs while reliability is being proven. Options: `cheapest_valid`, `balanced`, `highest_quality`.

**max\_parallel** `integer`

Optional cap on concurrent workers for this dispatch. Work that shares a repository is usually integration-bound well below this: more workers add merge contention, not throughput.

**expected\_artifacts** `string[]`

Optional expected final-output labels. Declaring at least one adds an artifact contract to the run.

**effects** `object`

Optional declared effect scope for the work. Recorded on the run and shown in the receipt. Declaring an effect never grants it — the platform intersects it with the caller authority.

**acceptance** `object[]`

Optional acceptance checks that define what counts as done. Declared BEFORE the work and hashed at dispatch. A check that already passes on the pre-state is reported as non-discriminating and excluded from the verdict.

**idempotency\_key** `string`

Optional client-supplied idempotency key for safe retries. The same key returns the same dispatch result without re-running the work.

**Required Scopes**: `agents:write`

**Profiles**: legacy

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "delegate_agent_task",
  "args": {
      "agent": "<agent_id>",
      "task": "<task>"
  }
}
```

***

### recall\_memory `read-only`

Use when the user asks "what did we decide about X" or prior context must be recovered from team memory. Searches organizational memory for prior decisions, artifacts, project context, and team knowledge. Also known as: search memory, recall decisions, find context, retrieve artifacts, what did we decide.

**query** `string` *required*

Search query for organizational memory

**scope** `string`

Optional scope filter. "all" (default) includes the work ledger; "ledger" searches only receipts, work sessions, and outreach touches. Options: `all`, `artifacts`, `decisions`, `initiatives`, `ledger`.

**limit** `number`

Maximum number of results to return

**Required Scopes**: `memory:read`

**Profiles**: legacy

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "recall_memory",
  "args": {
      "query": "<search_query>"
  }
}
```

***

### track\_project\_progress `read-only`

Use when the user asks how a project is going, what is blocked, or whether an initiative is on track. Returns health, blockers, milestones, owners, and recent activity. Also known as: project status, initiative pulse, blockers, roadmap progress, execution health.

**initiative\_id** `string`

Optional initiative UUID to check

**initiative\_name** `string`

Optional initiative title to resolve automatically if ID is unknown

**Required Scopes**: `initiatives:read`

**Profiles**: legacy

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "track_project_progress",
  "args": {}
}
```

***

## Decisions

6 tools for decisions operations.

### approve\_decision

Use when the user asks to approve a pending decision. Also known as: sign off, approve AI work, unblock agent, accept decision. A model cannot settle a decision: this returns where the person decides, either the Approve button in the decisions widget (ordinary decisions) or the decision page in OrgX (review\_url). USE WHEN: user says to approve a decision returned from the deprecated alias with type=decision and status=pending (or the legacy get\_pending\_decisions alias). NEXT: Show the decisions widget or give the user the review\_url; never say the decision was approved. DO NOT USE: to claim an approval happened. Requires decisions:write.

**decision\_id** `string` *required*

Decision ID to approve

**note** `string`

Optional note recorded with the approval

**option\_id** `string`

Optional decision option id when the decision includes selectable options.

**Required Scopes**: `decisions:write`

**Profiles**: legacy

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "approve_decision",
  "args": {
      "decision_id": "<decision_id>"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "decision_id": "dec_abc123",
  "status": "approved",
  "artifact_id": "art_xyz789",
  "resolved_at": "2026-02-26T10:05:00Z"
}
```

***

### get\_decision\_history `read-only`

Recall past decisions about a topic, project, customer, feature, or artifact. Also known as: decision log, what did we decide, prior approvals. USE WHEN: older clients still call this tool directly. NEXT: Present results with context; suggest approve\_decision or reject\_decision if relevant pending ones exist. DO NOT USE: for new prompts or skills. Read-only. Compatibility alias retained for older clients. Prefer `the deprecated alias` with scope=decisions with a topic query for new prompts, skills, and examples.

**topic** `string` *required*

Topic or theme to search decision history for

**initiative\_id** `string`

Optional initiative UUID to scope decision history

**limit** `number`

Maximum number of historical decisions to return

**Required Scopes**: `decisions:read`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "get_decision_history",
  "args": {
      "topic": "<topic>"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "decisions": [
    {
      "id": "dec_abc123",
      "type": "approval",
      "status": "approved",
      "resolved_by": "user_123",
      "resolved_at": "2026-02-26T10:05:00Z"
    }
  ],
  "total": 42,
  "cursor": "cur_next"
}
```

***

### get\_pending\_decisions `read-only`

List agent decisions and work items awaiting human approval. Also known as: pending approvals, agent blocked, sign off, review decisions, approve AI work. USE WHEN: older clients still call this tool directly. NEXT: Present each decision with title and urgency, then ask which to approve\_decision or reject\_decision. DO NOT USE: for new prompts or skills. Read-only. Compatibility alias retained for older clients. Prefer `the deprecated alias` with type=decision and status=pending for new prompts, skills, and examples.

**limit** `number`

Maximum number of decisions to return

**urgency\_filter** `string`

Optional urgency filter for the pending decision list Options: `all`, `critical`, `high`.

**initiative\_id** `string`

Optional initiative UUID to scope pending decisions

**workspace\_id** `string`

Optional workspace UUID to scope pending decisions

**Required Scopes**: `decisions:read`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "get_pending_decisions",
  "args": {}
}
```

**Response**:

```json theme={"dark"}
{
  "decisions": [
    {
      "id": "dec_abc123",
      "type": "approval",
      "title": "Campaign brief ready for Q1 launch",
      "urgency": "high",
      "agent": "marketing-agent",
      "artifact_id": "art_xyz789",
      "created_at": "2026-02-26T10:00:00Z"
    }
  ],
  "total": 4,
  "cursor": null
}
```

***

### orgx\_panel\_snapshot `read-only`

App-only: the OrgX panel in the ChatGPT sidebar and beside a conversation. Returns what needs your decision (most urgent first), the review packet for one of them, the last output a person accepted, and, when asked, the work agents are running. USE WHEN: the OrgX panel opens or refreshes. NEXT: the panel shows Approve and Send back when the decision can be settled there, otherwise it links to the decision in OrgX. DO NOT USE: from a model; models read decisions with orgx\_search. Read-only. Work receipts are read with orgx\_list\_work\_receipts and orgx\_get\_work\_receipt.

**focus** `object`

Optional decision to show as the review packet. Defaults to the most urgent pending decision.

**view** `string`

Optional panel view: running work, authorized workspace membership, or settled decisions. Options: `work`, `workspaces`, `history`.

**range** `string`

For decision history: today, 7d or 30d. Defaults to 7d. Options: `today`, `7d`, `30d`.

**Required Scopes**: `initiatives:read`

**Profiles**: v2, legacy, extended, chatgpt

**Availability**: Human widget callback; unavailable to the model.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_panel_snapshot",
  "args": {}
}
```

***

### orgx\_widget\_receipt\_call

App-only: records a person's call on a Work Ledger receipt from the OrgX panel: done, partly done, not done or blocked. The ledger keeps the latest call per receipt; it overrides the agent's own guess and teaches OrgX what done means. USE WHEN: the person presses a call on a receipt in the OrgX panel. DO NOT USE: from a model; models read receipts with orgx\_get\_work\_receipt or orgx\_list\_work\_receipts.

**receipt\_id** `string` *required*

The Work Ledger receipt the call is about.

**status** `string` *required*

The person's call on the outcome. Options: `succeeded`, `partially_succeeded`, `failed`, `blocked`.

**approval\_token** `string` *required*

Hidden receipt capability supplied by the widget after a person clicks.

**Required Scopes**: `decisions:write`, `agents:write`, `initiatives:write`

**Profiles**: v2, legacy, extended, chatgpt

**Availability**: Human widget callback; unavailable to the model.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_widget_receipt_call",
  "args": {
      "receipt_id": "<receipt_id>",
      "status": "succeeded",
      "approval_token": "<approval_token>"
  }
}
```

***

### reject\_decision

Use when the user wants to reject a pending decision or send the agent back with revisions. Also known as: request revisions, send feedback, decline decision. A model cannot settle a decision: this returns where the person decides, either the decisions widget (ordinary decisions) or the decision page in OrgX (review\_url). USE WHEN: user wants to reject or request revisions on a decision. NEXT: Show the decisions widget or give the user the review\_url; never say the decision was rejected. DO NOT USE: without a reason, and never to claim a rejection happened. Requires decisions:write.

**decision\_id** `string` *required*

Decision ID to reject

**reason** `string` *required*

Reason for rejecting the decision

**option\_id** `string`

Optional decision option id when the decision includes selectable options.

**Required Scopes**: `decisions:write`

**Profiles**: legacy

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "reject_decision",
  "args": {
      "decision_id": "<decision_id>",
      "reason": "<reason>"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "decision_id": "dec_abc123",
  "status": "rejected",
  "resolved_at": "2026-02-26T10:05:00Z"
}
```

***

## Legacy and internal: Agents

4 tools for agents operations.

### get\_agent\_status

Use when the user asks what agents are working on right now, whether delegated work is still running, or why nothing has landed yet. Successful calls record metered MCP allowance usage but do not change business records. Also known as: agent status, what agents are doing, active runs. USE WHEN: user asks about agent activity, progress, or what agents are working on. NEXT: If agents are stuck, use orgx\_search or orgx\_inspect to read the related blocker context. DO NOT USE: to check initiative health — use get\_initiative\_pulse instead.

**agent\_id** `string`

Optional agent ID to inspect

**workspace\_id** `string`

Optional workspace UUID to scope agent status

**command\_center\_id** `string`

Deprecated alias for workspace\_id

**initiative\_id** `string`

Optional initiative UUID to scope agent status

**include\_idle** `boolean`

Include idle agents in the response

**Required Scopes**: `agents:read`

**Profiles**: legacy, claude-plugin, claude-code-legacy

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "get_agent_status",
  "args": {}
}
```

**Response**:

```json theme={"dark"}
{
  "agent_type": "engineering-agent",
  "status": "idle",
  "current_task_id": null,
  "completed_tasks": 12,
  "trust_level": "act_with_approval"
}
```

***

### handoff\_task

Use when in-flight work must move to a different specialist agent without losing its context or execution state. Also known as: handoff task, transfer work, change assignee. USE WHEN: a task needs to be reassigned to a different specialist agent. NEXT: Use get\_agent\_status to confirm the new agent picked up the task. DO NOT USE: for new tasks — use spawn\_agent\_task instead.

**task\_id** `string` *required*

Task UUID to hand off

**agent** `string` *required*

Target agent (e.g., "engineering-agent", "marketing-agent")

**note** `string`

Handoff note: what to do, constraints, context, definition of done

**reason** `string`

Alias for note, accepted from older callers. note wins when both are sent.

**spawn** `boolean`

If true (default), spawn a new agent run for the target agent

**deadline** `string`

Optional ISO-8601 instant by which the work must finish (e.g. "2026-09-28T17:00:00Z"). Validated and recorded; free text is rejected because a constraint that cannot be evaluated is not a constraint.

**max\_cost\_usd** `number`

Optional hard cost ceiling in USD for this dispatch. If the estimate exceeds it, OrgX blocks, downgrades, or requests approval before dispatch.

**budget\_mode** `string`

Optional budget posture. Use cheapest\_valid for controlled validation runs while reliability is being proven. Options: `cheapest_valid`, `balanced`, `highest_quality`.

**max\_parallel** `integer`

Optional cap on concurrent workers for this dispatch. Work that shares a repository is usually integration-bound well below this: more workers add merge contention, not throughput.

**expected\_artifacts** `string[]`

Optional expected final-output labels. Declaring at least one adds an artifact contract to the run.

**effects** `object`

Optional declared effect scope for the work. Recorded on the run and shown in the receipt. Declaring an effect never grants it — the platform intersects it with the caller authority.

**acceptance** `object[]`

Optional acceptance checks that define what counts as done. Declared BEFORE the work and hashed at dispatch. A check that already passes on the pre-state is reported as non-discriminating and excluded from the verdict.

**idempotency\_key** `string`

Optional client-supplied idempotency key for safe retries. The same key returns the same dispatch result without re-running the work.

**Required Scopes**: `agents:write`, `initiatives:write`

**Profiles**: legacy

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "handoff_task",
  "args": {
      "task_id": "<task_id>",
      "agent": "<agent_id>"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "task_id": "tsk_abc123",
  "from_agent": "product-agent",
  "to_agent": "engineering-agent",
  "status": "handed_off"
}
```

***

### recommend\_next\_action `read-only`

Use this tool to recommend what should happen next after time away or when priority is unclear. It ranks progress gaps, blockers, and execution templates. Pass agent\_id or domain for an agent-owned runnable queue instead of the workspace-wide operator queue. Also known as: next best action, prioritize work, unblock project. USE WHEN: the user asks what to do next or needs help prioritizing. NEXT: Execute the recommended action (the deprecated alias, spawn\_agent\_task, etc.). DO NOT USE: when the user already knows what they want to do. Read-only.

**entity\_type** `string`

Entity type to recommend for (default: workspace) Options: `workspace`, `initiative`, `workstream`, `milestone`.

**entity\_id** `string`

Entity ID. For workspace, use "default" or a workspace ID.

**initiative\_id** `string`

Shortcut for entity\_type="initiative" with entity\_id=\<this id>. Ignored when entity\_type or entity\_id is set.

**workspace\_id** `string`

Optional workspace ID to scope recommendations (canonical).

**command\_center\_id** `string`

Deprecated alias for workspace\_id.

**agent\_id** `string`

Optional canonical agent ID. When present, only return work assigned to that agent.

**domain** `string`

Optional agent domain used to derive the canonical agent ID when agent\_id is omitted. Options: `engineering`, `product`, `design`, `marketing`, `sales`, `operations`, `orchestration`.

**canonical\_only** `boolean`

When true, return only the canonical next task linked to the active goal.

**limit** `number`

Max recommendations to return (default 5, max 25)

**cascade** `boolean`

If true, refresh recommendations across the entity chain first

**Required Scopes**: `initiatives:read`

**Profiles**: legacy

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "recommend_next_action",
  "args": {}
}
```

**Response**:

```json theme={"dark"}
{
  "recommendation": {
    "action": "approve_decision",
    "target_id": "dec_abc123",
    "confidence": 0.92
  }
}
```

***

### spawn\_agent\_task

Use when the user says "delegate this and tell me when it's done" — assign work to a specialist AI agent that owns the task and reports back with results. Also known as: hand this off, assign task, spawn agent, have an agent do it, autonomous work. Automatically checks authorization, rate limits, quality gates, model routing, and budget policy before spawning. Omit model\_tier/provider/model to let OrgX auto-route from task complexity; provide them only when the user or verification plan intentionally constrains routing. Returns modelTier, budget, and run details on success, or blockedReason if spawn is denied. USE WHEN: user explicitly wants to delegate work to an agent. NEXT: Use get\_agent\_status to monitor progress and record\_quality\_score after reviewing output. DO NOT USE: for creating tasks in the hierarchy — use the deprecated alias type=task instead. Requires agents:write.

**agent** `string` *required*

Target agent identifier or alias

**task** `string` *required*

Task instructions for the target agent

**context** `string`

Optional supporting context or background for the task

**initiative\_id** `string`

Optional initiative UUID to associate with the spawned task

**initiative\_name** `string`

Optional: Initiative title to resolve automatically if ID is unknown.

**workstream\_id** `string`

Optional workstream UUID. Bind the spawned run to an existing IWMT workstream so progress rolls up into the scaffolded hierarchy and the agent inherits workstream context (preferred over relying on domain resolution). Initiative is inferred from the workstream if initiative\_id is omitted.

**milestone\_id** `string`

Optional milestone UUID under the workstream to bind the spawned run to.

**task\_id** `string`

Optional task UUID to bind the spawned run to a specific scaffolded task, enabling direct task-level progress rollup. Use the deprecated alias type=task first if the task does not exist yet.

**style\_guidelines** `string`

Optional: Voice/format/style constraints for the agent.

**wait\_for\_completion** `boolean`

Optional: If true and safe, wait briefly for the first result before replying.

**model\_tier** `string`

Optional model tier override. Omit to let OrgX auto-route according to task complexity. Use standard for controlled verification runs; use balanced or precision when explicitly selected by the user, policy, or routing decision. Legacy tiers local/sonnet/opus are accepted for older clients. Options: `standard`, `balanced`, `precision`, `local`, `sonnet`, `opus`.

**model** `string`

Optional exact model identifier when the user explicitly chooses one. Omit to let OrgX resolve the model from task, tier, provider, policy, and budget.

**provider** `string`

Optional provider preference. Use auto unless the user requests a specific provider or the budget/capability comparison has selected one. Options: `auto`, `openai`, `anthropic`, `openrouter`, `groq`, `local`.

**deadline** `string`

Optional ISO-8601 instant by which the work must finish (e.g. "2026-09-28T17:00:00Z"). Validated and recorded; free text is rejected because a constraint that cannot be evaluated is not a constraint.

**max\_cost\_usd** `number`

Optional hard cost ceiling in USD for this dispatch. If the estimate exceeds it, OrgX blocks, downgrades, or requests approval before dispatch.

**budget\_mode** `string`

Optional budget posture. Use cheapest\_valid for controlled validation runs while reliability is being proven. Options: `cheapest_valid`, `balanced`, `highest_quality`.

