MCP Tools Reference

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.

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.

string

required

Options: playbook.

string

required

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

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.

string

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

string

Optional OrgX conversation-session context.

Required Scopes: initiatives:write Profiles: extended Availability: Extended profile model operation. Request:

{
  "tool": "orgx_activate_work",
  "args": {
      "type": "playbook",
      "id": "<id>"
  }
}

orgx_archive_work

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

string

required

Options: initiative, objective, playbook.

string

required

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

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.

string

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

string

Optional OrgX conversation-session context.

Required Scopes: initiatives:write Profiles: extended Availability: Extended profile model operation. Request:

{
  "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.

string

required

Options: initiative, workstream, milestone, task.

string

required

Target entity UUID or short ID prefix

string

required

Artifact title

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.

string

Artifact description

string

Optional markdown preview shown with the linked artifact. Does not replace artifact_url/external_url.

string

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

string

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

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.

string

Human or agent owner for the next review/action. Stored under metadata.artifact_contract.

string

Date or cadence for the next review point. Stored under metadata.artifact_contract.

string[]

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

string

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

string

Optional OrgX conversation-session context.

any

required

Durable internal or external artifact URL.

Required Scopes: initiatives:write Profiles: v2, extended, chatgpt Availability: Default ChatGPT and v2 model operation. Request:

{
  "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.

string

required

Options: task, workstream.

string

required

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

string

required

string

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

string

Optional OrgX conversation-session context.

Required Scopes: initiatives:write Profiles: extended Availability: Extended profile model operation. Request:

{
  "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.

string

required

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

string

required

UUID of the node

Required Scopes: agents:write, initiatives:write Profiles: v2, extended, chatgpt Availability: Default ChatGPT and v2 model operation. Request:

{
  "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.

string

required

string

Short title for the decision.

string

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

string

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

string

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

string

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

string

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

string

Optional OrgX conversation-session context.

Required Scopes: decisions:write Profiles: v2, extended, chatgpt Availability: Default ChatGPT and v2 model operation. Request:

{
  "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.

string

required

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

string

Existing task UUID.

string

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

string

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

string

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

Required Scopes: agents:read Profiles: extended Availability: Extended profile model operation. Request:

{
  "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.

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:

{
  "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.

string

required

Display title for the new work record.

string

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

string

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

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.

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.

string

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

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:

{
  "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.

string

required

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

string

required

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

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.

string

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

string

Optional OrgX conversation-session context.

Required Scopes: initiatives:write Profiles: extended Availability: Extended profile model operation. Request:

{
  "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.

string

required

Plan session UUID or orgx://plan_session/<uuid> URI.

string

required

integer

required

Authoritative plan_ref.version from the most recent read. Required to prevent overwriting another edit.

object[]

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:

{
  "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.

string

required

Options: initiative, workstream, milestone, task.

string

required

object

required

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.

number

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

string

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

string

Optional OrgX conversation-session context.

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:

{
  "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.

string

required

Display title for the new work record.

string

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

string[]

object[]

object

object[]

object

any

string

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

boolean

integer

object

Required Scopes: agents:write, initiatives:write Profiles: extended Availability: Extended profile model operation. Request:

{
  "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.

string

required

Display title for the new work record.

string

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

string

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

string

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

string

required

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

string

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

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.

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.

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.

number

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

string

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

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.

string[]

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

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.

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.

string

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

string

Optional OrgX conversation-session context.

Required Scopes: agents:write Profiles: extended Availability: Extended profile model operation. Request:

{
  "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.

string

required

Display title for the new work record.

string

required

string

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

string

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

string

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

string

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

string

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

string

Optional OrgX conversation-session context.

Required Scopes: decisions:write Profiles: extended Availability: Extended profile model operation. Request:

{
  "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.

string

required

Display title for the new work record.

string

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

string

Longer-form description used in detail views.

string

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

string[]

Objective UUIDs. Required when workspace policy enforces primary objectives.

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.

object

string

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

string

Optional OrgX conversation-session context.

Required Scopes: initiatives:write Profiles: v2, extended, chatgpt Availability: Default ChatGPT and v2 model operation. Request:

{
  "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.

string

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

object

required

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

object

string

required

Required Scopes: initiatives:write Profiles: v2, extended, chatgpt Availability: Default ChatGPT and v2 model operation. Request:

{
  "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.

string

required

Display title for the new work record.

string

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

string

Longer-form description used in detail views.

string

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

string[]

Objective UUIDs. Required when workspace policy enforces primary objectives.

string

object

string

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

string

Optional OrgX conversation-session context.

string

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

string

required

Parent workstream UUID.

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:

{
  "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.

string

required

Display title for the new work record.

string

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

string

Longer-form description used in detail views.

string

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

string[]

Objective UUIDs. Required when workspace policy enforces primary objectives.

string

object

string

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

string

Optional OrgX conversation-session context.

string

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

string

required

Parent workstream UUID.

string

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

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:

{
  "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.

string

required

Display title for the new work record.

string

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

string

Longer-form description used in detail views.

string

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

string[]

Objective UUIDs. Required when workspace policy enforces primary objectives.

string

object

string

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

string

Optional OrgX conversation-session context.

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:

{
  "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.

string

required

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

string

required

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

string

required

string

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

string

Optional OrgX conversation-session context.

Required Scopes: initiatives:write Profiles: extended Availability: Extended profile model operation. Request:

{
  "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.

any

required

string

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

string

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

string

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

string

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

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.

string

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

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:

{
  "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.

string

required

Options: milestone.

string

required

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

string

required

string

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

string

Optional OrgX conversation-session context.

Required Scopes: initiatives:write Profiles: extended Availability: Extended profile model operation. Request:

{
  "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.

string

Optional agent ID to inspect

string

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

string

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

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:

{
  "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.

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:

{
  "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.

string

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

string

Scoped entity ID

string

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

string

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

integer

Maximum recommendations

string

Optional OrgX conversation-session context.

Required Scopes: initiatives:read Profiles: v2, extended, chatgpt, read-only Availability: Default ChatGPT and v2 model operation. Request:

{
  "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.

string

Options: decision, run, command.

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:

{
  "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.

string

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

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:

{
  "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.

string

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

string

Required Scopes: initiatives:read Profiles: v2, legacy, extended, chatgpt, memory, commander, planner, executor, observer Availability: Default ChatGPT and v2 model operation. Request:

{
  "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.

string

required

Existing task UUID.

string

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

string

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

string

required

Specialist domain receiving the task.

string

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

string

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

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.

string

number

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

string

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

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.

string[]

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

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.

object[]

string

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

string

Optional OrgX conversation-session context.

Required Scopes: agents:write, initiatives:write Profiles: v2, extended, chatgpt Availability: Default ChatGPT and v2 model operation. Request:

{
  "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.

