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/agentic-os-skill-map.md
View on GitHub# Agentic OS Skill Map
Read this before routing to, recommending, or handing off to an `agent-agentic-os` skill. The plugin
ships two skills; each is a router whose modes were separate skills before the consolidation.
Verify the skill is installed in your active runtime harness (via `apm list` or your client's installed skills directory) before relying on it.
## Contents
- [The two skills](#the-two-skills)
- [How they relate](#how-they-relate)
- [Where the old skills went](#where-the-old-skills-went)
## The two skills
| Skill | Job | Modes |
|---|---|---|
| `running-control-plane` | Run engineering tasks under signed human gates, set up and check the substrate, switch gating on or off | `intake`, `init`, `mode`, `health`, `signing-setup`, `simulator`, `worktree` |
| `improving-skills-in-lab` | Plan, run, score, log and backport experiments that improve skills and agents | `plan`, `setup`, `loop`, `score`, `log`, `backport`, `memory` |
## How they relate
`running-control-plane` stands alone: it is a general task pipeline and does not depend on the lab.
Its state is `context/control_plane.db`; its authority is the human's SSH signature at the three
gates (APPROVED, VERIFY_EXIT, DONE).
The links run one way, from the lab to the control plane:
- When the lab updates or creates a skill, it registers that work as a control-plane task
(`agent_control.py`, task type `EVOLUTION`) and logs a prior-art scan, so lab changes pass the
same gates.
- The evolution cycle (`evolution_state.py`) runs the lab's locked evaluator
(`evaluate.py --decision-only`), so a repository that uses evolution cycles needs
`improving-skills-in-lab` installed too.
- The lab calls the installed `context/kernel.py` for the event bus and locks; it does not carry a copy.
## Where the old skills went
| Old skill | Now |
|---|---|
| the `intake` mode, `-init`, `-mode`, `-health`, `-signing-setup`, `-simulator`, `-worktree` and the `init` interview | the same-named mode of `running-control-plane` (`references/<mode>/workflow.md`) |
| the `plan` mode of `improving-skills-in-lab`, `-setup`, `-loop`, `-scorer`, `-log`, `-backport`, `-memory` and the interview | `plan`, `setup`, `loop`, `score`, `log`, `backport`, `memory` modes of `improving-skills-in-lab` |
See also `two-improvement-paths` in the `improving-skills-in-lab` skill for the two ways to improve a skill.
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 |