**max\_parallel** `integer`

Optional cap on concurrent workers for this dispatch. Work that shares a repository is usually integration-bound well below this: more workers add merge contention, not throughput.

**expected\_artifacts** `string[]`

Optional expected final-output labels. Declaring at least one adds an artifact contract to the run.

**effects** `object`

Optional declared effect scope for the work. Recorded on the run and shown in the receipt. Declaring an effect never grants it — the platform intersects it with the caller authority.

**acceptance** `object[]`

Optional acceptance checks that define what counts as done. Declared BEFORE the work and hashed at dispatch. A check that already passes on the pre-state is reported as non-discriminating and excluded from the verdict.

**idempotency\_key** `string`

Optional client-supplied idempotency key for safe retries. The same key returns the same dispatch result without re-running the work.

**execution\_target** `string`

Where to execute: cloud (default), local (on your machine), local\_preferred (try local first), or auto. Options: `auto`, `cloud`, `local`, `local_preferred`.

**sdk\_backend** `string`

Preferred execution backend. Use openai for cloud-safe execution, claude for Claude SDK routing, or auto to let OrgX decide. Options: `auto`, `openai`, `claude`.

**Required Scopes**: `agents:write`

**Profiles**: legacy

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "spawn_agent_task",
  "args": {
      "agent": "<agent_id>",
      "task": "<task>"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "task_id": "tsk_new123",
  "agent_type": "engineering-agent",
  "status": "queued",
  "estimated_start": "2026-02-26T10:10:00Z"
}
```

***

## Legacy and internal: Initiative Monitoring

1 tool for initiative monitoring operations.

### get\_initiative\_pulse

Use when the user asks how a project is going, what is blocked, or whether an initiative is on track. Successful calls record metered MCP allowance usage but do not change business records. Also known as: project status, roadmap progress, execution health, blockers. USE WHEN: user asks how an initiative is going, or wants a status update. NEXT: If blockers exist, use orgx\_inspect for one blocker or orgx\_search for related records. DO NOT USE: for an org-wide brief — use orgx\_recommend with mode=morning\_brief instead.

**initiative\_id** `string`

Optional: Initiative UUID to check.

**initiative\_name** `string`

Optional: Initiative title to resolve automatically if ID is unknown.

**Required Scopes**: `initiatives:read`

**Profiles**: legacy, claude-plugin, claude-code-legacy

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "get_initiative_pulse",
  "args": {}
}
```

**Response**:

```json theme={"dark"}
{
  "initiative_id": "init_abc123",
  "health": "on_track",
  "progress": 0.65,
  "active_workstreams": 3,
  "blocked_tasks": 0,
  "pending_decisions": 1,
  "last_activity": "2026-02-26T09:30:00Z"
}
```

***

## Legacy and internal: Entity Management

6 tools for entity management operations.

### batch\_create\_entities

Inline worker tool for creating multiple related entities with ref-based dependency resolution.

**entities** `object[]` *required*

Entity payloads. Each item must include type and required fields.

**owner\_id** `string`

Optional owner ID applied when item owner is omitted.

**user\_id** `string`

Deprecated alias for owner\_id.

**continue\_on\_error** `boolean`

Continue creating remaining entities after an error.

**concurrency** `number`

Parallel creation concurrency.

**Required Scopes**: Authenticated user

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "batch_create_entities",
  "args": {
      "entities": [
          {}
      ]
  }
}
```

**Response**:

```json theme={"dark"}
{
  "created": [
    {
      "ref": "task1",
      "id": "tsk_aaa",
      "type": "task"
    },
    {
      "ref": "task2",
      "id": "tsk_bbb",
      "type": "task"
    }
  ],
  "total": 2
}
```

***

### batch\_delete\_entities

Inline worker tool for permanently deleting multiple entities in one authenticated call.

**entities** `object[]` *required*

Entities to delete.

**concurrency** `number`

Parallel deletion concurrency.

**continue\_on\_error** `boolean`

Continue deleting remaining entities after an error.

**note** `string`

Optional reason note.

**Required Scopes**: Authenticated user

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "batch_delete_entities",
  "args": {
      "entities": [
          {
              "type": "workspace",
              "id": "<id>"
          }
      ]
  }
}
```

**Response**:

```json theme={"dark"}
{
  "deleted": [
    "tsk_aaa",
    "tsk_bbb"
  ],
  "total": 2
}
```

***

### comment\_on\_entity

Inline worker tool for adding threaded comments, concerns, progress notes, or handoff notes to an entity.

**entity\_type** `string` *required*

Entity type to comment on. Options: `initiative`, `workstream`, `milestone`, `task`, `decision`.

**entity\_id** `string` *required*

Entity ID to attach the comment to.

**body** `string` *required*

Comment body in plain text or markdown.

**parent\_comment\_id** `string`

Optional parent comment ID when replying in-thread.

**comment\_type** `string`

Optional comment classification. Options: `observation`, `concern`, `suggestion`, `progress_note`, `blocker_flag`, `question`, `handoff_note`, `cross_reference`, `note`.

**severity** `string`

Optional severity for triage. Options: `info`, `low`, `medium`, `high`, `critical`.

**tags** `string[]`

Optional tags.

**metadata** `object`

Optional structured metadata.

**Required Scopes**: Authenticated user

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "comment_on_entity",
  "args": {
      "entity_type": "initiative",
      "entity_id": "<entity_id>",
      "body": "<message_body>"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "comment_id": "cmt_abc123",
  "entity_id": "tsk_abc123",
  "body": "Looking good so far!",
  "created_at": "2026-02-26T10:00:00Z"
}
```

***

### list\_entity\_comments

Inline worker tool for reading the comment thread attached to an entity.

**entity\_type** `string` *required*

Entity type to read comments for. Options: `initiative`, `workstream`, `milestone`, `task`, `decision`.

**entity\_id** `string` *required*

Entity ID whose comment thread should be returned.

**limit** `number`

Maximum comments to return.

**Required Scopes**: Authenticated user

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "list_entity_comments",
  "args": {
      "entity_type": "initiative",
      "entity_id": "<entity_id>"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "comments": [
    {
      "id": "cmt_abc123",
      "body": "Looking good!",
      "author": "user_123",
      "created_at": "2026-02-26T10:00:00Z"
    }
  ],
  "total": 1
}
```

***

### scaffold\_initiative

Scaffold an initiative hierarchy to draft, create, or launch it. Returns initiative\_id, ref\_map, and preferred\_next\_calls.

**title** `string` *required*

Initiative title.

**summary** `string`

Initiative summary.

**description** `string`

Initiative description.

**workspace\_id** `string`

Workspace UUID; required unless session context provides one.

**objective\_ids** `string[]`

Preferred objective UUIDs.

**goal\_ids** `string[]`

Objective UUID alias for API compatibility.

**mode** `string`

Draft validates, scaffold creates records, launch creates and starts follow-up work. Options: `draft`, `scaffold`, `launch`.

**response\_mode** `string`

Return after durable creation or wait for launch follow-ups. Options: `fast_ack`, `complete`.

**workstreams** `object[]`

Nested workstream hierarchy.

**idempotency\_key** `string`

Stable retry key.

**command\_center\_id** `string`

Deprecated alias for workspace\_id.

**context** `object[]`

Context attachment pointers.

**source\_evidence** `object`

For initiatives based on a named external product/site: include \{ target\_url, verification\_state: "verified"|"partial"|"unverified", evidence\_urls: string\[], notes? }. Do not create or launch from search-result inference when the target could not be rendered; use mode="draft" until screenshots or browser evidence verify the source.

**coordination\_dependency** `object`

Most important cross-workstream dependency.

**owner\_id** `string`

Owner user ID.

**user\_id** `string`

Deprecated alias for owner\_id.

**continue\_on\_error** `boolean`

Continue remaining creates after an error.

**launch\_after\_create** `boolean`

Legacy mode alias.

**external\_sync** `object`

Optional work-tracker mirror configuration.

**concurrency** `number`

Creation concurrency.

**Required Scopes**: `initiatives:write`

**Profiles**: legacy, commander, planner

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "scaffold_initiative",
  "args": {
      "title": "<title>"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "initiative": {
    "id": "init_new789",
    "title": "<initiative_title>",
    "status": "active"
  },
  "workstreams": [
    {
      "id": "ws_001",
      "title": "Frontend"
    }
  ],
  "milestones": [
    {
      "id": "ms_001",
      "title": "Beta launch"
    }
  ],
  "tasks": [
    {
      "id": "tsk_001",
      "title": "Build hero section"
    }
  ],
  "total_entities_created": 5
}
```

***

### update\_entity

Inline worker tool for updating mutable fields on an existing entity.

**type** `string` *required*

Entity type to update.

**id** `string` *required*

Entity ID to update.

**fields** `object`

Fields to patch.

**title** `string`

Optional title patch.

**name** `string`

Optional name patch.

**description** `string`

Optional description patch.

**status** `string`

Optional status patch.

**Required Scopes**: Authenticated user

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "update_entity",
  "args": {
      "type": "<type>",
      "id": "<id>"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "id": "tsk_abc123",
  "type": "task",
  "title": "Updated title",
  "updated_at": "2026-02-26T10:00:00Z"
}
```

***

## Legacy and internal: Organization

1 tool for organization operations.

### get\_org\_snapshot

Inline worker tool for reading an organization-wide execution snapshot across initiatives, work, blockers, and context.

**view** `string`

Response view mode. Defaults to summary. Options: `summary`, `detailed`.

**initiative\_status** `string`

Initiative status filter. Defaults to active. Options: `active`, `paused`, `all`.

**include** `string[]`

Detailed mode sections to include.

**limit** `number`

Maximum initiatives to return.

**cursor** `string`

Pagination cursor from a previous response.

**Required Scopes**: Authenticated user

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "get_org_snapshot",
  "args": {}
}
```

**Response**:

```json theme={"dark"}
{
  "workspace": "My Startup",
  "initiatives": {
    "total": 3,
    "active": 2,
    "completed": 1
  },
  "pending_decisions": 4,
  "active_agents": 2,
  "recent_artifacts": 7
}
```

***

## Legacy and internal: Planning

5 tools for planning operations.

### complete\_plan

Complete a planning session and attach implementation details to durable work context. Also known as: finish plan, implementation record, planning handoff. USE WHEN: user finishes building the planned feature. NEXT: Optionally attach to entities via attach\_to. DO NOT USE: if the plan session is still in progress.

**session\_id** `string` *required*

Plan session ID

**implementation\_summary** `string`

Summary of what was built

**files\_changed** `string[]`

List of files modified

**deviations** `object[]`

Any deviations from the plan

**attach\_to** `object[]`

Optional: attach this plan session as context on target entities (pointers, not payloads).

**Required Scopes**: `initiatives:write`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "complete_plan",
  "args": {
      "session_id": "<session_id>"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "session_id": "ps_abc123",
  "status": "completed",
  "entities_created": 8,
  "completed_at": "2026-02-26T10:10:00Z"
}
```

***

### get\_active\_sessions `read-only`

Find active planning sessions so agents can continue prior planning context. Also known as: resume planning, active plans, planning memory. USE WHEN: resuming a conversation or checking if a plan session exists. NEXT: Continue with improve\_plan or complete\_plan. Read-only.

*No parameters required.*

**Required Scopes**: `agents:read`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "get_active_sessions",
  "args": {}
}
```

**Response**:

```json theme={"dark"}
{
  "sessions": [
    {
      "id": "ps_abc123",
      "initiative_id": "init_abc123",
      "status": "active",
      "created_at": "2026-02-26T10:00:00Z"
    }
  ]
}
```

***

### improve\_plan

Improve a plan with AI suggestions based on prior patterns and best practices. Also known as: plan critique, planning feedback, refine roadmap. USE WHEN: user wants feedback on a plan draft. NEXT: Apply suggestions via record\_plan\_edit. DO NOT USE: without an active plan session — call start\_plan\_session first. Alias of orgx\_plan (action=improve).

**session\_id** `string` *required*

Plan session ID

**plan\_content** `string` *required*

Current plan content to analyze

**Required Scopes**: `initiatives:write`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "improve_plan",
  "args": {
      "session_id": "<session_id>",
      "plan_content": "<plan_content>"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "session_id": "ps_abc123",
  "suggestions": [
    {
      "type": "add_task",
      "workstream": "Frontend",
      "title": "Add responsive breakpoints"
    }
  ]
}
```

***

### record\_plan\_edit

Record a plan edit so OrgX can preserve planning context and learn patterns. Also known as: save plan change, plan memory, planning history. USE WHEN: user modifies their plan during a session. NEXT: Continue editing or call improve\_plan for more suggestions. DO NOT USE: without an active plan session.

**session\_id** `string` *required*

Plan session ID

**edit\_type** `string` *required*

Type of edit made Options: `add_section`, `remove_section`, `modify_section`, `add_detail`, `change_approach`, `add_edge_case`, `add_constraint`, `reorder`, `other`.

**before\_content** `string`

Content before edit

**after\_content** `string` *required*

Content after edit

**section\_path** `string`

Section path like "## API Design"

**user\_reason** `string`

Why this edit was made

**Required Scopes**: `initiatives:write`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "record_plan_edit",
  "args": {
      "session_id": "<session_id>",
      "edit_type": "add_section",
      "after_content": "<after_content>"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "session_id": "ps_abc123",
  "edit_id": "ed_001",
  "recorded_at": "2026-02-26T10:05:00Z"
}
```

***

### start\_plan\_session

Start a multi-agent planning session that breaks a goal into projects, tasks, owners, and agent assignments. Also known as: feature planning, roadmap planning, planning workflow. USE WHEN: user begins planning a new feature or initiative. NEXT: Use improve\_plan for suggestions, record\_plan\_edit to track changes, complete\_plan when done. DO NOT USE: for creating initiative hierarchies — use scaffold\_initiative instead. Alias of orgx\_plan (action=start).

**feature\_name** `string` *required*

Name of the feature being planned

**initial\_plan** `string`

Initial plan content if any

**workspace\_id** `string`

Workspace UUID to scope the planning session. Defaults to current session workspace when omitted.

**Required Scopes**: `initiatives:write`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "start_plan_session",
  "args": {
      "feature_name": "<feature_name>"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "session_id": "ps_abc123",
  "initiative_id": "init_abc123",
  "status": "active",
  "created_at": "2026-02-26T10:00:00Z"
}
```

***

## Legacy and internal: Scoring & Queue

1 tool for scoring & queue operations.

### get\_scoring\_signals `read-only`

Show raw signal data (blocking decisions, stream conflicts, health, budget, critical path, quality) for scoring. USE WHEN: user wants to understand why items are ranked the way they are in the deprecated alias. NEXT: Adjust with set\_scoring\_weights if weights need tuning. Read-only.

**initiative\_id** `string` *required*

Initiative UUID to gather signals for

**workstream\_id** `string`

Optional: filter to a specific workstream

**Required Scopes**: `decisions:read`, `agents:read`, `initiatives:read`, `memory:read`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "get_scoring_signals",
  "args": {
      "initiative_id": "<initiative_id>"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "signals": [
    {
      "name": "urgency",
      "weight": 0.3,
      "description": "Time sensitivity based on deadlines"
    },
    {
      "name": "impact",
      "weight": 0.25,
      "description": "Business value"
    }
  ]
}
```

***

## Legacy and internal: Streams

2 tools for streams operations.

### get\_initiative\_stream\_state `read-only`

Get execution stream progress, blockers, and computed metrics for an initiative. Also known as: project stream state, execution health, workstream progress. USE WHEN: checking stream execution status for an initiative. NEXT: If streams are blocked, use the deprecated alias to unblock. DO NOT USE: for raw stream records — use the deprecated alias type=stream instead. Read-only.

**initiative\_id** `string` *required*

The initiative ID

**Required Scopes**: `decisions:read`, `agents:read`, `initiatives:read`, `memory:read`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "get_initiative_stream_state",
  "args": {
      "initiative_id": "<initiative_id>"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "initiative_id": "init_abc123",
  "streams": [
    {
      "id": "str_abc123",
      "workstream": "Frontend",
      "progress": 0.75,
      "status": "active"
    }
  ]
}
```

***

### update\_stream\_progress

Report progress and confidence on a stream with velocity tracking. USE WHEN: agent is actively working a stream and needs to report progress. NEXT: Continue work; call again at each meaningful progress change. DO NOT USE: for general entity status changes — use the deprecated alias instead.

**stream\_id** `string` *required*

The stream ID to update

**progress\_pct** `number`

Progress percentage (0-100)

**confidence** `number`

Confidence level (0-1) - separate from progress

**status\_note** `string`

Brief note about current status

**expected\_version** `number`

For optimistic locking

**Required Scopes**: `agents:write`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "update_stream_progress",
  "args": {
      "stream_id": "<stream_id>"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "stream_id": "str_abc123",
  "progress": 0.75,
  "updated_at": "2026-02-26T10:00:00Z"
}
```

***

## Legacy and internal: Client Integration

9 tools for client integration operations.

### check\_spawn\_guard `read-only`

Check whether agent delegation is allowed before assigning work. Also known as: spawn guard, delegation authorization, agent rate limit. Returns model tier, rate limit status, quality gate, and task verification. USE WHEN: before any spawn\_agent\_task call. NEXT: If allowed, proceed with spawn\_agent\_task using the returned model tier. If blocked, inform user of the reason.

**domain** `string` *required*

Agent domain: engineering, marketing, product, design, ops, sales, orchestration

**task\_id** `string`

OrgX task ID this spawn is for

**task\_title** `string`

Task title (for model routing if task\_id not provided)

**task\_description** `string`

Task description

**Required Scopes**: `agents:read`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "check_spawn_guard",
  "args": {
      "domain": "<domain>"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "allowed": true,
  "trust_level": "act_with_approval",
  "budget_remaining_usd": 4.5
}
```

***

### classify\_task\_model `read-only`

Classify a task and get pre-spawn model routing context. Also known as: estimate task cost, model routing estimate, cost frontier, route task. USE WHEN: deciding which model/budget posture to use before agent work. Returns the recommended tier and, when the backend can compute it, estimated tokens/cost and candidate route comparisons. NEXT: Use the returned tier or cost frontier when spawning via spawn\_agent\_task. Read-only.

**title** `string` *required*

Task title

**description** `string`

Task description

**entity\_type** `string`

Entity type: task, decision, initiative

**domain** `string`

Agent domain

**model\_tier** `string`

Optional tier to estimate. Omit to let OrgX auto-route. Options: `standard`, `balanced`, `precision`, `local`, `sonnet`, `opus`.

**provider** `string`

Optional provider preference for the estimate. Use auto unless explicitly selected. Options: `auto`, `openai`, `anthropic`, `openrouter`, `groq`, `local`.

**budget\_mode** `string`

Optional budget posture for the estimate. Use cheapest\_valid for controlled validation runs only. Options: `cheapest_valid`, `balanced`, `highest_quality`.

**max\_cost\_usd** `number`

Optional per-task hard cost ceiling to compare against the estimate.

**estimate\_only** `boolean`

When true, return pre-spawn estimate context without dispatching work.

**Required Scopes**: `agents:read`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "classify_task_model",
  "args": {
      "title": "<title>"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "task_id": "tsk_abc123",
  "recommended_model": "claude-sonnet-4-6"
}
```

***

### consolidate\_pr

Use when the user or an engineering agent must show a pull request actually shipped and needs durable review proof, not a status glance. Generate and persist an orchestration.consolidation\_pass receipt for a GitHub pull request. Requires OrgX server-side GitHub credentials; if the GitHub token is unavailable, use GitHub tools for PR facts and return a structured blocker instead of retrying. USE WHEN: Eli or another engineering agent needs a durable PR review receipt with reading order, existence evidence, deduped findings, verdict, and server-derived AQ score. NEXT: inspect the returned artifact\_id or attach it to task completion proof. DO NOT USE WHEN: only asking for PR status; use GitHub tools instead.

**pr\_url** `string` *required*

GitHub pull request URL, e.g. [https://github.com/org/repo/pull/123](https://github.com/org/repo/pull/123). OrgX must have server-side GitHub credentials to inspect it.

**workspace\_id** `string`

OrgX workspace UUID

**initiative\_id** `string`

Initiative to attach the consolidation\_pass artifact to

**task\_id** `string`

Task to attach the consolidation\_pass artifact to

**decision\_id** `string`

Decision to attach the consolidation\_pass artifact to

**commit\_sha** `string`

Override commit SHA for idempotency; defaults to merge commit or PR head SHA

**verdict** `string`

Optional verdict override; defaults from PR state Options: `ship`, `simplify_first`, `escalate`.

**reviewer\_note** `string`

Optional reviewer note to include in critic evidence

**Required Scopes**: `initiatives:write`

**Profiles**: legacy, commander, executor

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "consolidate_pr",
  "args": {
      "pr_url": "<pr_url>"
  }
}
```

***

### orgx\_apply\_changeset

Apply an idempotent transactional changeset for task/milestone/decision mutations. USE WHEN: agent needs to create/update multiple tasks, milestones, or decisions atomically. NEXT: Call orgx\_emit\_activity to log what was changed. DO NOT USE: for single entity updates — use the deprecated alias or update\_entity instead.

**initiative\_id** `string` *required*

Initiative UUID

**idempotency\_key** `string` *required*

Idempotency key for safe retries

**operations** `object[]` *required*

Ordered task, milestone, and decision mutations to apply atomically

**run\_id** `string`

Existing run UUID

**correlation\_id** `string`

Required when run\_id is not provided

**source\_client** `string`

Required when run\_id is not provided Options: `openclaw`, `codex`, `claude-code`, `chatgpt`, `cursor`, `copilot`, `gemini`, `opencode`, `cline`, `goose`, `qwen`, `kiro`, `web-ui`, `api`.

**runtime** `object`

Runtime provenance used by /live to bucket cloud, local, Anthropic, managed, and OpenClaw changeset decisions

**Required Scopes**: `agents:write`, `initiatives:write`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_apply_changeset",
  "args": {
      "initiative_id": "<initiative_id>",
      "idempotency_key": "<idempotency_key>",
      "operations": [
          {
              "op": "task.create",
              "title": "<title>"
          }
      ]
  }
}
```

**Response**:

```json theme={"dark"}
{
  "applied": true,
  "changeset_id": "cs_abc123",
  "entities_affected": 3
}
```

***

### orgx\_emit\_activity

Use when an agent is mid-execution and its progress must stay visible to operators and to the next agent that resumes the run. Emit append-only run telemetry for OrgX control-plane reporting. USE WHEN: agent is executing and needs to report progress. NEXT: Continue work; emit again at each phase change. DO NOT USE: for entity status changes — use the deprecated alias instead. Setting phase="completed" records telemetry only and does not mark tasks, workstreams, or initiatives complete.

**initiative\_id** `string` *required*

Initiative UUID

**message** `string` *required*

Human-readable activity update

**run\_id** `string`

Existing run UUID

**correlation\_id** `string`

Required when run\_id is not provided

**source\_client** `string`

Required when run\_id is not provided Options: `openclaw`, `codex`, `claude-code`, `chatgpt`, `cursor`, `copilot`, `gemini`, `opencode`, `cline`, `goose`, `qwen`, `kiro`, `web-ui`, `api`.

**phase** `string`

Optional reporting phase for the activity event Options: `intent`, `execution`, `blocked`, `review`, `handoff`, `completed`.

**progress\_pct** `number`

Optional progress percentage associated with this activity

**level** `string`

Optional severity level for the activity event Options: `info`, `warn`, `error`.

**next\_step** `string`

Optional next step to surface after this activity event

**metadata** `object`

Optional structured metadata to attach to the activity event

**runtime** `object`

Runtime provenance used by /live to bucket cloud, local, Anthropic, managed, and OpenClaw chokepoints

**chokepoint** `object`

Durable blocker/stall/error/approval to surface in /live when execution cannot proceed

**Required Scopes**: `initiatives:write`

**Profiles**: legacy, claude-plugin, executor

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_emit_activity",
  "args": {
      "initiative_id": "<initiative_id>",
      "message": "<message>"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "emitted": true,
  "activity_id": "act_abc123"
}
```

***

### orgx\_lease

Coordinate file edits with other agents working in the same repository. USE WHEN: about to edit files another agent might be editing — claim the paths first. action=claim needs repo (owner/name) and paths (repo-relative files or globs); a refused claim lists who holds which paths until when, so wait or take other work. action=list shows live leases on a repo. action=release frees a lease early (lease\_id). Leases are advisory and expire (default 60 minutes); claiming the same paths again renews yours.

**action** `string` *required*

claim paths, list live leases, or release one Options: `claim`, `list`, `release`.

**repo** `string`

Repository as owner/name, e.g. hopeatina/orgx. Required for claim and list.

**paths** `string[]`

Repo-relative files or globs you are about to edit. Required for claim.

**minutes** `integer`

How long to hold the lease; default 60.

**lease\_id** `string`

The lease to release. Required for release.

**task\_id** `string`

OrgX task the edit belongs to, if any.

**reason** `string`

One line other agents will see.

**Required Scopes**: Authenticated user

**Profiles**: executor

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_lease",
  "args": {
      "action": "claim"
  }
}
```

***

### record\_quality\_score

Record a quality score (1-5) for a completed agent task. Scores feed into the quality gate — low-scoring domains get throttled. USE WHEN: after reviewing agent output. NEXT: Scores affect future check\_spawn\_guard decisions. DO NOT USE: for in-progress tasks — wait until completion.

**task\_id** `string`

OrgX task ID (snake\_case alias; taskId also accepted)

**taskId** `string`

OrgX task ID (backend/camelCase alias)

**agent\_domain** `string`

Agent domain that completed the task (agentDomain/domain also accepted)

**agentDomain** `string`

Agent domain that completed the task (backend/camelCase alias)

**domain** `string`

Short alias for agentDomain

**score** `number` *required*

Quality score: 1=poor, 3=acceptable, 5=excellent

**scored\_by** `string`

Who scored this (snake\_case alias; scoredBy also accepted) Options: `human`, `auto`, `peer`.

**scoredBy** `string`

Who scored this (backend/camelCase alias) Options: `human`, `auto`, `peer`.

**notes** `string`

Notes on the score

**Required Scopes**: `decisions:write`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "record_quality_score",
  "args": {
      "score": 1
  }
}
```

**Response**:

```json theme={"dark"}
{
  "recorded": true,
  "entity_id": "tsk_abc123",
  "score": 0.88
}
```

***

### review\_artifact `read-only`

Use when the user asks to review work, sign off on a deliverable, or clear pending artifact reviews. Surfaces the next artifact awaiting review and renders the artifact-review widget with a preview, version filmstrip, and hold-to-approve / request-changes actions. USE WHEN the user asks to review work, approve a deliverable, or handle pending artifact reviews. DO NOT USE for listing all artifacts — use the deprecated alias type=artifact instead.

**artifact\_id** `string`

Specific artifact ID to review. Defaults to the next in\_review artifact.

**entity\_id** `string`

Scope to artifacts attached to this entity (initiative, workstream, milestone, or task).

**workspace\_id** `string`

Workspace UUID. Defaults to the session workspace.

**Required Scopes**: `initiatives:read`

**Profiles**: legacy

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "review_artifact",
  "args": {}
}
```

***

### sync\_client\_state

Sync local agent context with OrgX organizational memory. Also known as: push session memory, pull project context, cross-tool continuity. Push decisions/logs, pull active context. USE WHEN: at session start and periodically during long sessions. NEXT: Review returned initiatives and pending decisions, ask user what to focus on. USE BEFORE: spawning agent work, to ensure latest state.

**memory** `string`

Local MEMORY.md content to push

**daily\_log** `string`

Today's session log to push

**Required Scopes**: `decisions:write`, `initiatives:write`, `memory:read`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "sync_client_state",
  "args": {}
}
```

**Response**:

```json theme={"dark"}
{
  "synced": true,
  "last_sync": "2026-02-26T10:00:00Z",
  "pending_changes": 0
}
```

***

## Legacy and internal: Workspace

1 tool for workspace operations.

### workspace

Create, list, inspect, or switch the active OrgX workspace for shared memory and project context. Also known as: create workspace, workspace context, team scope, organization scope. USE WHEN: user wants to create a workspace, see workspaces, check which is active, or switch workspaces. action=create creates a workspace and sets it active by default; action=list to see all; action=get for current; action=set to switch.

**action** `string` *required*

list=show all, get=current, set=switch active, create=new workspace Options: `list`, `get`, `set`, `create`.

**workspace\_id** `string`

Workspace UUID to switch to (action=set only)

**name** `string`

Workspace name (action=create)

**title** `string`

Alias for name (action=create)

**description** `string`

Workspace narrative/description (action=create)

**tagline** `string`

Short workspace tagline (action=create)

**narrative** `string`

Workspace identity narrative (action=create)

**key\_metrics** `string[]`

Workspace identity metrics (action=create)

**roadmap\_url** `string`

Roadmap URL (action=create)

**source\_links** `string[]`

Source links for workspace identity (action=create)

**set\_active** `boolean`

Whether to make the new workspace active. Defaults true.

**Required Scopes**: `decisions:read`, `agents:read`, `initiatives:read`, `memory:read`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "workspace",
  "args": {
      "action": "list"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "workspace_id": "ws_abc123",
  "name": "My Startup",
  "plan": "team",
  "created_at": "2025-10-01T00:00:00Z"
}
```

***

## Legacy and internal: Onboarding

1 tool for onboarding operations.

### configure\_org

Check organizational setup, configure agents, or set AI operating policies. Also known as: onboarding, agent policy, organization setup. USE WHEN: first connecting, onboarding, or adjusting agent/policy settings. action=status for progress, action=configure\_agent to set agent preferences, action=set\_policy for org-wide rules.

**action** `string` *required*

Configuration operation Options: `status`, `configure_agent`, `set_policy`.

**agent\_type** `string`

Agent type (configure\_agent only) Options: `product`, `engineering`, `marketing`, `sales`, `operations`, `design`, `orchestrator`.

**trust\_level** `string`

Agent autonomy level (configure\_agent only) Options: `strict`, `balanced`, `autonomous`.

**focus\_areas** `string[]`

Agent focus areas (configure\_agent only)

**approval\_required** `string[]`

Actions requiring approval (configure\_agent only)

**skip\_approval** `string[]`

Actions without approval (configure\_agent only)

**policy\_type** `string`

Policy type (set\_policy only) Options: `approvals`, `notifications`, `working_hours`, `budget`, `artifact_collection`.

**config** `object`

Policy configuration (set\_policy only)

**workspace\_id** `string`

Workspace UUID to scope policy overrides (set\_policy only)

**command\_center\_id** `string`

Deprecated alias for workspace\_id (set\_policy only)

**Required Scopes**: `decisions:read`, `agents:read`, `initiatives:read`, `memory:read`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "configure_org",
  "args": {
      "action": "status"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "workspace_id": "ws_abc123",
  "steps": {
    "linear_connected": true,
    "github_connected": false,
    "first_initiative": true,
    "first_decision": false
  },
  "completion": 0.5
}
```

***

## Legacy and internal: Stats

1 tool for stats operations.

### stats `read-only`

Get execution statistics, achievements, and session diagnostics. Also known as: usage stats, productivity report, session status. scope=personal for your stats, scope=session for current session diagnostics. Read-only.

**scope** `string`

personal=your stats, session=current session diagnostics Options: `personal`, `session`. Default: `"personal"`.

**timeframe** `string`

Time period for stats (personal only) Options: `today`, `week`, `month`, `all_time`.

**Required Scopes**: `decisions:read`, `agents:read`, `initiatives:read`, `memory:read`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "stats",
  "args": {}
}
```

**Response**:

```json theme={"dark"}
{
  "period": "30d",
  "decisions_resolved": 42,
  "artifacts_shipped": 18,
  "agents_spawned": 7,
  "avg_decision_time_hours": 2.3
}
```

***

## Legacy and internal: Intelligence Flywheel

6 tools for intelligence flywheel operations.

### get\_morning\_brief `read-only`

Use when the user asks 'what happened,' 'catch me up,' or starts a session after time away. Returns the morning brief: curated receipts, exceptions, ROI delta, and value signals from the most recent autonomous session. Defaults to the most recent session if no session ID is provided. Prefer `get_morning_brief` with workspace brief with value and exception summaries for new prompts, skills, and examples.

**workspace\_id** `string` *required*

Workspace ID

**session\_id** `string`

Specific session ID (defaults to most recent)

**Required Scopes**: `initiatives:read`

**Profiles**: legacy, claude-plugin, claude-code-legacy

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "get_morning_brief",
  "args": {
      "workspace_id": "<workspace_id>"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "session_id": "auto_abc123",
  "summary": "7 tasks completed, 2 decisions pending review",
  "tasks_completed": 7,
  "decisions_created": 2,
  "total_cost_usd": 2.15,
  "artifacts": [
    "art_001",
    "art_002"
  ]
}
```

***

### get\_my\_trust\_context `read-only`

Use when an agent asks "what am I trusted to do, what do I need for promotion, and which receipts are helping or hurting?" Returns the full trust context for an agent including per-capability levels, scores, thresholds, and recent trust events.

**workspace\_id** `string` *required*

Workspace ID

**agent\_type** `string` *required*

Agent type to query trust for

**Required Scopes**: `agents:read`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "get_my_trust_context",
  "args": {
      "workspace_id": "<workspace_id>",
      "agent_type": "<agent_type>"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "agent_type": "engineering-agent",
  "trust_level": "act_with_approval",
  "capabilities": {
    "read_code": "autonomous",
    "create_pr": "act_with_approval",
    "merge_pr": "draft"
  },
  "promotion_progress": 0.7
}
```

***

### get\_relevant\_learnings `read-only`

Use when an agent is about to attempt work the org may already have learned something about. Answers "what has the org learned about my capability?" Returns ranked org learnings relevant to a specific capability or task context.

**workspace\_id** `string` *required*

Workspace ID

**capability\_key** `string`

Capability key to filter learnings

**keywords** `string[]`

Keywords for semantic matching

**limit** `integer`

Maximum number of learnings to return Default: `5`.

**Required Scopes**: `memory:read`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "get_relevant_learnings",
  "args": {
      "workspace_id": "<workspace_id>"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "learnings": [
    {
      "id": "lrn_abc123",
      "pattern": "Auth bugs often stem from token refresh race conditions",
      "source_task": "tsk_xyz",
      "confidence": 0.85
    }
  ]
}
```

***

### record\_outcome

Use when a business outcome lands — deal closed, meeting booked, cycle time reduced — and it must be credited to the work that produced it. Agents can self-report outcomes they detect. Triggers attribution inference to connect outcomes to receipts. If the outcome type is unknown, call configure\_outcome\_type first.