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.

string

required

Entity UUID or accepted short ID prefix

boolean

Include linked context where available; default true

integer

Approximate maximum hydrated context characters

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:

{
  "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.

string

required

Existing initiative UUID to launch.

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.

string

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

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:

{
  "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.

string

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

string

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

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:

{
  "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.

string

Specific artifact ID to review. Defaults to the next in_review artifact.

string

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

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:

{
  "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.

string

required

string

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

string

Optional OrgX conversation-session context.

Required Scopes: decisions:write Profiles: extended Availability: Extended profile model operation. Request:

{
  "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.

string

required

string

required

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

string

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

string

Optional OrgX conversation-session context.

Required Scopes: decisions:write Profiles: extended Availability: Extended profile model operation. Request:

{
  "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.

string

required

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:

{
  "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.

string

required

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

string

required

UUID of the node

Required Scopes: agents:write, initiatives:write Profiles: v2, extended, chatgpt Availability: Default ChatGPT and v2 model operation. Request:

{
  "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.

string

Plan session UUID or orgx://plan_session/<uuid> URI.

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:

{
  "tool": "orgx_read_plan",
  "args": {}
}

orgx_reassign_streams_work

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

string

required

Options: initiative.

string

required

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

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.

string

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

string

Optional OrgX conversation-session context.

Required Scopes: initiatives:write Profiles: extended Availability: Extended profile model operation. Request:

{
  "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.

string

required

Plan session UUID or orgx://plan_session/<uuid> URI.

string

required

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:

{
  "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.

string

required

Options: task.

string

required

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

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.

string

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

string

Optional OrgX conversation-session context.

Required Scopes: initiatives:write Profiles: extended Availability: Extended profile model operation. Request:

{
  "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.

string

required

Completed work_artifacts UUID to evaluate

Required Scopes: initiatives:write Profiles: v2, extended, chatgpt Availability: Default ChatGPT and v2 model operation. Request:

{
  "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.

string

required

Plan session UUID or orgx://plan_session/<uuid> URI.

string

required

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:

{
  "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.

string

required

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

string

required

UUID of the node

Required Scopes: agents:write, initiatives:write Profiles: v2, extended, chatgpt Availability: Default ChatGPT and v2 model operation. Request:

{
  "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.

string

required

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

string

required

UUID of the node

Required Scopes: agents:write, initiatives:write Profiles: v2, extended, chatgpt Availability: Default ChatGPT and v2 model operation. Request:

{
  "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.

string

required

Plan session UUID or orgx://plan_session/<uuid> URI.

string

required

string

Display title for the new work record.

string

integer

required

Authoritative plan_ref.version from the most recent read. Required to prevent overwriting another edit.

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:

{
  "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.

string

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

string

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

string

Search query for memory or title/text matching

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.

string

Optional status filter

string

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

string

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

integer

Maximum records to return

integer

Typed-search pagination offset. Prefer cursor when next_call returns one.

string

Opaque typed-search cursor returned by pagination.next_cursor or next_call.

string[]

Optional compact field list

string

Optional OrgX conversation-session context.

{
  "tool": "orgx_search",
  "args": {}
}

orgx_ship_batch_work

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

string

required

Options: milestone.

string

required

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

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.

string

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

string

Optional OrgX conversation-session context.

object

required

string[]

number

Required Scopes: initiatives:write Profiles: extended Availability: Extended profile model operation. Request:

{
  "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.

string

required

Existing task UUID to dispatch.

string

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

string

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

string

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

string

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

string

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

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.

string

number

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

string

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

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.

string[]

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

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.

object[]

string

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

string

Optional OrgX conversation-session context.

Required Scopes: agents:write Profiles: v2, extended, chatgpt Availability: Default ChatGPT and v2 model operation. Request:

{
  "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.

string

required

Display title for the new work record.

string

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

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:

{
  "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.

string

required

Options: milestone, workstream, task.

string

required

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

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.

string

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

string

Optional OrgX conversation-session context.

Required Scopes: initiatives:write Profiles: extended Availability: Extended profile model operation. Request:

{
  "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.

string

required

Options: task.

string

required

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

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.

string

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

string

Optional OrgX conversation-session context.

Required Scopes: initiatives:write Profiles: extended Availability: Extended profile model operation. Request:

{
  "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.

string

required

Options: initiative, workstream, milestone, task.

string

required

object

required

string

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

any

Required Scopes: initiatives:write Profiles: v2, extended, chatgpt Availability: Default ChatGPT and v2 model operation. Request:

{
  "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.

string

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

object

required

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

object

Required Scopes: initiatives:read Profiles: v2, extended, chatgpt Availability: Default ChatGPT and v2 model operation. Request:

{
  "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.

string

required

object

required

string

Required Scopes: initiatives:write Profiles: extended Availability: Extended profile model operation. Request:

{
  "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.

string

Workspace UUID. Defaults to the authenticated workspace.

string

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

integer

Default: 25.

Required Scopes: initiatives:read Profiles: v2, extended, chatgpt Availability: Default ChatGPT and v2 model operation. Request:

{
  "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.

string

Workspace UUID. Defaults to the authenticated workspace.

string

required

Required Scopes: initiatives:read Profiles: v2, legacy, extended, chatgpt Availability: Default ChatGPT and v2 model operation. Request:

{
  "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.

string

Workspace UUID. Defaults to the authenticated workspace.

string

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

string

Default: "".

string

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

integer

Default: 25.

Required Scopes: initiatives:read Profiles: v2, legacy, extended, chatgpt Availability: Default ChatGPT and v2 model operation. Request:

{
  "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.

string

Workspace UUID. Defaults to the authenticated workspace.

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.

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:

{
  "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.

object

required

Authentication: Account-free Profiles: v2, extended, chatgpt Availability: Default ChatGPT and v2 model operation. Request:

{
  "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>"
          }
      }
  }
}

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.

string

required

string

required

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

integer

string

Required Scopes: initiatives:write Profiles: v2, legacy, extended, chatgpt Availability: Human widget callback; unavailable to the model. Request:

{
  "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.

string

required

string

required

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

integer

string

required

Required Scopes: initiatives:write Profiles: v2, legacy, extended, chatgpt Availability: Human widget callback; unavailable to the model. Request:

{
  "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.

string

required

Required Scopes: initiatives:read Profiles: v2, legacy, extended, chatgpt Availability: Human widget callback; unavailable to the model. Request:

{
  "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.

string

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

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.

string

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

string

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

number

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

string

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

string

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

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:

{
  "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.

string

required

Target agent identifier or alias

string

required

Task instructions for the target agent

string

Optional supporting context or background for the task

string

Optional initiative UUID to associate with the spawned task

string

Optional initiative title to resolve automatically if ID is unknown

string

Optional voice, format, or style constraints

string

number

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

string

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

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.

string[]

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

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.

object[]

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:

{
  "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.

string

required

Search query for organizational memory

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.

