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).
Running the control plane
Gated engineering workflow: a task is registered in context/control_plane.db, specified, approved by a human signature, built in a worktree, verified and closed. Each mode below was a separate skill; its full workflow is a reference loaded when that mode starts.
Contents
Critical constraints
- Check the mode first. Run
python3 scripts/control_plane_mode.py status. When it saysdisabled, say so, skip registration and gating, and offer to enable. - Humans sign, agents never. The three gates (APPROVED, VERIFY_EXIT, DONE) need a human
ssh-keygen -Y sign. Never record a decision, approval or review skip on the human's behalf, and never run key enrollment. - Read before acting. Read the transition guidance and the database first; say which parts were read.
- One question per turn, answered from context and the running directives ledger first. Task artifacts live in
docs/plans/work-tasks/<task-id>/. - Stop on a blocked gate. State cause and cost; no workaround commands or direct database edits.
Quick start
python3 scripts/control_plane_mode.py status # is gating on?
python3 scripts/control_plane/coordinator.py transition-guidance --task-id <task-id>
Workflow
| Mode | Use when | Run | Workflow |
|---|---|---|---|
intake | Starting any non-trivial task; resuming one | scripts/agent_control.py, scripts/control_plane/coordinator.py | intake |
mode | Enabling, disabling or checking gating | scripts/control_plane_mode.py enable | disable | status | mode |
health | Checking liveness, event bus, locks, memory, os metrics, "system monitor", or whether the signing identity is ready (status check) | scripts/kernel.py; signing check: setup_ciba_identity.py --check from setting-up-agentic-os | health |
simulator | Testing a transition, edge or its guidance without real state ("simulate", "dry run", "did I break the edge rules") | scripts/control_plane/run_transition_simulation.py | simulator |
worktree | Choosing or cleaning up a worktree for a task | scripts/capability_probe.py, scripts/worktree_manager.py | worktree |
Project setup (init) and the human signing key (signing-setup) live in the setting-up-agentic-os skill, which needs this one installed beside it.
Routing rule: the table above only routes. Before acting in a mode, read that mode's workflow file in full (the last column); open the detail references below only from inside it.
Verification
Run python3 -m pytest tests from this skill's folder. Each mode's gates are in acceptance-criteria.md; on failure follow fallback-tree.md.
References
Detail files, grouped by the mode that uses them. Read the mode workflow first.
- intake: edge-matrix • healthy-transcript • intake-detailed-reference • multi-round-external-review-protocol
- health: health-detailed-reference
- simulator: cheap-agent-transition-simulation
- worktree: worktree-reconciliation-and-multi-worktree-practices
- shared: acceptance-criteria • agentic-os-skill-map • control-plane-architecture • control-plane-rebuild-recovery • control-plane-simulation-protocol • fallback-tree • implementation-ledger-contract • architecture • context-folder-patterns • vision
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 | Unverified | 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 |