**workspace\_id** `string`

Workspace ID

**workspaceId** `string`

CamelCase alias for workspace\_id

**outcome\_type\_key** `string`

Outcome type key: deal\_closed, meeting\_booked, etc.

**outcomeTypeKey** `string`

CamelCase alias for outcome\_type\_key

**outcome\_value** `number`

Value in the outcome type unit (e.g., USD amount)

**outcomeValue** `number`

CamelCase alias for outcome\_value

**source** `string`

Source that observed or reported the outcome Options: `manual`, `agent_self_report`, `crm_webhook`, `linear_sync`. Default: `"manual"`.

**source\_id** `string`

External source ID for deduplication

**sourceId** `string`

CamelCase alias for source\_id

**occurred\_at** `string`

ISO datetime when the outcome occurred

**occurredAt** `string`

CamelCase alias for occurred\_at

**metadata** `object`

Additional context

**Required Scopes**: `initiatives:write`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "record_outcome",
  "args": {}
}
```

**Response**:

```json theme={"dark"}
{
  "outcome_id": "out_abc123",
  "entity_id": "tsk_abc123",
  "recorded_at": "2026-02-26T10:00:00Z"
}
```

***

### start\_autonomous\_session

Use when the user says "run overnight with \$5 budget" or wants eligible work executed unattended within guardrails. Starts an autonomous execution session that produces receipts while executing eligible work items.

**workspace\_id** `string` *required*

Workspace ID.

**session\_type** `string`

Autonomy session mode to start. Options: `overnight`, `weekend`, `scheduled`, `manual`. Default: `"manual"`.

**max\_cost\_usd** `number`

Maximum budget in USD before the session stops. Default: `10`.

**max\_receipts** `integer`

Maximum number of receipts the session may produce. Default: `100`.

**allowed\_trust\_levels** `string[]`

Only execute capabilities at these trust levels. Default: `["autonomous","act_with_approval"]`.

**Required Scopes**: `agents:write`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "start_autonomous_session",
  "args": {
      "workspace_id": "<workspace_id>"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "session_id": "auto_abc123",
  "max_cost_usd": 5,
  "max_receipts": 50,
  "started_at": "2026-02-26T22:00:00Z"
}
```

***

### submit\_learning

Use when an agent discovers a pattern worth teaching the whole org — a failure mode, success pattern, cost optimization, or quality heuristic. Submits it as an org learning; enters org\_learnings after confidence validation. One agent's discovery benefits all agents.

**workspace\_id** `string` *required*

Workspace ID

**learning\_type** `string` *required*

Type of learning Options: `failure_pattern`, `success_pattern`, `cost_optimization`, `quality_heuristic`.

**summary** `string` *required*

Human-readable learning summary

**capability\_key** `string`

Applicable capability key

**evidence\_receipt\_ids** `string[]`

Receipt IDs that support this learning

**keywords** `string[]`

Semantic keywords for matching

**Required Scopes**: `memory:read`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "submit_learning",
  "args": {
      "workspace_id": "<workspace_id>",
      "learning_type": "failure_pattern",
      "summary": "<summary>"
  }
}
```

**Response**:

```json theme={"dark"}
{
  "learning_id": "lrn_new123",
  "submitted_at": "2026-02-26T10:00:00Z",
  "status": "accepted"
}
```

***

## Legacy and internal: Billing

3 tools for billing operations.

### account\_status

Inline worker tool for reading the authenticated user account tier, billing status, and usage snapshot.

*No parameters required.*

**Required Scopes**: Authenticated user

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "account_status",
  "args": {}
}
```

**Response**:

```json theme={"dark"}
{
  "user_id": "usr_abc123",
  "plan": "free",
  "tier": "free",
  "rate_limit_status": {
    "window": "1h",
    "limit_per_hour": 100,
    "remaining": 92
  }
}
```

***

### account\_upgrade

Inline worker tool for creating account upgrade or agent credit checkout flows.

**target\_plan** `string`

Target account plan. Defaults to pro. Options: `pro`, `enterprise`.

**billing\_cycle** `string`

Billing cadence for self-serve checkout. Options: `monthly`, `annual`.

**credit\_pack** `string`

Optional agent credit pack to buy instead of upgrading a plan. Options: `credits_500`, `credits_2000`.

**Required Scopes**: Authenticated user

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "account_upgrade",
  "args": {}
}
```

**Response**:

```json theme={"dark"}
{
  "target_plan": "pro",
  "billing_cycle": "monthly",
  "checkout_url": "https://checkout.stripe.com/c/pay/cs_abc123"
}
```

***

### account\_usage\_report

Inline worker tool for reading detailed usage, quota, billing-period, and overage signals.

*No parameters required.*

**Required Scopes**: Authenticated user

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "account_usage_report",
  "args": {}
}
```

**Response**:

```json theme={"dark"}
{
  "user_id": "usr_abc123",
  "plan": "free",
  "usage": {
    "creditsUsed": 15,
    "creditsIncluded": 100
  },
  "edge_rate_limit": {
    "window": "1h",
    "limit_per_hour": 100,
    "remaining": 92
  }
}
```

***

## Legacy and internal: MCP v2 Public Surface

10 tools for mcp v2 public surface operations.

### orgx\_act

Act on one OrgX entity. Required inputs:
• update → "fields" patch object.
• complete\_with\_proof, ship\_batch → "artifact" (artifact\_type + artifact\_url/external\_url; preview\_markdown optional).
• validate (studio) → "spec" payload.
• block, flag\_risk, decline, cancel, delete → "note" strongly recommended.
• dry\_run=true previews supported actions; update dry-runs must return would\_update.

Allowed (type → action) pairs (others return an error):
workspace: update|delete
initiative: launch|pause|resume|complete|archive|update|delete
milestone: start|complete|flag\_risk|cancel|ship\_batch|update|delete
workstream: start|pause|resume|block|complete|reassign\_streams|update|delete
task: start|complete|complete\_with\_proof|block|unblock|reopen|update|delete
objective, playbook, decision, studio: see field descriptions.

USE WHEN: changing entity state. Launch and resume can dispatch connected agent work. For pause, resume, retry, or cancel of running work, use manage\_lifecycle so descendant tasks and active runs stay synchronized. NEXT: orgx\_submit\_receipt for durable proof. DO NOT USE for creating records — use orgx\_write.

**type** `string` *required*

Target entity type (workspace, initiative, milestone, workstream, task, objective, playbook, decision, or studio). Options: `workspace`, `initiative`, `milestone`, `workstream`, `task`, `objective`, `playbook`, `decision`, `stream`, `studio_content`.

**id** `string` *required*

Target entity UUID or short ID prefix (8+ hex chars).

**action** `string` *required*

Lifecycle action to execute on the target entity. Must be valid for the given type — see tool description for the (type → action) matrix. Options: `launch`, `pause`, `resume`, `complete`, `complete_with_proof`, `archive`, `start`, `flag_risk`, `cancel`, `block`, `unblock`, `reopen`, `activate`, `approve`, `decline`, `supersede`, `update`, `delete`, `validate`, `ship_batch`, `reassign_streams`.

**fields** `object`

REQUIRED when action=update. Map of entity fields to patch (e.g. \{ name?: string, description?: string, owner\_id?: string, status?: string, due\_date?: string }). Only include fields you want to change.

**note** `string`

Strongly recommended for destructive or blocking actions (block, flag\_risk, decline, supersede, cancel, delete). Free-text rationale shown in audit history and downstream agent context.

**dry\_run** `boolean`

Preview update/delete or supported lifecycle actions without mutating. For action=update this returns would\_update and must not delegate to orgx\_write.

**force** `boolean`

Force action where server supports override semantics (skips pre-flight checks).

**spec** `object`

REQUIRED when action=validate. Spec payload for studio validation (shape varies per studio entity subtype).

**artifact** `object`

REQUIRED when action=complete\_with\_proof or action=ship\_batch. Proof artifact payload. Expected shape: \{ artifact\_type: string, artifact\_url?: string, external\_url?: string, preview\_markdown?: string, name?: string, description?: string }. Either artifact\_url or external\_url is required; preview\_markdown alone is rejected. Preferred founder/team artifact examples: orchestration.next\_initiative, eng.pull\_request, eng.deploy\_proof, eng.structured\_blocker, sales.strategy, sales.icp\_offer\_sequence, sales.send\_plan, sales.conversion\_gates, marketing.launch\_asset, marketing.channel\_hypothesis, marketing.positioning\_brief, marketing.proof\_distribution\_plan, marketing.interview\_pr\_plan, product.customer\_discovery, product.prd, product.pricing\_hypothesis, product.decision\_record, design.audit, design.component\_spec, design.token\_package, ops.operator\_brief, ops.runbook, ops.budget\_envelope, ops.incident\_status, proof.link.

**verification** `string[]`

Optional list of verification evidence URLs/IDs for completion flows.

**quality\_score** `number`

Quality score (0-5) attached to the action when used in proof/completion flows.

**idempotency\_key** `string`

Optional client-supplied retry key. Update requests transport it outside validated entity fields; lifecycle endpoints deduplicate where supported.

**session\_id** `string`

Optional bootstrap/session identifier returned by orgx\_bootstrap.

**Required Scopes**: `decisions:write`, `agents:write`, `initiatives:write`

**Profiles**: legacy, commander, planner, executor

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_act",
  "args": {
      "type": "workspace",
      "id": "<id>",
      "action": "launch"
  }
}
```

***

### orgx\_attach

Use when work produced a deliverable that needs provenance and review — attach the artifact or proof URL to an OrgX entity. Requires artifact\_url or external\_url; preview\_markdown is supporting context only. USE WHEN: saving evidence, PRs, documents, reports, screenshots, or external artifacts. For founder/team work, prefer practical artifact\_type codes such as orchestration.next\_initiative, eng.pull\_request, eng.deploy\_proof, eng.structured\_blocker, sales.strategy, sales.icp\_offer\_sequence, sales.send\_plan, sales.conversion\_gates, marketing.launch\_asset, marketing.channel\_hypothesis, marketing.positioning\_brief, marketing.proof\_distribution\_plan, marketing.interview\_pr\_plan, product.customer\_discovery, product.prd, product.pricing\_hypothesis, product.decision\_record, design.audit, design.component\_spec, design.token\_package, ops.operator\_brief, ops.runbook, ops.budget\_envelope, ops.incident\_status, proof.link. Include business\_outcome, owner/review\_date, and verification when the artifact should close agent work. NEXT: use orgx\_submit\_receipt to close attribution/quality loops or orgx\_act to complete with proof. DO NOT USE WHEN: creating generic entities; use orgx\_write.

**type** `string` *required*

Target entity type Options: `workspace`, `initiative`, `milestone`, `workstream`, `task`, `objective`, `playbook`, `decision`, `stream`, `studio_content`.

**id** `string` *required*

Target entity UUID or short ID prefix

**name** `string` *required*

Artifact title

**artifact\_type** `string` *required*

Artifact type code. Preferred founder/team examples: orchestration.next\_initiative, eng.pull\_request, eng.deploy\_proof, eng.structured\_blocker, sales.strategy, sales.icp\_offer\_sequence, sales.send\_plan, sales.conversion\_gates, marketing.launch\_asset, marketing.channel\_hypothesis, marketing.positioning\_brief, marketing.proof\_distribution\_plan, marketing.interview\_pr\_plan, product.customer\_discovery, product.prd, product.pricing\_hypothesis, product.decision\_record, design.audit, design.component\_spec, design.token\_package, ops.operator\_brief, ops.runbook, ops.budget\_envelope, ops.incident\_status, proof.link. Custom codes remain accepted.

**artifact\_url** `string`

Internal artifact URL. REQUIRED unless external\_url is provided; preview\_markdown alone is rejected.

**external\_url** `string`

External artifact URL. REQUIRED unless artifact\_url is provided; preview\_markdown alone is rejected.

**description** `string`

Artifact description

**preview\_markdown** `string`

Optional markdown preview shown with the linked artifact. Does not replace artifact\_url/external\_url.

**status** `string`

Artifact workflow status Options: `draft`, `in_review`, `approved`, `changes_requested`, `superseded`, `archived`.

**metadata** `object`

Artifact metadata

**agent\_type** `string`

Agent/domain that produced the artifact, such as engineering, sales, product, design, operations, marketing, or orchestrator. Stored under metadata.artifact\_contract.

**company\_stage** `string`

Founder/team context this artifact is calibrated for. Stored under metadata.artifact\_contract. Options: `early_founder`, `founder_led_company`, `operating_team`.

**business\_outcome** `string`

Business outcome this artifact is meant to advance, such as ship a PR, start founder-led sales, unblock launch, reduce incident risk, or choose the next initiative. Stored under metadata.artifact\_contract.

**owner** `string`

Human or agent owner for the next review/action. Stored under metadata.artifact\_contract.

**review\_date** `string`

Date or cadence for the next review point. Stored under metadata.artifact\_contract.

**verification** `string[]`

Verification evidence or checks required before the artifact can count as done. Stored under metadata.artifact\_contract.

**idempotency\_key** `string`

Strongly recommended client-generated idempotency key for safe retries

**session\_id** `string`

Optional bootstrap/session identifier

**Required Scopes**: `initiatives:write`

**Profiles**: legacy, claude-plugin, memory, commander, executor

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_attach",
  "args": {
      "type": "workspace",
      "id": "<id>",
      "name": "<name>",
      "artifact_type": "<artifact_type>"
  }
}
```

***

### orgx\_bootstrap

Use at the start of a fresh session, after reconnecting, or before continuing work another agent left behind. Establishes OrgX session context, discovers granted scopes, returns the v2 tool routing map, and persists workspace/session continuity when the selected context changes. Pass initiative\_id to bind an initiative and receive its compiled work context, including resolved decisions, acceptance checks, blockers, and artifact state. Also known as: bootstrap, setup, tool routing. USE WHEN: first call in a fresh session, after reconnecting, or before performing a multi-step workflow. NEXT: use orgx\_search, orgx\_inspect, or orgx\_recommend based on the returned routing map. DO NOT USE WHEN: you already have session context and need to read or mutate work. Updates private session state; it does not change business records.

**workspace\_id** `string`

Canonical workspace UUID to bind as the active session workspace

**initiative\_id** `string`

Optional initiative UUID to bind and hydrate as the active work context

**initiativeId** `string`

Alias for initiative\_id, accepted from older callers. initiative\_id wins when both are sent.

**initiative** `string`

Alias for initiative\_id (an initiative UUID), accepted from older callers. initiative\_id wins when both are sent.

**command\_center\_id** `string`

Deprecated alias for workspace\_id. workspace\_id wins when both are sent.

**conversation\_id** `string`

Optional client conversation/session identifier for continuity

**client\_name** `string`

Optional MCP client name, such as codex, chatgpt, cursor, or claude

**model** `string`

The model you are running as, as its provider names it (e.g. "claude-opus-5-5"). Say it once here: every receipt this session records it, so orgx\_submit\_receipt does not need it again.

**model\_provider** `string`

Provider of model when it cannot be read from the name (anthropic, openai, google…).

**timezone** `string`

Optional user timezone for date-sensitive readouts

**Required Scopes**: `initiatives:read`

**Profiles**: legacy, claude-plugin, memory, commander, planner, executor, observer

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_bootstrap",
  "args": {}
}
```

***

### orgx\_controller\_status `read-only`

Read the exact workspace-scoped projection for one domain controller without reconciling or triggering a run. USE WHEN: verifying whether a controller ran, its latest outcome, signal, receipt, projection cursor, or parity after a REST, SDK, or runner canary. NEXT: compare the returned lineage across surfaces or inspect the referenced Decision and Receipt. Requires an explicit workspace UUID. Read-only.

**workspace\_id** `string` *required*

Workspace UUID whose controller status should be read

**domain** `string` *required*

OrgX controller domain Options: `product`, `engineering`, `growth`, `sales`, `design`, `operations`.

**Required Scopes**: `decisions:read`, `initiatives:read`

**Profiles**: legacy, claude-plugin

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_controller_status",
  "args": {
      "workspace_id": "<workspace_id>",
      "domain": "product"
  }
}
```

***

### orgx\_decide

Creates or remembers durable OrgX decisions, lists pending decisions, and opens human review. Approval and rejection are human-session-only: those actions return a review URL and never resolve the decision or resume work from MCP.

Per-action input requirements:
• action="list\_pending" → No required fields; initiative\_id and workspace\_id are optional filters.
• action="create" → REQUIRES title and decision. Optional: context, initiative\_id.
• action="remember" → REQUIRES decision. Optional: title, context.
• action="approve" → REQUIRES decision\_id. Optional note is accepted but not persisted by MCP.
• action="reject" → REQUIRES decision\_id and reason; MCP does not persist the reason.

USE WHEN: capturing judgment or reviewing a pending decision. NEXT: open the returned review URL, then act only after the decision resolves. DO NOT USE WHEN: writing non-decision entities; use orgx\_write.

**action** `string` *required*

Decision operation. See top-level description for per-action required fields. Options: `create`, `remember`, `list_pending`, `approve`, `reject`.

**decision\_id** `string`

Decision UUID. REQUIRED for action=approve or action=reject. Returned by action=list\_pending or action=create.

**title** `string`

Short title for the decision. REQUIRED for action=create.

**decision** `string`

The decision text itself (what was decided). REQUIRED for action=create and action=remember.

**summary** `string`

Optional one-line summary used in lists. Falls back to title when omitted.

**context** `string`

Background context / rationale that led to the decision. Recommended for action=create to capture provenance.