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:

{
  "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.

string

Optional initiative UUID to check

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:

{
  "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.

string

required

Decision ID to approve

string

Optional note recorded with the approval

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:

{
  "tool": "approve_decision",
  "args": {
      "decision_id": "<decision_id>"
  }
}

Response:

{
  "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.

string

required

Topic or theme to search decision history for

string

Optional initiative UUID to scope decision history

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:

{
  "tool": "get_decision_history",
  "args": {
      "topic": "<topic>"
  }
}

Response:

{
  "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.

number

Maximum number of decisions to return

string

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

string

Optional initiative UUID to scope pending decisions

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:

{
  "tool": "get_pending_decisions",
  "args": {}
}

Response:

{
  "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.

object

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

string

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

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:

{
  "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.

string

required

The Work Ledger receipt the call is about.

string

required

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

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:

{
  "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.

string

required

Decision ID to reject

string

required

Reason for rejecting the decision

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:

{
  "tool": "reject_decision",
  "args": {
      "decision_id": "<decision_id>",
      "reason": "<reason>"
  }
}

Response:

{
  "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.

string

Optional agent ID to inspect

string

Optional workspace UUID to scope agent status

string

Deprecated alias for workspace_id

string

Optional initiative UUID to scope agent status

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:

{
  "tool": "get_agent_status",
  "args": {}
}

Response:

{
  "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.

string

required

Task UUID to hand off

string

required

Target agent (e.g., “engineering-agent”, “marketing-agent”)

string

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

string

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

boolean

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

string

number

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

string

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

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.

string[]

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

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.

object[]

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:

{
  "tool": "handoff_task",
  "args": {
      "task_id": "<task_id>",
      "agent": "<agent_id>"
  }
}

Response:

{
  "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.

string

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

string

Entity ID. For workspace, use “default” or a workspace ID.

string

Shortcut for entity_type=“initiative” with entity_id=<this id>. Ignored when entity_type or entity_id is set.

string

Optional workspace ID to scope recommendations (canonical).

string

Deprecated alias for workspace_id.

string

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

string

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

boolean

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

number

Max recommendations to return (default 5, max 25)

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:

{
  "tool": "recommend_next_action",
  "args": {}
}

Response:

{
  "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.

string

required

Target agent identifier or alias

string

required

Task instructions for the target agent

string

Optional supporting context or background for the task

string

Optional initiative UUID to associate with the spawned task

string

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

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.

string

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

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.

string

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

boolean

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

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.

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.

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.

string

number

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

string

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

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.

string[]

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

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.

object[]

string

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

string

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

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:

{
  "tool": "spawn_agent_task",
  "args": {
      "agent": "<agent_id>",
      "task": "<task>"
  }
}

Response:

{
  "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.

string

Optional: Initiative UUID to check.

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:

{
  "tool": "get_initiative_pulse",
  "args": {}
}

Response:

{
  "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.

object[]

required

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

string

Optional owner ID applied when item owner is omitted.

string

Deprecated alias for owner_id.

boolean

Continue creating remaining entities after an error.

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:

{
  "tool": "batch_create_entities",
  "args": {
      "entities": [
          {}
      ]
  }
}

Response:

{
  "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.

object[]

required

Entities to delete.

number

Parallel deletion concurrency.

boolean

Continue deleting remaining entities after an error.

string

Optional reason note.

{
  "tool": "batch_delete_entities",
  "args": {
      "entities": [
          {
              "type": "workspace",
              "id": "<id>"
          }
      ]
  }
}

Response:

{
  "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.

string

required

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

string

required

Entity ID to attach the comment to.

string

required

Comment body in plain text or markdown.

string

Optional parent comment ID when replying in-thread.

string

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

string

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

string[]

Optional tags.

object

Optional structured metadata.

{
  "tool": "comment_on_entity",
  "args": {
      "entity_type": "initiative",
      "entity_id": "<entity_id>",
      "body": "<message_body>"
  }
}

Response:

{
  "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.

string

required

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

string

required

Entity ID whose comment thread should be returned.

number

Maximum comments to return.

{
  "tool": "list_entity_comments",
  "args": {
      "entity_type": "initiative",
      "entity_id": "<entity_id>"
  }
}

Response:

{
  "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.

string

required

Initiative title.

string

Initiative summary.

string

Initiative description.

string

Workspace UUID; required unless session context provides one.

string[]

Preferred objective UUIDs.

string[]

Objective UUID alias for API compatibility.

string

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

string

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

object[]

Nested workstream hierarchy.

string

Stable retry key.

string

Deprecated alias for workspace_id.

object[]

Context attachment pointers.

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.

object

Most important cross-workstream dependency.

string

Owner user ID.

string

Deprecated alias for owner_id.

boolean

Continue remaining creates after an error.

boolean

Legacy mode alias.

object

Optional work-tracker mirror configuration.

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:

{
  "tool": "scaffold_initiative",
  "args": {
      "title": "<title>"
  }
}

Response:

{
  "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.

string

required

Entity type to update.

string

required

Entity ID to update.

object

Fields to patch.

string

Optional title patch.

string

Optional name patch.

string

Optional description patch.

string

Optional status patch.

{
  "tool": "update_entity",
  "args": {
      "type": "<type>",
      "id": "<id>"
  }
}

Response:

{
  "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.

string

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

string

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

string[]

Detailed mode sections to include.

number

Maximum initiatives to return.

string

Pagination cursor from a previous response.

{
  "tool": "get_org_snapshot",
  "args": {}
}

Response:

{
  "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.

string

required

Plan session ID

string

Summary of what was built

string[]

List of files modified

object[]

Any deviations from the plan

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:

{
  "tool": "complete_plan",
  "args": {
      "session_id": "<session_id>"
  }
}

Response:

{
  "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:

{
  "tool": "get_active_sessions",
  "args": {}
}

Response:

{
  "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).

string

required

Plan session ID

string

required

Current plan content to analyze

{
  "tool": "improve_plan",
  "args": {
      "session_id": "<session_id>",
      "plan_content": "<plan_content>"
  }
}

Response:

{
  "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.

string

required

Plan session ID

string

required

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

string

Content before edit

string

required

Content after edit

string

Section path like ”## API Design”

string

Why this edit was made

{
  "tool": "record_plan_edit",
  "args": {
      "session_id": "<session_id>",
      "edit_type": "add_section",
      "after_content": "<after_content>"
  }
}

Response:

{
  "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).

string

required

Name of the feature being planned

string

Initial plan content if any

string

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

{
  "tool": "start_plan_session",
  "args": {
      "feature_name": "<feature_name>"
  }
}

Response:

{
  "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.

string

required

Initiative UUID to gather signals for

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:

{
  "tool": "get_scoring_signals",
  "args": {
      "initiative_id": "<initiative_id>"
  }
}

Response:

{
  "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.

string

required

The initiative ID

{
  "tool": "get_initiative_stream_state",
  "args": {
      "initiative_id": "<initiative_id>"
  }
}

