richfrem/agent-plugins-skills / plugins/agent-agentic-os/.apm/skills/running-control-plane
running-control-plane
FlaggedCRITICAL INTAKE GATEWAY: use at the start of any non-trivial engineering task, feature, refactor, multi-file bugfix, work package or new idea, including requests to explore, brainstorm, build, fix or change something, before planning or code changes. Enforces read-only discovery, 1-3 structured questions with defaults, control-plane registration and the immutable four-pillar TASK_SPEC.md. Also runs the rest of the control plane: health ("run health check", "check os metrics", "system monitor", event bus, locks, memory, "is my signing identity ready" status check), transition simulation ("dry run transition", "simulate transition", "check edge X -> Y"), worktree selection, and gating on/off ("disable the control plane", "turn off the push guard", "stop gating my commits"). Not for project setup or key creation (use setting-up-agentic-os) or improving skills (use improving-skills-in-lab).
references/intake-detailed-reference.md
View on GitHub# the `intake` mode — Detailed Reference
Extracted from SKILL.md per Layer-1 procedural-core line budget (issue #551).
## Socratic Intake & Task Registration
Register the task in `context/control_plane.db`:
```bash
python3 scripts/agent_control.py init --task-id "<task-id>" --title "<title>" --runtime "<runtime>" --spec-path "docs/plans/work-tasks/<task-id>/<task-id>-spec.md"
```
## Triage Heuristics & Commands
Ask the human exactly one triage question:
> *"Is this a trivial fix (single-file/few-line, no architectural impact) or a standard task requiring the full spec/review pipeline? [Recommended: <heuristic default>]"*
- Heuristic: single file touched, description contains words like "typo", "fix wording", "one-line" → default `TRIVIAL`; anything else → default `STANDARD`.
### STANDARD Flow
```bash
python3 scripts/agent_control.py coordinate-transition --task-id "<task-id>" --to "INTERVIEW" --reason "Beginning Socratic intake"
```
During the interview, use `record_interview_question.py` to record each Q&A turn. Once concluded, compile the spec/plan using `write_plan_document.py` and coordinate:
```bash
python3 scripts/agent_control.py coordinate-transition --task-id "<task-id>" --to "DRAFT_PLAN" --reason "Draft spec and plan compiled from interview"
```
### TRIVIAL Fast-Track Flow
Fast-track straight to `DONE` via the `intake_to_done_trivial` edge (no spec file written):
```bash
python3 scripts/agent_control.py coordinate-transition --task-id "<task-id>" --to "DONE" \
--reason "TRIVIAL fast-track" --interactive \
--answers '{"triage_classification": "TRIVIAL: <one-line reason>, files=<n>, diff=<short sha or `git diff --stat` one-liner>"}'
```
If mis-triaged, use the escape hatch:
```bash
python3 scripts/agent_control.py coordinate-transition --task-id "<task-id>" --to "ESCALATED" --reason "Mis-triaged as TRIVIAL"
```
## Multi-Agent Review Stage Gate (User-Controlled)
Present the User Stage Gate:
> *"Step 3 (draft plan) is done. Do you want to trigger a multi-agent review of this plan (Step 4a — an external AI reviews it before you decide), or proceed straight to Step 5 (asking for your approval)?"*
### Path A: User Chooses Multi-Agent Review
```bash
python3 scripts/agent_control.py coordinate-transition --task-id "<task-id>" --to "MULTI_AGENT_REVIEW" --reason "User requested multi-agent review bundle"
```
Package with `bundling-context`:
- Target files: `docs/plans/work-tasks/<task-id>/<task-id>-spec.md`, `docs/plans/work-tasks/<task-id>/<task-id>-implementation-plan.md`, relevant architectural references.
- Persona template: `bundling-context`'s `plan-critique-reviewer` template or Multi-Persona Fan-Out.
- Output location: `temp/review_<task-id>/`.
- Present bundle path to user for browser review (ChatGPT, Claude Web, Grok). Ingest feedback, iterate, and transition to `AWAITING_APPROVAL`.
- See [multi-round-external-review-protocol.md](multi-round-external-review-protocol.md) for persona selection and multi-round rules.
### Path B: User Skips Multi-Agent Review
```bash
python3 scripts/agent_control.py transition --task-id "<task-id>" --to "AWAITING_APPROVAL" --reason "User opted to skip multi-agent review gate"
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |