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/modes/health.md
View on GitHub# OS Health Check (the `health` mode)
Scan across `context/events.jsonl` Event Bus stream, review `os-state.json` liveness, and compile system metrics deterministically without mutating user files.
## When to use
Carried over from the description of the former skill, so its trigger phrases and exclusions stay on record:
> Trigger with "run health check", "check os metrics", "system monitor", or when the user wants to review the Agentic OS liveness metrics across the Event Bus, locks, and memory arrays. Scans context/events.jsonl, os-state.json, and context/memory.md deterministically via kernel.py — no conversational judgment required. Migrated from the former the `health` mode agent (2026-09-05): deterministic Bash+Read diagnostic, no interview, no adversarial judgment — fits the skill archetype, not the agent archetype.
## Contents
- [Critical Constraints](#critical-constraints)
- [Quick start](#quick-start)
- [Cryptographic Verification Readiness](#cryptographic-verification-readiness)
- [Workflow](#workflow)
- [Verification](#verification)
- [References](#references)
## Critical Constraints
1. **Deterministic Diagnostic**: Do not modify user code or repo configs during health checks.
2. **Never Enroll CIBA Keys**: Check verification readiness via `--check`; never execute key enrollment scripts autonomously.
3. **Lock Hygiene**: Always release acquired monitor locks upon completion or error recovery.
## Quick start
Run a fast read-only check of the Agentic OS substrate and cryptographic readiness:
```bash
python3 ../setting-up-agentic-os/scripts/setup_ciba_identity.py --check
```
## Cryptographic Verification Readiness
Assert human cryptographic gates can verify via `ssh-keygen`, SSHSIG, and `allowed_signers`:
```bash
python3 ../setting-up-agentic-os/scripts/setup_ciba_identity.py --check
```
Exit 0 indicates trust anchors are ready, but is not proof of human presence. An agent must never run `setup_ciba_identity.py` to enroll keys.
## Workflow
1. **Emit Intent & Lock**: Emit intent event and acquire `monitor` lock via `kernel.py`:
```bash
python3 scripts/kernel.py emit_event --agent os-control-health --type intent --action scan_metrics
python3 scripts/kernel.py acquire_lock monitor
```
2. **Analyze Event Bus & State**: Inspect `context/events.jsonl`, check hook error logs, and inspect `os-state.json`.
3. **Inspect Memory & Substrate**: Review `context/memory.md` length, check `context/.locks/` for stale locks, and verify substrate components.
4. **Summarize & Release**:
```bash
python3 scripts/kernel.py emit_event --agent os-control-health --type result --action scan_metrics --status success --summary "Metrics compiled"
python3 scripts/kernel.py release_lock monitor
```
The agent's own simulation identity is part of readiness too: see the `agent-identity` and `setup-healthcheck-validation` references of `setting-up-agentic-os` (`dual_identity_status` reports human, simulation and isolation separately).
## Verification
Confirm monitor lock is released and event bus records clean result:
```bash
cat context/os-state.json
```
## References
- [detailed-reference.md](../health-detailed-reference.md) — Phase specifications and deep metric inspection patterns.
- [acceptance-criteria.md](../acceptance-criteria.md#mode-health) — Health assessment thresholds and pass/fail criteria.
- [fallback-tree.md](../fallback-tree.md#mode-health) — Remediation pathways for failed checks and leaked locks.
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: 472k | 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 |