Response:

{
  "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.

string

required

The stream ID to update

number

Progress percentage (0-100)

number

Confidence level (0-1) - separate from progress

string

Brief note about current status

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:

{
  "tool": "update_stream_progress",
  "args": {
      "stream_id": "<stream_id>"
  }
}

Response:

{
  "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.

string

required

Agent domain: engineering, marketing, product, design, ops, sales, orchestration

string

OrgX task ID this spawn is for

string

Task title (for model routing if task_id not provided)

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:

{
  "tool": "check_spawn_guard",
  "args": {
      "domain": "<domain>"
  }
}

Response:

{
  "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.

string

required

Task title

string

Task description

string

Entity type: task, decision, initiative

string

Agent domain

string

Optional tier to estimate. Omit to let OrgX auto-route. Options: standard, balanced, precision, local, sonnet, opus.

string

Optional provider preference for the estimate. Use auto unless explicitly selected. Options: auto, openai, anthropic, openrouter, groq, local.

string

Optional budget posture for the estimate. Use cheapest_valid for controlled validation runs only. Options: cheapest_valid, balanced, highest_quality.

number

Optional per-task hard cost ceiling to compare against the estimate.

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:

{
  "tool": "classify_task_model",
  "args": {
      "title": "<title>"
  }
}

Response:

{
  "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.

string

required

GitHub pull request URL, e.g. https://github.com/org/repo/pull/123. OrgX must have server-side GitHub credentials to inspect it.

string

OrgX workspace UUID

string

Initiative to attach the consolidation_pass artifact to

string

Task to attach the consolidation_pass artifact to

string

Decision to attach the consolidation_pass artifact to

string

Override commit SHA for idempotency; defaults to merge commit or PR head SHA

string

Optional verdict override; defaults from PR state Options: ship, simplify_first, escalate.

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:

{
  "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.

string

required

Initiative UUID

string

required

Idempotency key for safe retries

object[]

required

Ordered task, milestone, and decision mutations to apply atomically

string

Existing run UUID

string

Required when run_id is not provided

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.

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:

{
  "tool": "orgx_apply_changeset",
  "args": {
      "initiative_id": "<initiative_id>",
      "idempotency_key": "<idempotency_key>",
      "operations": [
          {
              "op": "task.create",
              "title": "<title>"
          }
      ]
  }
}

Response:

{
  "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.

string

required

Initiative UUID

string

required

Human-readable activity update

string

Existing run UUID

string

Required when run_id is not provided

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.

string

Optional reporting phase for the activity event Options: intent, execution, blocked, review, handoff, completed.

number

Optional progress percentage associated with this activity

string

Optional severity level for the activity event Options: info, warn, error.

string

Optional next step to surface after this activity event

object

Optional structured metadata to attach to the activity event

object

Runtime provenance used by /live to bucket cloud, local, Anthropic, managed, and OpenClaw chokepoints

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:

{
  "tool": "orgx_emit_activity",
  "args": {
      "initiative_id": "<initiative_id>",
      "message": "<message>"
  }
}

Response:

{
  "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.

string

required

claim paths, list live leases, or release one Options: claim, list, release.

string

Repository as owner/name, e.g. hopeatina/orgx. Required for claim and list.

string[]

Repo-relative files or globs you are about to edit. Required for claim.

integer

How long to hold the lease; default 60.

string

The lease to release. Required for release.

string

OrgX task the edit belongs to, if any.

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:

{
  "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.

string

OrgX task ID (snake_case alias; taskId also accepted)

string

OrgX task ID (backend/camelCase alias)

string

Agent domain that completed the task (agentDomain/domain also accepted)

string

Agent domain that completed the task (backend/camelCase alias)

string

Short alias for agentDomain

number

required

Quality score: 1=poor, 3=acceptable, 5=excellent

string

Who scored this (snake_case alias; scoredBy also accepted) Options: human, auto, peer.

string

Who scored this (backend/camelCase alias) Options: human, auto, peer.

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:

{
  "tool": "record_quality_score",
  "args": {
      "score": 1
  }
}

Response:

{
  "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.

string

Specific artifact ID to review. Defaults to the next in_review artifact.

string

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

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:

{
  "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.

string

Local MEMORY.md content to push

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:

{
  "tool": "sync_client_state",
  "args": {}
}

Response:

{
  "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.

string

required

list=show all, get=current, set=switch active, create=new workspace Options: list, get, set, create.

string

Workspace UUID to switch to (action=set only)

string

Workspace name (action=create)

string

Alias for name (action=create)

string

Workspace narrative/description (action=create)

string

Short workspace tagline (action=create)

string

Workspace identity narrative (action=create)

string[]

Workspace identity metrics (action=create)

string

Roadmap URL (action=create)

string[]

Source links for workspace identity (action=create)

boolean

Whether to make the new workspace active. Defaults true.

{
  "tool": "workspace",
  "args": {
      "action": "list"
  }
}

Response:

{
  "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.

string

required

Configuration operation Options: status, configure_agent, set_policy.

string

Agent type (configure_agent only) Options: product, engineering, marketing, sales, operations, design, orchestrator.

string

Agent autonomy level (configure_agent only) Options: strict, balanced, autonomous.

string[]

Agent focus areas (configure_agent only)

string[]

Actions requiring approval (configure_agent only)

string[]

Actions without approval (configure_agent only)

string

Policy type (set_policy only) Options: approvals, notifications, working_hours, budget, artifact_collection.

object

Policy configuration (set_policy only)

string

Workspace UUID to scope policy overrides (set_policy only)

string

Deprecated alias for workspace_id (set_policy only)

{
  "tool": "configure_org",
  "args": {
      "action": "status"
  }
}

Response:

{
  "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.

string

personal=your stats, session=current session diagnostics Options: personal, session. Default: "personal".

string

Time period for stats (personal only) Options: today, week, month, all_time.

{
  "tool": "stats",
  "args": {}
}

Response:

{
  "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.

string

required

Workspace ID

string

Specific session ID (defaults to most recent)

{
  "tool": "get_morning_brief",
  "args": {
      "workspace_id": "<workspace_id>"
  }
}

Response:

{
  "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.

string

required

Workspace ID

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:

{
  "tool": "get_my_trust_context",
  "args": {
      "workspace_id": "<workspace_id>",
      "agent_type": "<agent_type>"
  }
}

Response:

{
  "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.

string

required

Workspace ID

string

Capability key to filter learnings

string[]

Keywords for semantic matching

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:

{
  "tool": "get_relevant_learnings",
  "args": {
      "workspace_id": "<workspace_id>"
  }
}

Response:

{
  "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.

string

Workspace ID

string

CamelCase alias for workspace_id

string

Outcome type key: deal_closed, meeting_booked, etc.

string

CamelCase alias for outcome_type_key

number

Value in the outcome type unit (e.g., USD amount)

number

CamelCase alias for outcome_value

string

Source that observed or reported the outcome Options: manual, agent_self_report, crm_webhook, linear_sync. Default: "manual".

string

External source ID for deduplication

string

CamelCase alias for source_id

string

ISO datetime when the outcome occurred

string

CamelCase alias for occurred_at

object

Additional context

{
  "tool": "record_outcome",
  "args": {}
}

Response:

{
  "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.

string

required

Workspace ID.

string

Autonomy session mode to start. Options: overnight, weekend, scheduled, manual. Default: "manual".

number

Maximum budget in USD before the session stops. Default: 10.

integer

Maximum number of receipts the session may produce. Default: 100.

