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/fallback-tree.md
View on GitHub# Fallback Tree: running-control-plane
Merged verbatim from the retired skills; one section per mode. Headings inside a section are one level deeper than in the original.
## Contents
- [Mode: intake](#mode-intake)
- [Mode: mode](#mode-mode)
- [Mode: health](#mode-health)
- [Mode: simulator](#mode-simulator)
## Mode: intake
1. Claude Code Native -> 2. Antigravity IDE Artifact -> 3. Socratic Fallback CLI
## Mode: mode
Start from the symptom. Every command here is safe to repeat.
| Symptom | Meaning | Do this |
|---|---|---|
| `status` exit 1, "not wired" / "script missing" while enabled | Hooks were reset or reinstalled by something else | Run `enable --yes`; it reinstalls and rewires the guards |
| `status` warns "still wired (inert)" while disabled | A guard is wired but exits 0 because of the mode | Harmless; `disable --yes` unwires it |
| `status` warns "stale" | The guard in `.git/hooks` was stamped for another install location, or differs from the installed skill's copy (typical after `apm update` or a move) | Run `enable --yes`; it reinstalls the guard and re-stamps the current script paths |
| Exit 2: "cannot enable: guard script source not found" | The installed skill is incomplete (a guard script is missing beside `control_plane_mode.py`) | Reinstall the skill (`apm install`), then retry |
| "unrecognized" for a dispatcher hook | A hand-edited hook mentions the guard in a different shape | Left untouched on purpose. The guard still exits 0 while disabled. Edit the hook by hand if you want it unwired |
| "mode file must contain 'enabled' or 'disabled'" | `context/control-plane-mode` is corrupt | Delete the file (missing means enabled) or write a valid word, then run `status` |
| Gates still blocking after `disable` | You are in a different clone, or hooks were reinstalled afterwards | Run `status` in that clone; the mode and the hooks are per clone (worktrees share the main checkout's) |
| `status` warns `.git/hooks` is missing | Not a git checkout, or a bare clone | Nothing to wire; the mode file is still written |
### Undo
Each toggle backs up the mode file and the dispatcher hooks to `context/control-plane-backup/<timestamp>/`. Re-running the opposite toggle is the normal undo; the backup is the manual one.
## Mode: health
1. Deterministic scan of events.jsonl/os-state.json/memory.md via kernel.py -> 2. If kernel.py unavailable, fall back to direct file existence + line-count checks.
## Mode: simulator
1. If the requested transition is unknown, stop and report the valid transition names.
2. If deterministic simulation fails, inspect the raw reply and identify whether the
guidance template or coordinator logic is at fault.
3. If the behavioral simulation fails, fix the specific guidance or question-handling
defect and retry the same edge.
4. After three failed attempts, stop and escalate with all attempt evidence.
5. Never replace a failed behavioral test with a structural-only pass.
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 |