**reason** `string`

REQUIRED for action=reject before returning the human-session review URL. MCP does not persist or submit this reason.

**note** `string`

Optional compatibility field for action=approve. MCP does not persist it; enter the final rationale in the human review session.

**initiative\_id** `string`

Optional initiative UUID to scope the decision. Used as filter when action=list\_pending; used as parent when action=create.

**workspace\_id** `string`

Optional workspace UUID to scope the decision. Defaults to the MCP session's workspace.

**idempotency\_key** `string`

Strongly recommended client-supplied idempotency key for action=create or action=remember. Same key returns the same result without duplicating state.

**session\_id** `string`

Optional bootstrap/session identifier returned by orgx\_bootstrap.

**Required Scopes**: `decisions:read`, `decisions:write`

**Profiles**: legacy, claude-plugin, memory, commander, planner, observer

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_decide",
  "args": {
      "action": "create"
  }
}
```

***

### orgx\_plan

Use when planning should survive the session and become executable context instead of a lost chat draft. Starts, resumes, edits, improves, or completes a tracked OrgX planning session.

Per-action input requirements:
• action="start"       → REQUIRES feature\_name. Optional: initial\_plan (markdown to seed the session).
• action="resume"      → Optional session\_id; when omitted, resumes the most recent active session in the authenticated workspace.
• action="improve"     → REQUIRES session\_id AND plan\_content (the current draft to critique).
• action="record\_edit" → REQUIRES session\_id AND edit\_summary (one-line description of the change).
• action="complete"    → REQUIRES session\_id AND plan\_content (the final accepted plan). Optional: attach\_to (one target or an array of targets to link the completed plan to).

USE WHEN: work is still in planning or should become executable context. NEXT: use orgx\_write or orgx\_act after the plan is accepted and needs durable execution state. DO NOT USE WHEN: directly scaffolding a full initiative hierarchy; use scaffold\_initiative for that compatibility path.

**action** `string` *required*

Planning action to perform. See top-level description for per-action required fields. Options: `start`, `resume`, `improve`, `record_edit`, `complete`.

**session\_id** `string`

Plan session UUID or orgx://plan\_session/\<uuid> URI. Optional for action=resume, which defaults to the most recent active session in the authenticated workspace. REQUIRED for action=improve | record\_edit | complete. Omit for action=start.

**feature\_name** `string`

Feature or plan name. REQUIRED when action=start.

**initial\_plan** `string`

Markdown plan content to seed the new session. Optional on action=start; the session can also be started empty and filled via improve/record\_edit.

**plan\_content** `string`

Current/final plan markdown. REQUIRED when action=improve (the draft to critique) or action=complete (the final accepted plan).

**edit\_summary** `string`

One-line description of the change being recorded. REQUIRED when action=record\_edit.

**attach\_to** `any`

Optional target or targets to link the completed plan to when action=complete. A single \{ entity\_type, entity\_id } object is accepted and normalized to the API array contract.

**workspace\_id** `string`

Workspace UUID to scope action=start plan sessions. Defaults to current session workspace when omitted.

**idempotency\_key** `string`

Optional idempotency key for safe retries. Same key returns the same result without creating duplicate session state.

**Required Scopes**: `initiatives:read`, `initiatives:write`

**Profiles**: legacy, commander, planner, executor, observer

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_plan",
  "args": {
      "action": "start"
  }
}
```

***

### orgx\_recommend

Use when the user asks what to do next, wants a brief, or returns after time away and needs priorities. Recommends next work, summarizes operator-chronicle/morning-brief signals, and reads prioritization context. The default next\_action mode records metered MCP allowance usage; it does not change business records. USE WHEN: user asks what to do next, wants a brief, asks what changed yesterday/week/30 days, or needs priority guidance. mode=morning\_brief returns the operator chronicle when available. NEXT: present the recommendation and ask for explicit confirmation before any separate action. DO NOT USE WHEN: the user already specified a concrete action.

**mode** `string`

Recommendation mode; default next\_action Options: `next_action`, `morning_brief`.

**period** `string`

Reporting period for mode=morning\_brief; default 30d Options: `day`, `week`, `30d`.

**entity\_type** `string`

Recommendation scope type Options: `workspace`, `initiative`, `workstream`, `milestone`, `task`.

**entity\_id** `string`

Scoped entity ID

**initiative\_id** `string`

Shortcut for entity\_type="initiative" with entity\_id=\<this id>. Ignored when entity\_type or entity\_id is set.

**workspace\_id** `string`

Workspace UUID

**limit** `integer`

Maximum recommendations

**session\_id** `string`

Optional bootstrap/session identifier

**Required Scopes**: `initiatives:read`

**Profiles**: legacy, claude-plugin, claude-code-legacy, memory, commander, observer

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_recommend",
  "args": {}
}
```

***

### orgx\_spawn

Delegate specialist work or check whether delegation is allowed. Actions: guard, estimate, classify, spawn, and handoff.

Requirements: existing-task spawn needs task\_id; ad-hoc spawn needs title + instructions and should include agent\_type. handoff needs task\_id + agent\_type. guard needs agent\_type. classify needs title or task\_id. action="estimate" needs title or task\_id and returns candidate routes and cost context without dispatching work. OAuth: guard/classify/estimate require agents:read; spawn requires agents:write; handoff requires BOTH agents:write and initiatives:write.

Routing: omit model\_tier/provider/model for OrgX auto-routing. Set routing or budget fields only when the user, policy, or verification plan constrains them. For controlled reliability validation, use model\_tier="standard" and budget\_mode="cheapest\_valid".

USE WHEN: delegating work or checking permission/cost before delegation. NEXT: monitor with orgx\_inspect or orgx\_search, then attach proof with orgx\_submit\_receipt. DO NOT USE: to create only a task row; use orgx\_write.

**action** `string`

Spawn operation. Defaults to "spawn". Use estimate for pre-spawn cost/routing context without dispatching work. See top-level description for per-action required fields. Options: `guard`, `estimate`, `spawn`, `handoff`, `classify`.

**title** `string`

Task title. REQUIRED for ad-hoc spawn (action=spawn without task\_id) or action=classify without task\_id. Used as the human-readable label of the spawned task.

**task\_id** `string`

Existing task UUID. REQUIRED for action=handoff. REQUIRED for action=spawn when spawning work for an already-created task. Either task\_id or title (with instructions) must be provided for action=spawn.

**initiative\_id** `string`

Optional initiative UUID to scope the spawned task. Inferred from task\_id when omitted.

**workspace\_id** `string`

Optional workspace UUID to scope the spawned task. Defaults to the MCP session's workspace.

**agent\_type** `string`

Target agent type/domain (e.g. "engineering", "marketing", "design"). REQUIRED for action=guard or action=handoff. Strongly recommended for action=spawn so the work routes to the right specialist.

**instructions** `string`

Delegation instructions for the agent. REQUIRED for action=spawn when spawning ad-hoc (without task\_id). Used to override the task description for action=handoff.

**model\_tier** `string`

Optional model tier override. Omit to let OrgX auto-route from task complexity. Legacy local/sonnet/opus are accepted for older clients. Options: `standard`, `balanced`, `precision`, `local`, `sonnet`, `opus`.

**model** `string`

Optional exact model identifier when the user explicitly selects one. Otherwise OrgX resolves the model from task, tier, provider, policy, and budget.

**provider** `string`

Optional provider preference. Use auto unless the user asks for a specific provider or a cost comparison selects one. Options: `auto`, `openai`, `anthropic`, `openrouter`, `groq`, `local`.

**runtime** `string`

Optional runtime OrgX runs the work on. Omit or auto to let OrgX choose. cloud\_claude / cloud\_openai: OrgX cloud on the Claude Agent SDK or OpenAI Responses. managed\_openai / managed\_anthropic: the OpenAI Agents API or Claude Managed Agents under OrgX governance. local: a paired local peer (Claude Code, Codex, OpenClaw) on the user machine. Options: `auto`, `cloud_claude`, `cloud_openai`, `managed_openai`, `managed_anthropic`, `local`.

**deadline** `string`

Optional ISO-8601 instant by which the work must finish (e.g. "2026-09-28T17:00:00Z"). Validated and recorded; free text is rejected because a constraint that cannot be evaluated is not a constraint.

**max\_cost\_usd** `number`

Optional hard cost ceiling in USD for this dispatch. If the estimate exceeds it, OrgX blocks, downgrades, or requests approval before dispatch.

**budget\_mode** `string`

Optional budget posture. Use cheapest\_valid for controlled validation runs while reliability is being proven. Options: `cheapest_valid`, `balanced`, `highest_quality`.

**max\_parallel** `integer`

Optional cap on concurrent workers for this dispatch. Work that shares a repository is usually integration-bound well below this: more workers add merge contention, not throughput.

**expected\_artifacts** `string[]`

Optional expected final-output labels. Declaring at least one adds an artifact contract to the run.

**effects** `object`

Optional declared effect scope for the work. Recorded on the run and shown in the receipt. Declaring an effect never grants it — the platform intersects it with the caller authority.

**acceptance** `object[]`

Optional acceptance checks that define what counts as done. Declared BEFORE the work and hashed at dispatch. A check that already passes on the pre-state is reported as non-discriminating and excluded from the verdict.

**idempotency\_key** `string`

Optional client-supplied idempotency key for safe retries. The same key returns the same dispatch result without re-running the work.

**session\_id** `string`

Optional bootstrap/session identifier returned by orgx\_bootstrap.

**Required Scopes**: `agents:read`, `agents:write`, `initiatives:write`

**Profiles**: legacy, commander, executor

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_spawn",
  "args": {}
}
```

***

### orgx\_submit\_receipt

Use when the user says "show me it actually shipped" — completion must be proven with evidence, not prose. Submits a durable receipt anchored to an OrgX entity or artifact.

Required: receipt\_type + summary. Strongly recommended: one anchor (entity\_type+entity\_id OR artifact\_id), artifact\_type, business\_outcome, agent\_type, and a verifiable URL in evidence.

Recognized receipt\_type: "proof", "outcome" (measurable result), "quality" (review/score), "attribution" (credit link to revenue/value), "learning" (distilled lesson). Custom keys also accepted.

Recognized evidence shapes (mix and match):
\{ prs: string\[] } — GitHub PR URLs.
\{ deploys: string\[] } — deployment URLs.
\{ test\_runs: string\[] } — CI run URLs.
\{ metrics: \{ name, value, unit? }\[] } — quantitative outcomes.
\{ links: string\[] }, \{ notes: string } — supporting URLs/text.

Pass idempotency\_key when retrying — server deduplicates.

USE WHEN: closing the loop on agent work with provenance. Receipts should prove the practical artifact and its business outcome, not just say the agent finished. NEXT: orgx\_recommend or orgx\_search to find the next priority. DO NOT USE for telemetry — use orgx\_emit\_activity.

**workspace\_id** `string`

Workspace UUID. Defaults to the MCP session's workspace when omitted.

**entity\_type** `string`

Related entity type (initiative, workstream, milestone, task, decision). Required if no artifact\_id is provided — pair with entity\_id.

**entity\_id** `string`

Related entity UUID. Required when entity\_type is provided.

**receipt\_type** `string` *required*

Receipt category key. Recognized values: "proof", "outcome", "quality", "attribution", "learning". Custom domain-specific keys are also accepted.

**summary** `string` *required*

One-sentence human-readable description of what the receipt proves (e.g. "Merged PR #142 unblocking the auth refactor").

**evidence** `object`

Structured evidence payload. Recognized shapes: \{ prs: string\[] }, \{ deploys: string\[] }, \{ test\_runs: string\[] }, \{ metrics: \{ name, value, unit? }\[] }, \{ links: string\[] }, \{ notes: string }. See top-level description for full list. At least one verifiable URL is strongly recommended.

**artifact\_id** `string`

Related artifact UUID to anchor the receipt to. Alternative to entity\_type+entity\_id when the proof lives in OrgX as an artifact.

**artifact\_type** `string`

Artifact type this receipt proves. Preferred founder/team examples: orchestration.next\_initiative, eng.pull\_request, eng.deploy\_proof, eng.structured\_blocker, sales.strategy, sales.icp\_offer\_sequence, sales.send\_plan, sales.conversion\_gates, marketing.launch\_asset, marketing.channel\_hypothesis, marketing.positioning\_brief, marketing.proof\_distribution\_plan, marketing.interview\_pr\_plan, product.customer\_discovery, product.prd, product.pricing\_hypothesis, product.decision\_record, design.audit, design.component\_spec, design.token\_package, ops.operator\_brief, ops.runbook, ops.budget\_envelope, ops.incident\_status, proof.link.

**agent\_type** `string`

Agent/domain that produced the receipt, such as engineering, sales, product, design, operations, marketing, or orchestrator.

**business\_outcome** `string`

Business outcome advanced by the receipt.

**verification\_status** `string`

Whether the artifact verification passed, failed, was blocked, or was not run. Options: `passed`, `failed`, `blocked`, `not_run`.

**validation\_rung** `string`

Optional OrgX loop validation rung this receipt proves. Required for promotion-grade loop validation receipts. Options: `schema_discovery`, `dry_run_spawn`, `single_domain_fixture`, `cross_domain_initiative_fixture`, `overnight_canary`, `calibrated_auto_route_expansion`.

**loop\_validation** `boolean`

Set true when this receipt should be evaluated against the OrgX loop reliability validation ladder.

**model\_tier** `string`

Model tier used for the run being receipted. For validation rungs before calibrated expansion, use standard. Options: `standard`, `balanced`, `precision`, `local`, `sonnet`, `opus`.

**budget\_mode** `string`

Budget posture used for the run being receipted. For validation rungs before calibrated expansion, use cheapest\_valid. Options: `cheapest_valid`, `balanced`, `highest_quality`.

**max\_cost\_usd** `number`

Per-task or canary spend cap used during the validation run, when known.

**model** `string`

Model that did the work, as its provider names it (e.g. "claude-opus-5-5"). Defaults to the model given to orgx\_bootstrap this session; pass it only if that was not given or this work ran on a different model.

**model\_provider** `string`

Provider of model when it cannot be read from the name (anthropic, openai, google…).

**agent\_work\_receipt** `object`

A complete Agent Work Receipt (v0.2), stored verbatim instead of one built from the other fields. Include actor.runtime and actor.model, and ideally extensions\["org.orgx.review/v1"]: criteria frozen before the work, one check per criterion, output attached.

**status** `string`

Terminal state of the work being receipted. Pass failed or cancelled when that is what happened — omitting it records completed, and a receipt that can only say "completed" makes every reliability number a survivorship filter. Options: `in_progress`, `completed`, `failed`, `cancelled`.

**started\_at** `string`

ISO-8601 timestamp of when the work actually started. Omit if unknown rather than guessing: the record leaves duration unknown instead of claiming zero. Must not be in the future.

**idempotency\_key** `string`

Strongly recommended client-supplied idempotency key. Submitting the same key twice will not create a duplicate receipt.

**session\_id** `string`

Optional bootstrap/session identifier returned by orgx\_bootstrap.