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:

{
  "tool": "start_autonomous_session",
  "args": {
      "workspace_id": "<workspace_id>"
  }
}

Response:

{
  "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.

string

required

Workspace ID

string

required

Type of learning Options: failure_pattern, success_pattern, cost_optimization, quality_heuristic.

string

required

Human-readable learning summary

string

Applicable capability key

string[]

Receipt IDs that support this learning

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:

{
  "tool": "submit_learning",
  "args": {
      "workspace_id": "<workspace_id>",
      "learning_type": "failure_pattern",
      "summary": "<summary>"
  }
}

Response:

{
  "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:

{
  "tool": "account_status",
  "args": {}
}

Response:

{
  "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.

string

Target account plan. Defaults to pro. Options: pro, enterprise.

string

Billing cadence for self-serve checkout. Options: monthly, annual.

string

Optional agent credit pack to buy instead of upgrading a plan. Options: credits_500, credits_2000.

{
  "tool": "account_upgrade",
  "args": {}
}

Response:

{
  "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:

{
  "tool": "account_usage_report",
  "args": {}
}

Response:

{
  "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

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.

string

required

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

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.

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.

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.

boolean

Preview update/delete or supported lifecycle actions without mutating. For action=update this returns would_update and must not delegate to orgx_write.

boolean

Force action where server supports override semantics (skips pre-flight checks).

object

REQUIRED when action=validate. Spec payload for studio validation (shape varies per studio entity subtype).

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.

string[]

Optional list of verification evidence URLs/IDs for completion flows.

number

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

string

Optional client-supplied retry key. Update requests transport it outside validated entity fields; lifecycle endpoints deduplicate where supported.

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:

{
  "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.

string

required

Target entity type Options: workspace, initiative, milestone, workstream, task, objective, playbook, decision, stream, studio_content.

string

required

Target entity UUID or short ID prefix

string

required

Artifact title

string

required

string

Internal artifact URL. REQUIRED unless external_url is provided; preview_markdown alone is rejected.

string

External artifact URL. REQUIRED unless artifact_url is provided; preview_markdown alone is rejected.

string

Artifact description

string

Optional markdown preview shown with the linked artifact. Does not replace artifact_url/external_url.

string

Artifact workflow status Options: draft, in_review, approved, changes_requested, superseded, archived.

object

Artifact metadata

string

Agent/domain that produced the artifact, such as engineering, sales, product, design, operations, marketing, or orchestrator. Stored under metadata.artifact_contract.

string

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

string

Human or agent owner for the next review/action. Stored under metadata.artifact_contract.

string

Date or cadence for the next review point. Stored under metadata.artifact_contract.

string[]

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

string

Strongly recommended client-generated idempotency key for safe retries

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:

{
  "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.

string

Canonical workspace UUID to bind as the active session workspace

string

Optional initiative UUID to bind and hydrate as the active work context

string

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

string

Alias for initiative_id (an initiative UUID), accepted from older callers. initiative_id wins when both are sent.

string

Deprecated alias for workspace_id. workspace_id wins when both are sent.

string

Optional client conversation/session identifier for continuity

string

Optional MCP client name, such as codex, chatgpt, cursor, or claude

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.

string

Provider of model when it cannot be read from the name (anthropic, openai, google…).

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:

{
  "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.

string

required

Workspace UUID whose controller status should be read

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:

{
  "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.

string

required

Decision operation. See top-level description for per-action required fields. Options: create, remember, list_pending, approve, reject.

string

Decision UUID. REQUIRED for action=approve or action=reject. Returned by action=list_pending or action=create.

string

Short title for the decision. REQUIRED for action=create.

string

The decision text itself (what was decided). REQUIRED for action=create and action=remember.

string

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

string

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

string

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

string

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

string

Optional initiative UUID to scope the decision. Used as filter when action=list_pending; used as parent when action=create.

string

Optional workspace UUID to scope the decision. Defaults to the MCP session’s workspace.

string

Strongly recommended client-supplied idempotency key for action=create or action=remember. Same key returns the same result without duplicating state.

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:

{
  "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.

string

required

Planning action to perform. See top-level description for per-action required fields. Options: start, resume, improve, record_edit, complete.

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.

string

Feature or plan name. REQUIRED when action=start.

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.

string

Current/final plan markdown. REQUIRED when action=improve (the draft to critique) or action=complete (the final accepted plan).

string

One-line description of the change being recorded. REQUIRED when action=record_edit.

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.

string

Workspace UUID to scope action=start plan sessions. Defaults to current session workspace when omitted.

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:

{
  "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.

string

Recommendation mode; default next_action Options: next_action, morning_brief.

string

Reporting period for mode=morning_brief; default 30d Options: day, week, 30d.

string

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

string

Scoped entity ID

string

Shortcut for entity_type=“initiative” with entity_id=<this id>. Ignored when entity_type or entity_id is set.

string

Workspace UUID

integer

Maximum recommendations

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:

{
  "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.

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.

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.

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.

string

Optional initiative UUID to scope the spawned task. Inferred from task_id when omitted.

string

Optional workspace UUID to scope the spawned task. Defaults to the MCP session’s workspace.

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.

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.

string

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

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.

string

number

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

string

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

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.

string[]

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

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.

object[]

string

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

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:

{
  "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.

string

Workspace UUID. Defaults to the MCP session’s workspace when omitted.

string

Related entity type (initiative, workstream, milestone, task, decision). Required if no artifact_id is provided — pair with entity_id.

string

Related entity UUID. Required when entity_type is provided.

string

required

Receipt category key. Recognized values: “proof”, “outcome”, “quality”, “attribution”, “learning”. Custom domain-specific keys are also accepted.

string

required

One-sentence human-readable description of what the receipt proves (e.g. “Merged PR #142 unblocking the auth refactor”).

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.

string

Related artifact UUID to anchor the receipt to. Alternative to entity_type+entity_id when the proof lives in OrgX as an artifact.

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.

string

Agent/domain that produced the receipt, such as engineering, sales, product, design, operations, marketing, or orchestrator.

string

Business outcome advanced by the receipt.

string

Whether the artifact verification passed, failed, was blocked, or was not run. Options: passed, failed, blocked, not_run.

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.

boolean

Set true when this receipt should be evaluated against the OrgX loop reliability validation ladder.

string

Model tier used for the run being receipted. For validation rungs before calibrated expansion, use standard. Options: standard, balanced, precision, local, sonnet, opus.

string

Budget posture used for the run being receipted. For validation rungs before calibrated expansion, use cheapest_valid. Options: cheapest_valid, balanced, highest_quality.

number

Per-task or canary spend cap used during the validation run, when known.

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.

string

Provider of model when it cannot be read from the name (anthropic, openai, google…).

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.

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.

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.

string

Strongly recommended client-supplied idempotency key. Submitting the same key twice will not create a duplicate receipt.

string

Optional bootstrap/session identifier returned by orgx_bootstrap.

{
  "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.

string

Write operation. Defaults to “create”. Set “update” (with id + fields) to patch an existing entity. Options: create, update.

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.

string

REQUIRED when operation=“update”. Target entity UUID to patch.

string

REQUIRED on create (provide either “title” or “name” — they are aliases). Display title of the new entity.

string

Alternative to “title” on create. REQUIRED on create when “title” is not provided.

string

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

string

Longer-form description used in detail views.

object

REQUIRED when operation=“update”. Map of entity fields to patch (only include fields you want to change).

string

Parent initiative UUID. REQUIRED when type=“workstream”. Optional context for tasks/milestones/artifacts to associate them with an initiative.

string

Parent workstream UUID. REQUIRED when type=“milestone” or type=“task”.

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.

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).

string[]

Objective UUIDs for initiative/workstream/milestone/task creation. REQUIRED when the workspace enforces a primary objective. Resolve via orgx_inspect type=objective.

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.

string

Initial workflow status; common agent aliases such as “active” are normalized per entity type (“active” → “in_progress”).

string

REQUIRED when type=“artifact”. Entity type to attach the artifact to (initiative, workstream, milestone, task, or decision).

string

REQUIRED when type=“artifact” (unless task_id is provided). UUID of the entity to attach the artifact to.

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.

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.

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.

string

External artifact URL (https://). Either artifact_url or external_url is required when type=“artifact”; preview_markdown alone is not accepted.

string

Optional inline markdown preview shown with the linked artifact. Supporting context only; it does not replace artifact_url/external_url.

string

REQUIRED when type=“blocker”. Agent run UUID the blocker applies to.

string

Optional agent run step UUID for blocker creation.

string

Blocker category/type when type=“blocker” (e.g. “missing_input”, “permission”, “external_dependency”).

string

Blocker resolution text when known. Used to mark a blocker as resolved.

string

Initiative live-link visibility. Only applies when type=“initiative”. Options: private, public.

boolean

Shortcut to publish an initiative live link (sets live_visibility=“public”). Only applies when type=“initiative”.

boolean

When true, public live-link visitors see the initiative title. Only applies when type=“initiative” with live_visibility=“public”.

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 }).

string

Workspace tagline when type=“workspace”.

string

Workspace identity narrative when type=“workspace”.

string[]

Workspace identity metrics when type=“workspace”.

string

Workspace roadmap URL when type=“workspace”.

string[]

Workspace source links when type=“workspace”.

boolean

For workspace create, make the new workspace active. Defaults true.

string

Client-generated retry key. Creates deduplicate by key; updates transport the key outside validated entity fields.

string

Optional bootstrap/session identifier returned by orgx_bootstrap.

{
  "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.

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:

{
  "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.

string

Workspace ID

string

CamelCase alias for workspace_id

string

required

Outcome type key, normalized server-side to snake_case

string

Human-facing outcome type label

string

CamelCase alias for display_name

string

Measurement unit for this outcome type Options: usd, hours, count, percent. Default: "count".

string

How the value should be interpreted by ROI/proof loops Options: revenue, time_saved, risk_reduced, quality_improved. Default: "quality_improved".

string

CamelCase alias for value_semantics Options: revenue, time_saved, risk_reduced, quality_improved.

{
  "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.

string

Workspace UUID to scope the chronicle.

string

Deprecated alias for workspace_id.

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:

{
  "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.

string

required

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

string

required

UUID of the node

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:

{
  "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.

string

required

Attention/decision UUID

string

required

Native continuation state proven by this receipt Options: answer_received, resuming, resumed, resume_failed, cancelled.

string

required

Stable key for retrying the same receipt

string

Native session handle that processed the answer

string

Client event proving the continuation transition

string

Actionable continuation result or failure detail

string

ISO timestamp when this state was observed

object

Additional non-secret receipt metadata

{
  "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.

string

required

Entity type whose workflow state should change. Options: initiative, workstream, milestone, task, objective, playbook.

string

required

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

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.

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.

string

Optional client-supplied retry key. Update requests transport it outside validated entity fields; lifecycle endpoints deduplicate where supported.

string

Optional OrgX session identifier.

{
  "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.

string

required

Task classification or route and cost estimate. Options: classify, estimate.

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.

string

Optional initiative UUID to scope the spawned task. Inferred from task_id when omitted.

string

Optional workspace UUID to scope the spawned task. Defaults to the MCP session’s workspace.

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.

string

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

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.

string

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

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:

{
  "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.

string

required

What the id refers to Options: decision, run, command.

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:

{
  "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.

string

required

Work entity type to complete with proof. Options: task, milestone, workstream, initiative.

string

required

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

object

required

Proof artifact with artifact_type and artifact_url or external_url; optional name, description, and preview_markdown.

string[]

Optional list of verification evidence URLs/IDs for completion flows.

number

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

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.

string

Optional client-supplied retry key. Update requests transport it outside validated entity fields; lifecycle endpoints deduplicate where supported.

string

Optional OrgX session identifier.

{
  "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.

string

required

Work record type to create. Options: workspace, initiative, workstream, milestone, task, objective, skill, blocker.

string

REQUIRED on create (provide either “title” or “name” — they are aliases). Display title of the new entity.

string

Alternative to “title” on create. REQUIRED on create when “title” is not provided.

string

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

string

Longer-form description used in detail views.

string

Parent initiative UUID. REQUIRED when type=“workstream”. Optional context for tasks/milestones/artifacts to associate them with an initiative.

string

Parent workstream UUID. REQUIRED when type=“milestone” or type=“task”.

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.

string

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

string[]

Objective UUIDs. Required when the workspace enforces a primary objective.

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.

string

REQUIRED when type=“blocker”. Agent run UUID the blocker applies to.

string

Optional agent run step UUID for blocker creation.

string

Blocker category/type when type=“blocker” (e.g. “missing_input”, “permission”, “external_dependency”).

string

Initiative live-link visibility. Only applies when type=“initiative”. Options: private, public.

boolean

Shortcut to publish an initiative live link (sets live_visibility=“public”). Only applies when type=“initiative”.

boolean

When true, public live-link visitors see the initiative title. Only applies when type=“initiative” with live_visibility=“public”.