**Required Scopes**: `initiatives:write`

**Profiles**: legacy, claude-plugin, memory, commander, executor

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_submit_receipt",
  "args": {
      "receipt_type": "<receipt_type>",
      "summary": "<summary>"
  }
}
```

***

### orgx\_write

Create or update one OrgX record (snake\_case fields).

Operations: create (default) uses per-type fields; update REQUIRES id + fields.

Create requirements: workspace name/title; initiative title/name + workspace\_id + goal\_ids when the workspace enforces primary objectives; workstream title + initiative\_id; milestone title + workstream\_id; task title + workstream\_id + milestone\_id when the workspace requires backlog milestones; decision title; artifact target + artifact\_type + artifact\_url/external\_url; blocker run\_id + metadata.description; skill/studio records title.

Retry behavior: pass idempotency\_key on creates. A key match returns the same UUID as an idempotent replay, without creating a duplicate.

Initiative constraints: priority accepts low|medium|high|urgent, not portfolio labels such as active/critical/maintenance/hold. due\_date is not accepted on initiative create; store portfolio urgency and target dates in metadata.

USE WHEN: adding/editing records. Initiative writes can publish a public live link, and update patches overwrite the supplied fields. NEXT: orgx\_act to launch/complete the record. DO NOT USE for lifecycle changes — use orgx\_act or orgx\_attach.

**operation** `string`

Write operation. Defaults to "create". Set "update" (with id + fields) to patch an existing entity. Options: `create`, `update`.

**type** `string` *required*

Entity type to write: workspace, task, milestone, decision, artifact, skill, blocker, studio\_brand, studio\_content, initiative, workstream, or objective. See top-level description for per-type required fields.

**id** `string`

REQUIRED when operation="update". Target entity UUID to patch.

**title** `string`

REQUIRED on create (provide either "title" or "name" — they are aliases). Display title of the new entity.

**name** `string`

Alternative to "title" on create. REQUIRED on create when "title" is not provided.

**summary** `string`

Short description shown in lists and previews. Recommended on create.

**description** `string`

Longer-form description used in detail views.

**fields** `object`

REQUIRED when operation="update". Map of entity fields to patch (only include fields you want to change).

**initiative\_id** `string`

Parent initiative UUID. REQUIRED when type="workstream". Optional context for tasks/milestones/artifacts to associate them with an initiative.

**workstream\_id** `string`

Parent workstream UUID. REQUIRED when type="milestone" or type="task".

**milestone\_id** `string`

Parent milestone UUID for tasks. Some workspaces require an explicit backlog milestone under the workstream; create/resolve that milestone first instead of relying on auto-resolution.

**workspace\_id** `string`

Workspace UUID. REQUIRED when the MCP session does not already carry workspace context (resolve via the deprecated alias type=command\_center or orgx\_inspect type=workspace).

**goal\_ids** `string[]`

Objective UUIDs for initiative/workstream/milestone/task creation. REQUIRED when the workspace enforces a primary objective. Resolve via orgx\_inspect type=objective.

**priority** `string`

Record urgency. Only low|medium|high|urgent are accepted here; do not send portfolio/live labels such as active, critical, maintenance, or hold. "urgent" is normalized to "high" server-side. Options: `low`, `medium`, `high`, `urgent`.

**due\_date** `string`

Due date as YYYY-MM-DD for supported entity types. Do not send due\_date when type="initiative"; put initiative target dates in metadata.

**status** `string`

Initial workflow status; common agent aliases such as "active" are normalized per entity type ("active" → "in\_progress").

**entity\_type** `string`

REQUIRED when type="artifact". Entity type to attach the artifact to (initiative, workstream, milestone, task, or decision).

**entity\_id** `string`

REQUIRED when type="artifact" (unless task\_id is provided). UUID of the entity to attach the artifact to.

**task\_id** `string`

Shortcut for attaching an artifact directly to a task. Use instead of entity\_type+entity\_id when type="artifact" and the target is a task.

**artifact\_type** `string`

REQUIRED when type="artifact". Artifact type code. Preferred founder/team examples: orchestration.next\_initiative, eng.pull\_request, eng.deploy\_proof, eng.structured\_blocker, sales.strategy, sales.icp\_offer\_sequence, sales.send\_plan, sales.conversion\_gates, marketing.launch\_asset, marketing.channel\_hypothesis, marketing.positioning\_brief, marketing.proof\_distribution\_plan, marketing.interview\_pr\_plan, product.customer\_discovery, product.prd, product.pricing\_hypothesis, product.decision\_record, design.audit, design.component\_spec, design.token\_package, ops.operator\_brief, ops.runbook, ops.budget\_envelope, ops.incident\_status, proof.link. Custom codes remain accepted.

**artifact\_url** `string`

Internal artifact URL (e.g. /api/artifacts/...). Either artifact\_url or external\_url is required when type="artifact"; preview\_markdown alone is not accepted.

**external\_url** `string`

External artifact URL (https\://). Either artifact\_url or external\_url is required when type="artifact"; preview\_markdown alone is not accepted.

**preview\_markdown** `string`

Optional inline markdown preview shown with the linked artifact. Supporting context only; it does not replace artifact\_url/external\_url.

**run\_id** `string`

REQUIRED when type="blocker". Agent run UUID the blocker applies to.

**step\_id** `string`

Optional agent run step UUID for blocker creation.

**blocker\_type** `string`

Blocker category/type when type="blocker" (e.g. "missing\_input", "permission", "external\_dependency").

**resolution** `string`

Blocker resolution text when known. Used to mark a blocker as resolved.

**live\_visibility** `string`

Initiative live-link visibility. Only applies when type="initiative". Options: `private`, `public`.

**live\_public** `boolean`

Shortcut to publish an initiative live link (sets live\_visibility="public"). Only applies when type="initiative".

**live\_reveal\_title** `boolean`

When true, public live-link visitors see the initiative title. Only applies when type="initiative" with live\_visibility="public".

**metadata** `object`

Free-form object for type-specific metadata. Schema varies per entity type (e.g. for skills: \{ capabilities, guardrails, channels }; for studio\_brand: \{ tokens, voice, exemplars }).

**tagline** `string`

Workspace tagline when type="workspace".

**narrative** `string`

Workspace identity narrative when type="workspace".

**key\_metrics** `string[]`

Workspace identity metrics when type="workspace".

**roadmap\_url** `string`

Workspace roadmap URL when type="workspace".

**source\_links** `string[]`

Workspace source links when type="workspace".

**set\_active** `boolean`

For workspace create, make the new workspace active. Defaults true.

**idempotency\_key** `string`

Client-generated retry key. Creates deduplicate by key; updates transport the key outside validated entity fields.

**session\_id** `string`

Optional bootstrap/session identifier returned by orgx\_bootstrap.

**Required Scopes**: `decisions:write`, `agents:write`, `initiatives:write`

**Profiles**: legacy, commander, planner, executor

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_write",
  "args": {
      "type": "<type>"
  }
}
```

***

## Other

27 tools for other operations.

### check\_execution\_readiness `read-only`

Check whether the workspace has the credentials needed to dispatch agent work, BEFORE spawning. USE WHEN: about to call orgx\_spawn / spawn\_agent\_task and you want to confirm execution credentials exist — avoids dispatching a run that fails on missing keys. NEXT: if not ready, surface what is missing and resolve it; if ready, proceed to orgx\_spawn. Read-only; dispatches nothing.

**workspace\_id** `string`

Workspace UUID to check. Defaults to the MCP session workspace.

**Required Scopes**: `initiatives:read`

**Profiles**: legacy, commander, executor

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "check_execution_readiness",
  "args": {}
}
```

***

### configure\_outcome\_type

Use when record\_outcome returns an unknown outcome type recovery hint, or a custom result must become measurable. Creates or approves a workspace outcome type before recording custom baseline, audit, or quality-gate outcomes.

**workspace\_id** `string`

Workspace ID

**workspaceId** `string`

CamelCase alias for workspace\_id

**key** `string` *required*

Outcome type key, normalized server-side to snake\_case

**display\_name** `string`

Human-facing outcome type label

**displayName** `string`

CamelCase alias for display\_name

**unit** `string`

Measurement unit for this outcome type Options: `usd`, `hours`, `count`, `percent`. Default: `"count"`.

**value\_semantics** `string`

How the value should be interpreted by ROI/proof loops Options: `revenue`, `time_saved`, `risk_reduced`, `quality_improved`. Default: `"quality_improved"`.

**valueSemantics** `string`

CamelCase alias for value\_semantics Options: `revenue`, `time_saved`, `risk_reduced`, `quality_improved`.

**Required Scopes**: `initiatives:write`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "configure_outcome_type",
  "args": {
      "key": "<key>"
  }
}
```

***

### get\_operator\_chronicle `read-only`

Use when the user asks what happened, wants to catch up after time away, or needs a reporting window summarized with decisions and proof. Read the operator chronicle: decision chronology, yesterday/week/30-day rollups, reportingNarrative.briefMarkdown, artifacts, PR receipts, active initiatives, goals, top priorities, velocity, and reporting gaps for a workspace. USE WHEN: user asks what changed yesterday, this week, or this month; asks for decision chronology, top priorities, PR velocity, artifacts, goals, or what OrgX is missing. NEXT: present reportingNarrative.briefMarkdown first, then use reportingNarrative.nextAction and topPriorities for drill-down. Read-only.

**workspace\_id** `string`

Workspace UUID to scope the chronicle.

**command\_center\_id** `string`

Deprecated alias for workspace\_id.

**period** `string`

Reporting window. day=24h, week=7d, 30d=30 days. Options: `day`, `week`, `30d`.

**Required Scopes**: `initiatives:read`

**Profiles**: legacy, claude-plugin, claude-code-legacy, commander, observer

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "get_operator_chronicle",
  "args": {}
}
```

***

### manage\_lifecycle

Pause, resume, retry, or cancel any node in the work hierarchy — an initiative, workstream, milestone, task, or run. Propagates to descendant tasks + active runs. USE WHEN: the user wants to halt, restart, or re-run part of an initiative. resume/retry re-dispatch the work; pause/cancel stop active runs. NEXT: get\_initiative\_pulse to confirm. DO NOT USE: to mark a task done — use the deprecated alias instead.

**level** `string` *required*

Which hierarchy node to act on Options: `initiative`, `workstream`, `milestone`, `task`, `run`.

**id** `string` *required*

UUID of the node

**action** `string` *required*

Lifecycle action to apply Options: `pause`, `resume`, `retry`, `cancel`.

**Required Scopes**: `agents:write`, `initiatives:write`

**Profiles**: legacy

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "manage_lifecycle",
  "args": {
      "level": "initiative",
      "id": "<id>",
      "action": "pause"
  }
}
```

***

### orgx\_ack\_attention

Report what happened after an owner answered an attention request. Use answer\_received when stored locally, resuming when native continuation begins, resumed only after work emits again, resume\_failed with an actionable detail when it cannot restart, or cancelled when intentionally stopped. USE WHEN: the source client has objective evidence for a continuation state transition. NEXT: keep the same attention\_id and idempotency key through terminal resumed, resume\_failed, or cancelled state. DO NOT USE: to infer that work resumed merely because the decision was resolved; wait for native execution evidence. This receipt prevents Live from claiming work is moving before the source client confirms it.

**attention\_id** `string` *required*

Attention/decision UUID

**state** `string` *required*

Native continuation state proven by this receipt Options: `answer_received`, `resuming`, `resumed`, `resume_failed`, `cancelled`.

**idempotency\_key** `string` *required*

Stable key for retrying the same receipt

**session\_handle** `string`

Native session handle that processed the answer

**client\_event\_id** `string`

Client event proving the continuation transition

**detail** `string`

Actionable continuation result or failure detail

**occurred\_at** `string`

ISO timestamp when this state was observed

**metadata** `object`

Additional non-secret receipt metadata

**Required Scopes**: `initiatives:write`

**Profiles**: legacy, commander, executor

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_ack_attention",
  "args": {
      "attention_id": "<attention_id>",
      "state": "answer_received",
      "idempotency_key": "<idempotency_key>"
  }
}
```

***

### orgx\_change\_entity\_state

Change the workflow state of an OrgX initiative, workstream, milestone, task, objective, or playbook. Supports starting or launching work, blocking or unblocking, reopening, flagging risk, archiving, activating, or reassigning workstreams where valid for the entity type. Launching can dispatch connected agent work and incur costs. Records a supplied rationale in audit history.

**type** `string` *required*

Entity type whose workflow state should change. Options: `initiative`, `workstream`, `milestone`, `task`, `objective`, `playbook`.

**id** `string` *required*

Target entity UUID or short ID prefix (8+ hex chars).

**action** `string` *required*

Workflow state change. Must be valid for the selected entity type. Options: `launch`, `start`, `block`, `unblock`, `reopen`, `flag_risk`, `archive`, `reassign_streams`, `activate`.

**note** `string`

Strongly recommended for destructive or blocking actions (block, flag\_risk, decline, supersede, cancel, delete). Free-text rationale shown in audit history and downstream agent context.

**idempotency\_key** `string`

Optional client-supplied retry key. Update requests transport it outside validated entity fields; lifecycle endpoints deduplicate where supported.

**session\_id** `string`

Optional OrgX session identifier.

**Required Scopes**: `initiatives:write`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_change_entity_state",
  "args": {
      "type": "initiative",
      "id": "<id>",
      "action": "launch"
  }
}
```

***

### orgx\_check\_delegation `read-only`

Classify task complexity or estimate candidate model routes and cost for OrgX agent work. Requires a title or task ID. These operations do not create a task, consume a dispatch rate-limit allowance, or dispatch a run.

**action** `string` *required*

Task classification or route and cost estimate. Options: `classify`, `estimate`.

**title** `string`

Task title. REQUIRED for ad-hoc spawn (action=spawn without task\_id) or action=classify without task\_id. Used as the human-readable label of the spawned task.

**task\_id** `string`

Existing task UUID. REQUIRED for action=handoff. REQUIRED for action=spawn when spawning work for an already-created task. Either task\_id or title (with instructions) must be provided for action=spawn.

**initiative\_id** `string`

Optional initiative UUID to scope the spawned task. Inferred from task\_id when omitted.

**workspace\_id** `string`

Optional workspace UUID to scope the spawned task. Defaults to the MCP session's workspace.

**agent\_type** `string`

Target agent type/domain (e.g. "engineering", "marketing", "design"). REQUIRED for action=guard or action=handoff. Strongly recommended for action=spawn so the work routes to the right specialist.

**instructions** `string`

Delegation instructions for the agent. REQUIRED for action=spawn when spawning ad-hoc (without task\_id). Used to override the task description for action=handoff.

**model\_tier** `string`

Optional model tier override. Omit to let OrgX auto-route from task complexity. Legacy local/sonnet/opus are accepted for older clients. Options: `standard`, `balanced`, `precision`, `local`, `sonnet`, `opus`.

**model** `string`

Optional exact model identifier when the user explicitly selects one. Otherwise OrgX resolves the model from task, tier, provider, policy, and budget.

**provider** `string`

Optional provider preference. Use auto unless the user asks for a specific provider or a cost comparison selects one. Options: `auto`, `openai`, `anthropic`, `openrouter`, `groq`, `local`.

**runtime** `string`

Optional runtime OrgX runs the work on. Omit or auto to let OrgX choose. cloud\_claude / cloud\_openai: OrgX cloud on the Claude Agent SDK or OpenAI Responses. managed\_openai / managed\_anthropic: the OpenAI Agents API or Claude Managed Agents under OrgX governance. local: a paired local peer (Claude Code, Codex, OpenClaw) on the user machine. Options: `auto`, `cloud_claude`, `cloud_openai`, `managed_openai`, `managed_anthropic`, `local`.

**budget\_mode** `string`

Optional budget posture. Use cheapest\_valid for controlled validation runs while reliability is being proven. Options: `cheapest_valid`, `balanced`, `highest_quality`.

**max\_cost\_usd** `number`

Optional hard cost ceiling in USD for this dispatch. If the estimate exceeds it, OrgX blocks, downgrades, or requests approval before dispatch.

**Required Scopes**: `agents:read`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_check_delegation",
  "args": {
      "action": "classify"
  }
}
```

***

### orgx\_command\_status `read-only`

Read the current state of something already started: a decision waiting on a person, an agent run, or a work command. Also known as: is it done yet, did it go through, run status, poll. USE WHEN: a widget or the user needs to know whether a decision, run or command has settled. NEXT: when next\_poll\_after\_ms is a number, check again after that many milliseconds; when it is null the state is final. DO NOT USE: to start or change work. Read-only.

**kind** `string` *required*

What the id refers to Options: `decision`, `run`, `command`.

**id** `string` *required*

Decision, run or command UUID

**Required Scopes**: `decisions:read`

**Profiles**: legacy, claude-plugin, commander, planner, executor, observer

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_command_status",
  "args": {
      "kind": "decision",
      "id": "<id>"
  }
}
```

***

### orgx\_complete\_with\_proof

Complete an OrgX task, milestone, workstream, or initiative with a linked proof artifact and verification evidence. Requires an artifact type and artifact URL or external URL. Records durable evidence and applies completion checks before changing the work state.

**type** `string` *required*

Work entity type to complete with proof. Options: `task`, `milestone`, `workstream`, `initiative`.

**id** `string` *required*

Target entity UUID or short ID prefix (8+ hex chars).

**artifact** `object` *required*

Proof artifact with artifact\_type and artifact\_url or external\_url; optional name, description, and preview\_markdown.

**verification** `string[]`

Optional list of verification evidence URLs/IDs for completion flows.

**quality\_score** `number`

Quality score (0-5) attached to the action when used in proof/completion flows.

**note** `string`

Strongly recommended for destructive or blocking actions (block, flag\_risk, decline, supersede, cancel, delete). Free-text rationale shown in audit history and downstream agent context.

**idempotency\_key** `string`

Optional client-supplied retry key. Update requests transport it outside validated entity fields; lifecycle endpoints deduplicate where supported.

**session\_id** `string`

Optional OrgX session identifier.