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 }).

string

Workspace tagline when type=“workspace”.

string

Workspace identity narrative when type=“workspace”.

string[]

Workspace identity metrics when type=“workspace”.

string

Workspace roadmap URL when type=“workspace”.

string[]

Workspace source links when type=“workspace”.

boolean

For workspace create, make the new workspace active. Defaults true.

string

Client-generated retry key. Creates deduplicate by key; updates transport the key outside validated entity fields.

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:

{
  "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.

string

Dispatch new agent work or hand off an existing task. Options: spawn, handoff. Default: "spawn".

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.

string

Optional initiative UUID to scope the spawned task. Inferred from task_id when omitted.

string

Optional workspace UUID to scope the spawned task. Defaults to the MCP session’s workspace.

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.

string

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

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.

string

number

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

string

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

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.

string[]

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

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.

object[]

string

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

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:

{
  "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.

string

required

Initiative UUID

string

Existing run UUID

string

Required when run_id is not provided

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.

object

Runtime provenance used by /live to bucket chokepoints

string

Optional human-readable rollup of the graph state

object[]

Execution graph nodes; each carries claimed status + optional verification

object[]

Raw OTel-compatible events to semantically promote. Only explicitly material native/observed facts become graph nodes; prompts and inferred reasoning do not.

object[]

depends_on edges between node ids

object[]

Explicit trust-ledger events such as authority_exceeded that OrgX cannot infer from graph shape

object

Optional structured metadata to attach to the execution-graph emission

{
  "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.

string

metric_coverage (default) registers the supported delayed observer; task_prediction records expected task results before acting. Options: metric_coverage, task_prediction.

string

Required for metric_coverage: exact observer registry ID.

string

Workspace UUID. Defaults to the MCP session workspace. The subject and metric scope are derived from this exact workspace.

string

Required for metric_coverage: future ISO-8601 datetime with timezone offset. Registration is rejected after this window begins.

string

Required for metric_coverage: ISO-8601 datetime with timezone offset, after window_starts_at and no more than 31 days later.

number

Required receipt coverage ratio. Defaults to 0.95. The predicate is fixed to greater-than-or-equal.

integer

Minimum terminal-run denominator required for a conclusive result. Defaults to 20.

integer

Maximum seconds from terminal session end to durable automatic receipt. Defaults to 60.

integer

Retry cadence when the observer is unavailable. Defaults to 300 seconds.

string

Required for task_prediction: task UUID. The task must be ready to start.

string

Required for task_prediction: UUID of the current agreed expectation set that applies to this task.

integer

Required for task_prediction: exact persisted version of that agreed expectation set.

string

Required for task_prediction: expected task outcome, stated before acting.

number

Required for task_prediction: confidence in the expected outcome, from 0 to 1.

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.

string

Required for task_prediction. Sent as Idempotency-Key; reuse the same key when retrying. Generated when omitted for metric_coverage.

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:

{
  "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.

string

required

Workspace ID to audit

string

Agent type to benchmark trust against Default: "orchestrator".

string

ROI attribution period used for ROI Visibility Options: 7d, 30d, 90d. Default: "30d".

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:

{
  "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.

string

required

Plan session UUID or orgx://plan_session/<uuid> URI.

string

required

Current markdown plan draft to improve.

string

Optional idempotency key for safe retries. Same key returns the same result without creating duplicate session state.

{
  "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.

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:

{
  "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.

string

required

Question/decision UUID returned by orgx_request_question

{
  "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.

string

Create a named decision or remember decision text. Options: create, remember. Default: "create".

string

Short title for the decision. REQUIRED for action=create.

string

required

Decision text to record.

string

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

string

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

string

Optional initiative UUID to scope the decision. Used as filter when action=list_pending; used as parent when action=create.

string

Optional workspace UUID to scope the decision. Defaults to the MCP session’s workspace.

string

Strongly recommended client-supplied idempotency key for action=create or action=remember. Same key returns the same result without duplicating state.

string

Optional OrgX session identifier.

{
  "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.

string

required

Initiative UUID

string

required

Why human attention is required Options: question, permission, approval, recovery.

string

required

Stable key for safe retries of this request

string

required

The concrete request the owner must answer

string

What led here, what is preserved, and what the answer changes

string

What remains paused or at risk until the owner responds

object[]

Pre-allocated valid responses

string

Answer control; inferred from options when omitted Options: single_select, multi_select, free_text, confirmation.

string

Recommended option when the agent can justify one

string

Concise recommendation and why it is safest or highest leverage

boolean

Whether linked work is gated; default true

string

Owner attention urgency; default medium Options: low, medium, high, urgent.

string

Affected workstream UUID

string

Existing OrgX run UUID

string

Stable client correlation when run_id is unavailable

string

Originating native client Options: openclaw, codex, claude-code, chatgpt, cursor, copilot, gemini, opencode, cline, goose, qwen, kiro, web-ui, api.

object

Runtime and provider provenance for the preserved execution

string

Originating client session identifier

string

required

Native hook or tool that requested attention

string

Originating hook or tool-call event identifier

object

Additional non-secret source and continuation references

object

How OrgX should return the answer to the preserved client session

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:

{
  "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.

string

required

Initiative UUID

string

required

Stable key for safe retries of the same question

string

required

The concrete question the owner must answer

string

What led here, what is preserved, and what the answer changes

object[]

Pre-allocated answers for single-select or multi-select questions

string

Answer control; inferred from options when omitted Options: single_select, multi_select, free_text, confirmation.

boolean

Whether this answer gates the linked work; default true

string

Owner attention urgency; default medium Options: low, medium, high, urgent.

string

Affected workstream UUID

string

Existing run UUID

string

Required with source_client when run_id is absent

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.

object

Runtime/provider provenance for the paused execution

string

Claude, Codex, Cursor, or other client session identifier

string

required

Originating tool, e.g. AskUserQuestion or request_user_input

string

Originating question/tool-call event identifier

object

Additional non-secret client continuation references

object

Additional non-secret structured context

{
  "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.

string

required

Exact capsule_id returned by orgx_bootstrap.

integer

required

Exact as_of_global_sequence or next_after_sequence from the previous call.

string

Workspace UUID. Defaults to the MCP session workspace.

integer

Maximum material changes per page (1-100).

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:

{
  "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.

string

required

Work record type whose content should change. Options: workspace, initiative, workstream, milestone, task, objective, skill.

string

required

Existing entity UUID.

object

required

Nonempty content patch. Workflow status, approval, ownership, and completion fields are not accepted.

string

Client-generated retry key. Creates deduplicate by key; updates transport the key outside validated entity fields.

string

Optional OrgX session identifier.

{
  "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.

string

required

Pending item being settled (decision, agent-run approval or action id)

string

The item’s widget_actions.kind. Defaults to decision. Options: decision, approval, action.

string

required

approve or reject Options: approve, reject.

string

What should change. Required when rejecting if widget_actions.reject_requires_reason, and when the chosen option requires a reason

string

Typed answer when widget_actions.answer asks for one

string

The option the person chose, when widget_actions.selection.mode is single

string[]

The options the person chose, when widget_actions.selection.mode is multiple

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:

{
  "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.

string

required

Queue operation Options: pin, unpin, skip.

string

required

Initiative UUID

string

required

Workstream UUID

string

Workspace UUID

string

Deprecated alias for workspace_id

number

Position among pinned items, 0=top (pin only)

number

Skip duration in minutes, default 60, max 10080 (skip only)

{
  "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.

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:

{
  "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.

string

required

Agent run UUID to resume.

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:

{
  "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.

string

required

get=read config, update=modify settings Options: get, update.

string

Workspace UUID

string

Deprecated alias for workspace_id

boolean

Enable/disable scoring_v2 (action=update only)

string[]

Signal names to activate (action=update only)

object

Partial weight overrides e.g. { priority: 300 } (action=update only)

{
  "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.

string

Workspace UUID. Defaults to the MCP session’s workspace when omitted.

string

required

REQUIRED. UUID of the ledger work item to complete.

string

required

REQUIRED. The task’s current updated_at as an ISO datetime with timezone offset. A mismatch returns a conflict.

integer

required

REQUIRED. The task’s current aggregate version. A mismatch returns a conflict.

string

Completion summary (max 4000 characters).

object

Free-form JSON evidence recorded on the completion event.

integer

Actual cost in cents. Defaults to 0.

string

Optional UUID of the event that caused this command.

string

Optional correlation UUID linking related commands.

string

Client-supplied retry key sent as the Idempotency-Key header. Generated when omitted; reuse the same key to retry safely.

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:

{
  "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.

string

Workspace UUID. Defaults to the MCP session’s workspace when omitted.

string

required

Work item title (max 240 characters).

string

Longer description (max 4000 characters).

string

required

REQUIRED. Parent initiative UUID.

string

required

REQUIRED. Parent workstream UUID.

string

required

REQUIRED. Parent milestone UUID.

string

Priority. Defaults to medium. Options: low, medium, high, urgent.

string

Due date as YYYY-MM-DD.

object

Free-form JSON metadata stored on the work item.

integer

Estimated cost in cents. Defaults to 0.

string

Client-supplied command UUID. Generated when omitted.

integer

Must be 0 when provided — create-work targets a brand-new aggregate. Sent as 0 by default.

string

Optional UUID of the event that caused this command.

string

Optional correlation UUID linking related commands.

string

Client-supplied retry key sent as the Idempotency-Key header. Generated when omitted; reuse the same key to retry safely.

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:

{
  "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.

string

Workspace UUID. Defaults to the MCP session’s workspace when omitted.

string

Cursor from a previous page (alias of cursor): returns the page after it.

string

Opaque cursor from meta.nextCursor of a previous page.

integer

Maximum events per page (1-100).

string

Optional event type filter. Comma-separate multiple types.

string

Optional aggregate type filter (lowercase identifier).

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:

{
  "tool": "orgx_events_tail",
  "args": {}
}

Deprecated Tools

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.

Tool Catalog Overview

Workflow Operations

orgx_activate_work

orgx_archive_work

orgx_attach_artifact

orgx_block_work

orgx_cancel_work

orgx_capture_decision

orgx_check_agent_delegation read-only

orgx_check_execution_readiness read-only

orgx_classify_agent_task read-only

orgx_complete_entity

orgx_complete_plan

orgx_complete_work_with_proof

orgx_create_and_launch_initiative_hierarchy

orgx_create_and_start_agent_task

orgx_create_decision

orgx_create_initiative

orgx_create_initiative_hierarchy

orgx_create_milestone

orgx_create_task

orgx_create_workstream

orgx_delete_work

orgx_estimate_agent_task read-only

orgx_flag_risk_work

orgx_get_agent_status

orgx_get_initiative_progress

orgx_get_next_actions

orgx_get_operation_status read-only

orgx_get_operator_brief read-only

orgx_get_workspace_context read-only

orgx_handoff_task

orgx_inspect read-only

orgx_launch_initiative

orgx_list_pending_decisions read-only

orgx_open_artifact_review read-only

orgx_open_decision_approval_review read-only

orgx_open_decision_rejection_review read-only

orgx_open_decision_review read-only

orgx_pause_work

orgx_read_plan read-only

orgx_reassign_streams_work

orgx_record_plan_edit

orgx_reopen_work

orgx_request_independent_artifact_review

orgx_request_plan_critique

orgx_resume_work

orgx_retry_work

orgx_save_plan

orgx_search

orgx_ship_batch_work

orgx_start_agent_task

orgx_start_plan

orgx_start_work

orgx_unblock_work

orgx_update_work

orgx_validate_initiative_plan read-only

orgx_validate_studio_content read-only

Portable Work Receipts

orgx_get_receipt_review_queue read-only

orgx_get_work_receipt read-only

orgx_list_work_receipts read-only

orgx_submit_work_receipt

orgx_validate_work_receipt read-only

Human Widget Operations

orgx_widget_approve_artifact

orgx_widget_request_artifact_changes

orgx_widget_select_workspace

Legacy and internal: Recommended Entry Points

approve_agent_work

delegate_agent_task

recall_memory read-only

track_project_progress read-only

Decisions

approve_decision

get_decision_history read-only

get_pending_decisions read-only

orgx_panel_snapshot read-only

orgx_widget_receipt_call

reject_decision

orgx_check_agent_delegation `read-only`

orgx_check_execution_readiness `read-only`

orgx_classify_agent_task `read-only`

orgx_estimate_agent_task `read-only`

orgx_get_operation_status `read-only`

orgx_get_operator_brief `read-only`

orgx_get_workspace_context `read-only`

orgx_inspect `read-only`

orgx_list_pending_decisions `read-only`

orgx_open_artifact_review `read-only`

orgx_open_decision_approval_review `read-only`

orgx_open_decision_rejection_review `read-only`

orgx_open_decision_review `read-only`

orgx_read_plan `read-only`

orgx_validate_initiative_plan `read-only`

orgx_validate_studio_content `read-only`

orgx_get_receipt_review_queue `read-only`

orgx_get_work_receipt `read-only`

orgx_list_work_receipts `read-only`

orgx_validate_work_receipt `read-only`

recall_memory `read-only`

track_project_progress `read-only`

get_decision_history `read-only`

get_pending_decisions `read-only`

orgx_panel_snapshot `read-only`

recommend_next_action `read-only`

get_active_sessions `read-only`

get_scoring_signals `read-only`

get_initiative_stream_state `read-only`

check_spawn_guard `read-only`

classify_task_model `read-only`

review_artifact `read-only`

stats `read-only`

get_morning_brief `read-only`

get_my_trust_context `read-only`

get_relevant_learnings `read-only`