**Required Scopes**: `initiatives:write`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_complete_with_proof",
  "args": {
      "type": "task",
      "id": "<id>",
      "artifact": {}
  }
}
```

***

### orgx\_create\_entity

Create one OrgX workspace, initiative, workstream, milestone, task, objective, skill, or blocker record in its default initial workflow state. Accepts per-type parent IDs, titles, and metadata. Initiative creation can publish a public live link when explicitly requested. Reusing an idempotency key returns the existing record instead of creating a duplicate.

**type** `string` *required*

Work record type to create. Options: `workspace`, `initiative`, `workstream`, `milestone`, `task`, `objective`, `skill`, `blocker`.

**title** `string`

REQUIRED on create (provide either "title" or "name" — they are aliases). Display title of the new entity.

**name** `string`

Alternative to "title" on create. REQUIRED on create when "title" is not provided.

**summary** `string`

Short description shown in lists and previews. Recommended on create.

**description** `string`

Longer-form description used in detail views.

**initiative\_id** `string`

Parent initiative UUID. REQUIRED when type="workstream". Optional context for tasks/milestones/artifacts to associate them with an initiative.

**workstream\_id** `string`

Parent workstream UUID. REQUIRED when type="milestone" or type="task".

**milestone\_id** `string`

Parent milestone UUID for tasks. Some workspaces require an explicit backlog milestone under the workstream; create/resolve that milestone first instead of relying on auto-resolution.

**workspace\_id** `string`

Workspace UUID. Defaults to the authenticated session workspace when omitted.

**goal\_ids** `string[]`

Objective UUIDs. Required when the workspace enforces a primary objective.

**priority** `string`

Record urgency. Only low|medium|high|urgent are accepted here; do not send portfolio/live labels such as active, critical, maintenance, or hold. "urgent" is normalized to "high" server-side. Options: `low`, `medium`, `high`, `urgent`.

**due\_date** `string`

Due date as YYYY-MM-DD for supported entity types. Do not send due\_date when type="initiative"; put initiative target dates in metadata.

**run\_id** `string`

REQUIRED when type="blocker". Agent run UUID the blocker applies to.

**step\_id** `string`

Optional agent run step UUID for blocker creation.

**blocker\_type** `string`

Blocker category/type when type="blocker" (e.g. "missing\_input", "permission", "external\_dependency").

**live\_visibility** `string`

Initiative live-link visibility. Only applies when type="initiative". Options: `private`, `public`.

**live\_public** `boolean`

Shortcut to publish an initiative live link (sets live\_visibility="public"). Only applies when type="initiative".

**live\_reveal\_title** `boolean`

When true, public live-link visitors see the initiative title. Only applies when type="initiative" with live\_visibility="public".

**metadata** `object`

Free-form object for type-specific metadata. Schema varies per entity type (e.g. for skills: \{ capabilities, guardrails, channels }; for studio\_brand: \{ tokens, voice, exemplars }).

**tagline** `string`

Workspace tagline when type="workspace".

**narrative** `string`

Workspace identity narrative when type="workspace".

**key\_metrics** `string[]`

Workspace identity metrics when type="workspace".

**roadmap\_url** `string`

Workspace roadmap URL when type="workspace".

**source\_links** `string[]`

Workspace source links when type="workspace".

**set\_active** `boolean`

For workspace create, make the new workspace active. Defaults true.

**idempotency\_key** `string`

Client-generated retry key. Creates deduplicate by key; updates transport the key outside validated entity fields.

**session\_id** `string`

Optional OrgX session identifier.

**Required Scopes**: `decisions:write`, `agents:write`, `initiatives:write`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_create_entity",
  "args": {
      "type": "workspace"
  }
}
```

***

### orgx\_delegate\_work

Dispatch OrgX specialist agent work for an existing task or a new task with a title and instructions. spawn creates or runs delegated work; handoff reassigns an existing task to an agent type. Delegation can incur model costs and interact with connected services. Applies durable assignment, deadline, budget, acceptance, permission, and idempotency constraints.

**action** `string`

Dispatch new agent work or hand off an existing task. Options: `spawn`, `handoff`. Default: `"spawn"`.

**title** `string`

Task title. REQUIRED for ad-hoc spawn (action=spawn without task\_id) or action=classify without task\_id. Used as the human-readable label of the spawned task.

**task\_id** `string`

Existing task UUID. REQUIRED for action=handoff. REQUIRED for action=spawn when spawning work for an already-created task. Either task\_id or title (with instructions) must be provided for action=spawn.

**initiative\_id** `string`

Optional initiative UUID to scope the spawned task. Inferred from task\_id when omitted.

**workspace\_id** `string`

Optional workspace UUID to scope the spawned task. Defaults to the MCP session's workspace.

**agent\_type** `string`

Target agent type/domain (e.g. "engineering", "marketing", "design"). REQUIRED for action=guard or action=handoff. Strongly recommended for action=spawn so the work routes to the right specialist.

**instructions** `string`

Delegation instructions for the agent. REQUIRED for action=spawn when spawning ad-hoc (without task\_id). Used to override the task description for action=handoff.

**model\_tier** `string`

Optional model tier override. Omit to let OrgX auto-route from task complexity. Legacy local/sonnet/opus are accepted for older clients. Options: `standard`, `balanced`, `precision`, `local`, `sonnet`, `opus`.

**model** `string`

Optional exact model identifier when the user explicitly selects one. Otherwise OrgX resolves the model from task, tier, provider, policy, and budget.

**provider** `string`

Optional provider preference. Use auto unless the user asks for a specific provider or a cost comparison selects one. Options: `auto`, `openai`, `anthropic`, `openrouter`, `groq`, `local`.

**runtime** `string`

Optional runtime OrgX runs the work on. Omit or auto to let OrgX choose. cloud\_claude / cloud\_openai: OrgX cloud on the Claude Agent SDK or OpenAI Responses. managed\_openai / managed\_anthropic: the OpenAI Agents API or Claude Managed Agents under OrgX governance. local: a paired local peer (Claude Code, Codex, OpenClaw) on the user machine. Options: `auto`, `cloud_claude`, `cloud_openai`, `managed_openai`, `managed_anthropic`, `local`.

**deadline** `string`

Optional ISO-8601 instant by which the work must finish (e.g. "2026-09-28T17:00:00Z"). Validated and recorded; free text is rejected because a constraint that cannot be evaluated is not a constraint.

**max\_cost\_usd** `number`

Optional hard cost ceiling in USD for this dispatch. If the estimate exceeds it, OrgX blocks, downgrades, or requests approval before dispatch.

**budget\_mode** `string`

Optional budget posture. Use cheapest\_valid for controlled validation runs while reliability is being proven. Options: `cheapest_valid`, `balanced`, `highest_quality`.

**max\_parallel** `integer`

Optional cap on concurrent workers for this dispatch. Work that shares a repository is usually integration-bound well below this: more workers add merge contention, not throughput.

**expected\_artifacts** `string[]`

Optional expected final-output labels. Declaring at least one adds an artifact contract to the run.

**effects** `object`

Optional declared effect scope for the work. Recorded on the run and shown in the receipt. Declaring an effect never grants it — the platform intersects it with the caller authority.

**acceptance** `object[]`

Optional acceptance checks that define what counts as done. Declared BEFORE the work and hashed at dispatch. A check that already passes on the pre-state is reported as non-discriminating and excluded from the verdict.

**idempotency\_key** `string`

Optional client-supplied idempotency key for safe retries. The same key returns the same dispatch result without re-running the work.

**session\_id** `string`

Optional OrgX session identifier.

**Required Scopes**: `agents:write`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_delegate_work",
  "args": {}
}
```

***

### orgx\_emit\_execution\_graph

Emit the deterministic execution graph + trust ledger for the active run from explicit nodes, OTel semantic events, or both. OTel promotion requires orgx.material=true plus episode/kind attributes; inferred events stay gaps and raw prompts are never retained. OrgX derives false-completion, hallucinated-receipt, and dependency-violation signals from this and surfaces them on /live. USE WHEN: reporting the structured shape of multi-step work — NOT a single progress line (use orgx\_emit\_activity for that). NEXT: continue work; re-emit as the graph advances (idempotent per run + graph fingerprint). DO NOT USE to mark entities complete — telemetry only.

**initiative\_id** `string` *required*

Initiative UUID

**run\_id** `string`

Existing run UUID

**correlation\_id** `string`

Required when run\_id is not provided

**source\_client** `string`

Required when run\_id is not provided Options: `openclaw`, `codex`, `claude-code`, `chatgpt`, `cursor`, `copilot`, `gemini`, `opencode`, `cline`, `goose`, `qwen`, `kiro`, `web-ui`, `api`.

**runtime** `object`

Runtime provenance used by /live to bucket chokepoints

**summary** `string`

Optional human-readable rollup of the graph state

**nodes** `object[]`

Execution graph nodes; each carries claimed status + optional verification

**otel\_events** `object[]`

Raw OTel-compatible events to semantically promote. Only explicitly material native/observed facts become graph nodes; prompts and inferred reasoning do not.

**edges** `object[]`

depends\_on edges between node ids

**trust\_events** `object[]`

Explicit trust-ledger events such as authority\_exceeded that OrgX cannot infer from graph shape

**metadata** `object`

Optional structured metadata to attach to the execution-graph emission

**Required Scopes**: `initiatives:write`

**Profiles**: legacy, commander, executor

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_emit_execution_graph",
  "args": {
      "initiative_id": "<initiative_id>"
  }
}
```

***

### orgx\_expect

Register an OrgX prediction before acting. mode=task\_prediction records the expected outcome, confidence, and met/unmet predictions for criteria in the task's current agreed expectation set; it requires the exact set ID/version and an idempotency\_key. Checked receipt evidence resolves those predictions. mode=metric\_coverage (default) registers the exact orgx.run\_receipt\_coverage.v1 observer before its window starts, with defaults of at least 95% within 60 seconds over at least 20 runs. USE WHEN: stating a task prediction before work starts or registering the supported delayed reliability result. NEXT: inspect the task and its agreed criteria; submit receipt evidence when work finishes. DO NOT USE WHEN: reporting completion — use orgx\_submit\_receipt; or registering an unsupported metric.

**mode** `string`

metric\_coverage (default) registers the supported delayed observer; task\_prediction records expected task results before acting. Options: `metric_coverage`, `task_prediction`.

**metric** `string`

Required for metric\_coverage: exact observer registry ID.

**workspace\_id** `string`

Workspace UUID. Defaults to the MCP session workspace. The subject and metric scope are derived from this exact workspace.

**window\_starts\_at** `string`

Required for metric\_coverage: future ISO-8601 datetime with timezone offset. Registration is rejected after this window begins.

**window\_ends\_at** `string`

Required for metric\_coverage: ISO-8601 datetime with timezone offset, after window\_starts\_at and no more than 31 days later.

**threshold** `number`

Required receipt coverage ratio. Defaults to 0.95. The predicate is fixed to greater-than-or-equal.

**minimum\_sample\_size** `integer`

Minimum terminal-run denominator required for a conclusive result. Defaults to 20.

**receipt\_deadline\_seconds** `integer`

Maximum seconds from terminal session end to durable automatic receipt. Defaults to 60.

**evaluation\_interval\_seconds** `integer`

Retry cadence when the observer is unavailable. Defaults to 300 seconds.

**task\_id** `string`

Required for task\_prediction: task UUID. The task must be ready to start.

**expectation\_set\_id** `string`

Required for task\_prediction: UUID of the current agreed expectation set that applies to this task.

**expectation\_set\_version** `integer`

Required for task\_prediction: exact persisted version of that agreed expectation set.

**expected\_outcome** `string`

Required for task\_prediction: expected task outcome, stated before acting.

**confidence** `number`

Required for task\_prediction: confidence in the expected outcome, from 0 to 1.

**criteria\_predictions** `object[]`

Required for task\_prediction: 1 to 50 unique criterion IDs from that set, each with predicted met/unmet and confidence from 0 to 1.

**idempotency\_key** `string`

Required for task\_prediction. Sent as Idempotency-Key; reuse the same key when retrying. Generated when omitted for metric\_coverage.

**session\_id** `string`

Optional bootstrap/session identifier returned by orgx\_bootstrap.

**Required Scopes**: `initiatives:write`

**Profiles**: legacy, claude-plugin, memory, commander, planner, executor

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_expect",
  "args": {}
}
```

***

### orgx\_free\_audit `read-only`

Use when a workspace wants to know how ready it is for autonomous agent work before spending anything. Runs a free autonomy benchmark from trust, proof, ROI, and workspace signals. Returns Proof Score, Context Debt, Autonomy Maturity, ROI Visibility, and next recommendations without starting an autonomous session or consuming agent credits.

**workspace\_id** `string` *required*

Workspace ID to audit

**agent\_type** `string`

Agent type to benchmark trust against Default: `"orchestrator"`.

**period** `string`

ROI attribution period used for ROI Visibility Options: `7d`, `30d`, `90d`. Default: `"30d"`.

**include\_raw\_signals** `boolean`

Include raw upstream signal payloads for debugging and verification Default: `false`.

**Required Scopes**: `agents:read`, `initiatives:read`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_free_audit",
  "args": {
      "workspace_id": "<workspace_id>"
  }
}
```

***

### orgx\_improve\_plan

Submit the current draft of a durable OrgX plan for critique and improvement. Updates planning session state using the supplied session ID and markdown plan content. Supports an idempotency key for retries.

**session\_id** `string` *required*

Plan session UUID or orgx://plan\_session/\<uuid> URI.

**plan\_content** `string` *required*

Current markdown plan draft to improve.

**idempotency\_key** `string`

Optional idempotency key for safe retries. Same key returns the same result without creating duplicate session state.

**Required Scopes**: `initiatives:write`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_improve_plan",
  "args": {
      "session_id": "<session_id>",
      "plan_content": "<plan_content>"
  }
}
```

***

### orgx\_poll\_attention `read-only`

Read the durable owner response and continuation state for orgx\_request\_attention. USE WHEN: the client has a preserved attention\_id and must determine whether the owner answered without creating another request. When resolved=true, apply the answer to the preserved session. NEXT: call orgx\_ack\_attention with state=resuming, then state=resumed only after native execution actually restarts. Read-only.

**attention\_id** `string` *required*

Attention/decision UUID

**Required Scopes**: `initiatives:read`

**Profiles**: legacy, commander, planner, executor, observer

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_poll_attention",
  "args": {
      "attention_id": "<attention_id>"
  }
}
```

***

### orgx\_poll\_question `read-only`

Read the durable answer receipt for a question previously forwarded with orgx\_request\_question. USE WHEN: an external client is paused for human input. NEXT: when resolved=true and continuation.should\_resume=true, resume the preserved source session with answer and resolution\_context; when false, remain paused without creating another question. Read-only.

**question\_id** `string` *required*

Question/decision UUID returned by orgx\_request\_question

**Required Scopes**: `initiatives:read`

**Profiles**: legacy, commander, planner, executor, observer

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_poll_question",
  "args": {
      "question_id": "<question_id>"
  }
}
```

***

### orgx\_record\_decision

Create or remember a durable OrgX decision with its rationale and provenance. create requires a title and decision text; remember accepts decision text and an optional title. Can associate the record with an initiative and deduplicate retries with an idempotency key. Does not approve a pending decision.

**action** `string`

Create a named decision or remember decision text. Options: `create`, `remember`. Default: `"create"`.

**title** `string`

Short title for the decision. REQUIRED for action=create.

**decision** `string` *required*

Decision text to record.

**summary** `string`

Optional one-line summary used in lists. Falls back to title when omitted.

**context** `string`

Background context / rationale that led to the decision. Recommended for action=create to capture provenance.

**initiative\_id** `string`

Optional initiative UUID to scope the decision. Used as filter when action=list\_pending; used as parent when action=create.

**workspace\_id** `string`

Optional workspace UUID to scope the decision. Defaults to the MCP session's workspace.

**idempotency\_key** `string`

Strongly recommended client-supplied idempotency key for action=create or action=remember. Same key returns the same result without duplicating state.

**session\_id** `string`

Optional OrgX session identifier.

**Required Scopes**: `decisions:write`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_record_decision",
  "args": {
      "decision": "<decision>"
  }
}
```

***

### orgx\_request\_attention

Forward a typed human-interruption request while preserving the originating run and session. Use kind=question for missing context, permission for a scoped tool or file action, approval for owner sign-off, and recovery only when automatic retry cannot safely continue. USE WHEN: a native client reaches a genuine human decision that prevents the preserved session from continuing safely. NEXT: poll orgx\_poll\_attention; resume only after the answer is applied, then call orgx\_ack\_attention so Live can show that work actually restarted. DO NOT USE: for internal turn boundaries or retryable runtime events.

**initiative\_id** `string` *required*

Initiative UUID

**attention\_kind** `string` *required*

Why human attention is required Options: `question`, `permission`, `approval`, `recovery`.

**idempotency\_key** `string` *required*

Stable key for safe retries of this request

**question** `string` *required*

The concrete request the owner must answer

**context** `string`

What led here, what is preserved, and what the answer changes

**impact\_if\_delayed** `string`

What remains paused or at risk until the owner responds

**options** `object[]`

Pre-allocated valid responses

**response\_mode** `string`

Answer control; inferred from options when omitted Options: `single_select`, `multi_select`, `free_text`, `confirmation`.

**recommended\_option\_id** `string`

Recommended option when the agent can justify one

**recommended\_action** `string`

Concise recommendation and why it is safest or highest leverage

**blocking** `boolean`

Whether linked work is gated; default true

**urgency** `string`

Owner attention urgency; default medium Options: `low`, `medium`, `high`, `urgent`.

**workstream\_id** `string`

Affected workstream UUID

**run\_id** `string`

Existing OrgX run UUID

**correlation\_id** `string`

Stable client correlation when run\_id is unavailable

**source\_client** `string`

Originating native client Options: `openclaw`, `codex`, `claude-code`, `chatgpt`, `cursor`, `copilot`, `gemini`, `opencode`, `cline`, `goose`, `qwen`, `kiro`, `web-ui`, `api`.

**runtime** `object`

Runtime and provider provenance for the preserved execution

**source\_session\_id** `string`

Originating client session identifier

**source\_tool** `string` *required*

Native hook or tool that requested attention

**source\_event\_id** `string`

Originating hook or tool-call event identifier

**source\_ref** `object`

Additional non-secret source and continuation references

**continuation** `object`

How OrgX should return the answer to the preserved client session

**metadata** `object`

Additional non-secret request context

**Required Scopes**: `initiatives:write`

**Profiles**: legacy, commander, planner, executor

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_request_attention",
  "args": {
      "initiative_id": "<initiative_id>",
      "attention_kind": "question",
      "idempotency_key": "<idempotency_key>",
      "question": "<question>",
      "source_tool": "<source_tool>"
  }
}
```

***

### orgx\_request\_question

Pause at a safe checkpoint and forward a contextual question to the initiative owner. OrgX renders the right single-select, multi-select, free-text, or confirmation control and preserves the source run/session so work can resume with the exact answer. USE WHEN: Claude Code AskUserQuestion, Codex request\_user\_input, Cursor, OpenClaw, or another client needs human judgment to continue. NEXT: poll orgx\_poll\_question with the returned question\_id; continue only when continuation.should\_resume is true. DO NOT USE: for runtime failures with an automatic retry path — report a chokepoint instead.

**initiative\_id** `string` *required*

Initiative UUID

**idempotency\_key** `string` *required*

Stable key for safe retries of the same question

**question** `string` *required*

The concrete question the owner must answer

**context** `string`

What led here, what is preserved, and what the answer changes

**options** `object[]`

Pre-allocated answers for single-select or multi-select questions

**response\_mode** `string`

Answer control; inferred from options when omitted Options: `single_select`, `multi_select`, `free_text`, `confirmation`.

**blocking** `boolean`

Whether this answer gates the linked work; default true

**urgency** `string`

Owner attention urgency; default medium Options: `low`, `medium`, `high`, `urgent`.

**workstream\_id** `string`

Affected workstream UUID

**run\_id** `string`

Existing run UUID

**correlation\_id** `string`

Required with source\_client when run\_id is absent

**source\_client** `string`

Originating client; required when run\_id is absent Options: `openclaw`, `codex`, `claude-code`, `chatgpt`, `cursor`, `copilot`, `gemini`, `opencode`, `cline`, `goose`, `qwen`, `kiro`, `web-ui`, `api`.

**runtime** `object`

Runtime/provider provenance for the paused execution

**source\_session\_id** `string`

Claude, Codex, Cursor, or other client session identifier

**source\_tool** `string` *required*

Originating tool, e.g. AskUserQuestion or request\_user\_input

**source\_event\_id** `string`

Originating question/tool-call event identifier

**source\_ref** `object`

Additional non-secret client continuation references

**metadata** `object`

Additional non-secret structured context

**Required Scopes**: `initiatives:write`

**Profiles**: legacy, commander, planner, executor

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_request_question",
  "args": {
      "initiative_id": "<initiative_id>",
      "idempotency_key": "<idempotency_key>",
      "question": "<question>",
      "source_tool": "<source_tool>"
  }
}
```

***

### orgx\_tail `read-only`

Use during a long-running session to read accepted material state changes since orgx\_bootstrap. Pass the exact capsule\_id and as\_of\_global\_sequence returned by bootstrap. Returns only the currently ledger-backed allowlist in ascending global-sequence order: accepted/superseded decisions, authority lease changes, blocker changes, and metric-expectation registration/resolution. It explicitly reports material classes that are not ledger-backed yet. Read-only. USE WHEN: the session may have outlived its bootstrap context. NEXT: use next\_after\_sequence while has\_more=true to inspect the feed, then bootstrap current context before consequential action. The capsule base is not verified; this feed cannot establish complete or coherent current state. DO NOT USE: as a substitute for orgx\_bootstrap or to infer applied learning, constraints, or incidents that the coverage boundary marks unavailable.

**capsule\_id** `string` *required*

Exact capsule\_id returned by orgx\_bootstrap.

**after\_sequence** `integer` *required*

Exact as\_of\_global\_sequence or next\_after\_sequence from the previous call.

**workspace\_id** `string`

Workspace UUID. Defaults to the MCP session workspace.

**limit** `integer`

Maximum material changes per page (1-100).

**session\_id** `string`

Optional bootstrap/session identifier returned by orgx\_bootstrap.

**Required Scopes**: `initiatives:read`

**Profiles**: legacy, claude-plugin, commander, executor, observer

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_tail",
  "args": {
      "capsule_id": "<capsule_id>",
      "after_sequence": 0
  }
}
```

***

### orgx\_update\_entity

Update the content of one existing OrgX workspace, initiative, workstream, milestone, task, objective, or skill selected by type and ID. Supports titles, summaries, descriptions, priority, due date, objectives, and metadata. The patch overwrites only supplied fields. It cannot change workflow status, approve work, or mark completion.

**type** `string` *required*

Work record type whose content should change. Options: `workspace`, `initiative`, `workstream`, `milestone`, `task`, `objective`, `skill`.

**id** `string` *required*

Existing entity UUID.

**fields** `object` *required*

Nonempty content patch. Workflow status, approval, ownership, and completion fields are not accepted.

**idempotency\_key** `string`

Client-generated retry key. Creates deduplicate by key; updates transport the key outside validated entity fields.

**session\_id** `string`

Optional OrgX session identifier.

**Required Scopes**: `decisions:write`, `agents:write`, `initiatives:write`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_update_entity",
  "args": {
      "type": "workspace",
      "id": "<id>",
      "fields": {}
  }
}
```

***

### orgx\_widget\_decide

Widget-only: settles one pending item (a decision of any type, an agent-run approval, or an action awaiting approval) after the person clicks in the decisions widget or the OrgX panel. Sends what the item's widget\_actions ask for: an option, several options, a typed answer or a reason. USE WHEN: the widget sends a click with its approval token from result metadata, which models never see. NEXT: the widget shows the item as settled. DO NOT USE: from a model or without a widget approval token; use approve\_decision or reject\_decision to point the person to where they decide.

**decision\_id** `string` *required*

Pending item being settled (decision, agent-run approval or action id)

**kind** `string`

The item's widget\_actions.kind. Defaults to decision. Options: `decision`, `approval`, `action`.

**action** `string` *required*

approve or reject Options: `approve`, `reject`.

**reason** `string`

What should change. Required when rejecting if widget\_actions.reject\_requires\_reason, and when the chosen option requires a reason

**answer** `string`

Typed answer when widget\_actions.answer asks for one

**option\_id** `string`

The option the person chose, when widget\_actions.selection.mode is single

**option\_ids** `string[]`

The options the person chose, when widget\_actions.selection.mode is multiple

**approval\_token** `string` *required*

Widget approval token

**Required Scopes**: `decisions:write`

**Profiles**: v2, legacy, extended, chatgpt, memory, commander, planner, observer

**Availability**: Human widget callback; unavailable to the model.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_widget_decide",
  "args": {
      "decision_id": "<decision_id>",
      "action": "approve",
      "approval_token": "<approval_token>"
  }
}
```

***

### queue\_action

Pin, unpin, or skip a workstream in the Next Up queue. USE WHEN: user wants to force-prioritize or deprioritize a workstream. action=pin to force-top, action=unpin to remove pin, action=skip to temporarily deprioritize. Requires initiatives:write.

**action** `string` *required*

Queue operation Options: `pin`, `unpin`, `skip`.

**initiative\_id** `string` *required*

Initiative UUID

**workstream\_id** `string` *required*

Workstream UUID

**workspace\_id** `string`

Workspace UUID

**command\_center\_id** `string`

Deprecated alias for workspace\_id

**rank** `number`

Position among pinned items, 0=top (pin only)

**duration\_minutes** `number`

Skip duration in minutes, default 60, max 10080 (skip only)

**Required Scopes**: `initiatives:write`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "queue_action",
  "args": {
      "action": "pin",
      "initiative_id": "<initiative_id>",
      "workstream_id": "<workstream_id>"
  }
}
```

***

### request\_independent\_artifact\_review

Queue OrgX's independent evaluator for one completed agent artifact. The producing agent cannot supply or choose the score. OrgX persists the native evaluation and its 1–5 rating projection under the rubric version. USE WHEN: an agent has produced one final artifact and you need an independently scored record. NEXT: inspect the artifact evals after the queued evaluation completes. DO NOT USE: for drafts or to record a self-score.

**artifact\_id** `string` *required*

Completed work\_artifacts UUID to evaluate

**Required Scopes**: `initiatives:write`

**Profiles**: legacy

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "request_independent_artifact_review",
  "args": {
      "artifact_id": "<artifact_id>"
  }
}
```

***

### resume\_agent\_run

Widget-only: resumes a paused or TTL auto-closed agent run after the person clicks Resume in the agent-status widget.

**run\_id** `string` *required*

Agent run UUID to resume.

**note** `string`

Optional audit note.

**Required Scopes**: `decisions:write`, `agents:write`, `initiatives:write`

**Profiles**: v2, legacy, extended, chatgpt, memory, commander, planner, executor, observer

**Availability**: Human widget callback; unavailable to the model.

**Request**:

```json theme={"dark"}
{
  "tool": "resume_agent_run",
  "args": {
      "run_id": "<run_id>"
  }
}
```

***

### scoring\_config

Read or update scoring engine configuration. USE WHEN: user asks about scoring setup, wants to toggle scoring, adjust weights, or change active signals. action=get to read, action=update to modify. NEXT: Run recommend\_next\_action to see effects in the preferred workflow, or the deprecated alias if you need raw queue scoring. Read-only for get, requires initiatives:write for update.

**action** `string` *required*

get=read config, update=modify settings Options: `get`, `update`.

**workspace\_id** `string`

Workspace UUID

**command\_center\_id** `string`

Deprecated alias for workspace\_id

**enabled** `boolean`

Enable/disable scoring\_v2 (action=update only)

**active\_signals** `string[]`

Signal names to activate (action=update only)

**weights** `object`

Partial weight overrides e.g. \{ priority: 300 } (action=update only)

**Required Scopes**: `decisions:read`, `agents:read`, `initiatives:read`, `memory:read`

**Profiles**: Internal source definition

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "scoring_config",
  "args": {
      "action": "get"
  }
}
```

***

## Legacy and internal: Proof Runtime v1

3 tools for proof runtime v1 operations.

### orgx\_complete\_work

Marks a v1 ledger work item complete (POST /api/v1/commands/complete-work) with optimistic concurrency: expected\_updated\_at and expected\_aggregate\_version must match the current task record or the command returns a conflict — read them fresh, never guess. Records summary, evidence, and cost on the completion event; it does not verify the work. An Idempotency-Key is generated when none is supplied. USE WHEN: closing a ledger-backed work item created with orgx\_create\_work. NEXT: orgx\_submit\_receipt for durable proof of the completed work. DO NOT USE WHEN: completing ordinary OrgX tasks — use orgx\_act (complete\_with\_proof); or on a version conflict — re-read the task and retry with current values.

**workspace\_id** `string`

Workspace UUID. Defaults to the MCP session's workspace when omitted.

**task\_id** `string` *required*

REQUIRED. UUID of the ledger work item to complete.

**expected\_updated\_at** `string` *required*

REQUIRED. The task's current updated\_at as an ISO datetime with timezone offset. A mismatch returns a conflict.

**expected\_aggregate\_version** `integer` *required*

REQUIRED. The task's current aggregate version. A mismatch returns a conflict.

**summary** `string`

Completion summary (max 4000 characters).

**evidence** `object`

Free-form JSON evidence recorded on the completion event.

**cost\_cents** `integer`

Actual cost in cents. Defaults to 0.

**causation\_id** `string`

Optional UUID of the event that caused this command.

**correlation\_id** `string`

Optional correlation UUID linking related commands.

**idempotency\_key** `string`

Client-supplied retry key sent as the Idempotency-Key header. Generated when omitted; reuse the same key to retry safely.

**session\_id** `string`

Optional bootstrap/session identifier returned by orgx\_bootstrap.

**Required Scopes**: `initiatives:write`

**Profiles**: commander, executor

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_complete_work",
  "args": {
      "task_id": "<task_id>",
      "expected_updated_at": "<expected_updated_at>",
      "expected_aggregate_version": 0
  }
}
```

***

### orgx\_create\_work

Accepts organizational work onto the v1 proof-runtime ledger (POST /api/v1/commands/create-work). Records the work item as a command event; it does not start external execution. Requires an existing initiative + workstream + milestone chain. An Idempotency-Key is generated when none is supplied; retrying with the same idempotency\_key returns the original result instead of duplicating. USE WHEN: registering a ledger-backed work item under an existing milestone so its lifecycle is event-sourced. NEXT: orgx\_complete\_work when the work finishes, or orgx\_events\_tail to watch the recorded events. DO NOT USE WHEN: creating initiatives, workstreams, milestones, or ordinary tasks — use orgx\_write; or when dispatching an agent — use orgx\_spawn.

**workspace\_id** `string`

Workspace UUID. Defaults to the MCP session's workspace when omitted.

**title** `string` *required*

Work item title (max 240 characters).

**description** `string`

Longer description (max 4000 characters).

**initiative\_id** `string` *required*

REQUIRED. Parent initiative UUID.

**workstream\_id** `string` *required*

REQUIRED. Parent workstream UUID.

**milestone\_id** `string` *required*

REQUIRED. Parent milestone UUID.

**priority** `string`

Priority. Defaults to medium. Options: `low`, `medium`, `high`, `urgent`.

**due\_date** `string`

Due date as YYYY-MM-DD.

**metadata** `object`

Free-form JSON metadata stored on the work item.

**estimated\_cost\_cents** `integer`

Estimated cost in cents. Defaults to 0.

**command\_id** `string`

Client-supplied command UUID. Generated when omitted.

**expected\_aggregate\_version** `integer`

Must be 0 when provided — create-work targets a brand-new aggregate. Sent as 0 by default.

**causation\_id** `string`

Optional UUID of the event that caused this command.

**correlation\_id** `string`

Optional correlation UUID linking related commands.

**idempotency\_key** `string`

Client-supplied retry key sent as the Idempotency-Key header. Generated when omitted; reuse the same key to retry safely.

**session\_id** `string`

Optional bootstrap/session identifier returned by orgx\_bootstrap.

**Required Scopes**: `initiatives:write`

**Profiles**: commander, executor

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_create_work",
  "args": {
      "title": "<title>",
      "initiative_id": "<initiative_id>",
      "workstream_id": "<workstream_id>",
      "milestone_id": "<milestone_id>"
  }
}
```

***

### orgx\_events\_tail `read-only`

Reads the workspace's v1 ledger event stream (GET /api/v1/events/stream) in JSON cursor-page mode — never SSE. Returns events newest-first plus meta.nextCursor/hasMore; pass the returned cursor back (cursor or after) to continue paging. Read-only. USE WHEN: tailing what the proof runtime recorded — work commands, completions, receipts — or resuming from a saved cursor. NEXT: orgx\_inspect for one referenced entity, or call again with the returned cursor while hasMore=true.

**workspace\_id** `string`

Workspace UUID. Defaults to the MCP session's workspace when omitted.

**after** `string`

Cursor from a previous page (alias of cursor): returns the page after it.

**cursor** `string`

Opaque cursor from meta.nextCursor of a previous page.

**limit** `integer`

Maximum events per page (1-100).

**event\_type** `string`

Optional event type filter. Comma-separate multiple types.

**aggregate\_type** `string`

Optional aggregate type filter (lowercase identifier).

**session\_id** `string`

Optional bootstrap/session identifier returned by orgx\_bootstrap.

**Required Scopes**: `initiatives:read`

**Profiles**: commander, executor, observer

**Availability**: Legacy or internal source definition; unavailable in the default ChatGPT and v2 profiles.

**Request**:

```json theme={"dark"}
{
  "tool": "orgx_events_tail",
  "args": {}
}
```

***

## Deprecated Tools

> [!WARNING]
>
> The following names are not part of the current published tool set. They are
> retained here only to help existing clients migrate to current operations.

| Deprecated Tool | Replacement | Migration Note |
| - | - | - |
| `create_initiative` | create\_entity type=initiative (or scaffold\_initiative for full hierarchy) | The create\_initiative tool has been replaced by the generic entity system. |
| `list_initiatives` | list\_entities type=initiative | The list\_initiatives tool has been replaced by the generic entity system. |
| `create_milestone` | create\_entity type=milestone | The create\_milestone tool has been replaced by the generic entity system. |
| `create_task` | create\_entity type=task | The create\_task tool has been replaced by the generic entity system. |
| `launch_entity` | entity\_action action=launch | The launch\_entity tool has been replaced by the unified entity\_action tool. |
| `pause_entity` | entity\_action action=pause | The pause\_entity tool has been replaced by the unified entity\_action tool. |
| `complete_entity` | entity\_action action=complete | The complete\_entity tool has been replaced by the unified entity\_action tool. |
| `create_entity` | Use the current resource-specific MCP operation. | Migration alias; not part of the current published tool set. |
| `create_decision` | Use the current resource-specific MCP operation. | Migration alias; not part of the current published tool set. |
| `remember_decision` | Use the current resource-specific MCP operation. | Migration alias; not part of the current published tool set. |
| `entity_action` | Use the current resource-specific MCP operation. | Migration alias; not part of the current published tool set. |
| `verify_entity_completion` | Use the current resource-specific MCP operation. | Migration alias; not part of the current published tool set. |
| `save_artifact` | Use the current resource-specific MCP operation. | Migration alias; not part of the current published tool set. |
| `score_next_up_queue` | Use the current resource-specific MCP operation. | Migration alias; not part of the current published tool set. |
| `get_outcome_attribution` | Use the current resource-specific MCP operation. | Migration alias; not part of the current published tool set. |
| `validate_studio_content` | Use the current resource-specific MCP operation. | Migration alias; not part of the current published tool set. |
| `get_task_with_context` | Use the current resource-specific MCP operation. | Migration alias; not part of the current published tool set. |
| `list_entities` | Use the current resource-specific MCP operation. | Migration alias; not part of the current published tool set. |
| `query_org_memory` | Use the current resource-specific MCP operation. | Migration alias; not part of the current published tool set. |

***

## Next Steps

> [card] [MCP Protocol](https://docs.useorgx.com/docs/api/mcp-protocol.md)
>
> Protocol implementation details.

> [card] [Agent Ops](https://docs.useorgx.com/docs/agent-ops/agent-quickstart.md)
>
> Get started with agent workflows.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.