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).
evals/evals.json
View on GitHub[
{
"prompt": "run a health check on the OS",
"should_trigger": true,
"note": "from os-control-health"
},
{
"prompt": "check os metrics",
"should_trigger": true,
"note": "from os-control-health"
},
{
"prompt": "run a system monitor check on the OS",
"should_trigger": true,
"note": "from os-control-health"
},
{
"prompt": "is the event bus healthy? any stuck agents?",
"should_trigger": true,
"note": "from os-control-health"
},
{
"prompt": "clear stale locks from context/.locks",
"should_trigger": false,
"note": "from os-control-health"
},
{
"prompt": "summarize what the agentic OS ecosystem does",
"should_trigger": false,
"note": "from os-control-health"
},
{
"prompt": "set up my approval signing key",
"should_trigger": false,
"note": "belongs to setting-up-agentic-os"
},
{
"prompt": "is my signing identity ready? run the status check",
"should_trigger": false,
"note": "belongs to setting-up-agentic-os"
},
{
"prompt": "Can you initialize the Agentic OS structure in my project?",
"should_trigger": false,
"note": "belongs to setting-up-agentic-os"
},
{
"prompt": "Where do I put CLAUDE.md and what goes in the context folder?",
"should_trigger": false,
"note": "belongs to setting-up-agentic-os"
},
{
"prompt": "I want Claude to remember things between sessions. How do I set that up?",
"should_trigger": false,
"note": "belongs to setting-up-agentic-os"
},
{
"prompt": "How do I get Claude to use skills in this project?",
"should_trigger": false,
"note": "belongs to setting-up-agentic-os"
},
{
"prompt": "I want to set up an agent harness for my legacy system documentation project",
"should_trigger": false,
"note": "belongs to setting-up-agentic-os"
},
{
"prompt": "I want Claude to run scheduled tasks every night. How do I set up the loop?",
"should_trigger": false,
"note": "belongs to setting-up-agentic-os"
},
{
"prompt": "What is Claude?",
"should_trigger": false,
"note": "from os-control-init"
},
{
"prompt": "Create a new skill for me that converts markdown to Word",
"should_trigger": false,
"note": "from os-control-init"
},
{
"prompt": "What did we decide last session? Check context/memory.md",
"should_trigger": false,
"note": "from os-control-init"
},
{
"prompt": "I already have a CLAUDE.md but want to add the context folder structure and sub-agents",
"should_trigger": false,
"note": "belongs to setting-up-agentic-os"
},
{
"prompt": "set up my approval signing key and allowed_signers",
"should_trigger": false,
"note": "belongs to setting-up-agentic-os"
},
{
"prompt": "test that my ssh signing key works before I approve",
"should_trigger": false,
"note": "belongs to setting-up-agentic-os"
},
{
"prompt": "I have an idea for a new plugin subsystem, let's start the intake and spec interview.",
"should_trigger": true,
"note": "from os-control-intake"
},
{
"prompt": "Compile a 4-pillar specification contract for the new control plane feature.",
"should_trigger": true,
"note": "from os-control-intake"
},
{
"prompt": "Can we run a Socratic developer interview to clarify requirements before writing code?",
"should_trigger": true,
"note": "from os-control-intake"
},
{
"prompt": "Run pytest on the test suite to verify tests pass.",
"should_trigger": false,
"note": "from os-control-intake"
},
{
"prompt": "Fix this git merge conflict in skills-lock.json.",
"should_trigger": false,
"note": "from os-control-intake"
},
{
"prompt": "The user said no plan review is needed for this task; continue the os-control-intake pipeline to approval and handle the review-skip decision for the task.",
"should_trigger": true,
"note": "from os-control-intake"
},
{
"prompt": "disable the control plane",
"should_trigger": true,
"note": "from os-control-mode"
},
{
"prompt": "enable the control plane",
"should_trigger": true,
"note": "from os-control-mode"
},
{
"prompt": "can you turn off os-control-intake, this is just a quick fix",
"should_trigger": true,
"note": "from os-control-mode"
},
{
"prompt": "turn os-control-intake back on, I'm starting a big feature",
"should_trigger": true,
"note": "from os-control-mode"
},
{
"prompt": "stop gating my commits and pushes for now",
"should_trigger": true,
"note": "from os-control-mode"
},
{
"prompt": "turn off the push guard",
"should_trigger": true,
"note": "from os-control-mode"
},
{
"prompt": "is the control plane on?",
"should_trigger": true,
"note": "from os-control-mode"
},
{
"prompt": "control plane status",
"should_trigger": true,
"note": "from os-control-mode"
},
{
"prompt": "I want the full pipeline for this one, switch the control plane on",
"should_trigger": true,
"note": "from os-control-mode"
},
{
"prompt": "the pre-push hook keeps blocking me, can you just get past it",
"should_trigger": false,
"note": "from os-control-mode"
},
{
"prompt": "run os-control-intake for this new feature",
"should_trigger": true,
"note": "flipped: negative for os-control-mode, now a mode of running-control-plane"
},
{
"prompt": "push with --no-verify",
"should_trigger": false,
"note": "from os-control-mode"
},
{
"prompt": "clean up stale locks in the context folder",
"should_trigger": false,
"note": "from os-control-mode"
},
{
"prompt": "deploy to production",
"should_trigger": false,
"note": "from os-control-mode"
},
{
"prompt": "set up my approval key for the control plane",
"should_trigger": false,
"note": "belongs to setting-up-agentic-os"
},
{
"prompt": "create the ssh key I need to approve gate 1",
"should_trigger": false,
"note": "belongs to setting-up-agentic-os"
},
{
"prompt": "I got HUMAN_PROOF_REQUIRED, how do I set up my signing identity?",
"should_trigger": false,
"note": "belongs to setting-up-agentic-os"
},
{
"prompt": "test my signing key works before I approve",
"should_trigger": false,
"note": "belongs to setting-up-agentic-os"
},
{
"prompt": "add a second key to allowed_signers",
"should_trigger": false,
"note": "belongs to setting-up-agentic-os"
},
{
"prompt": "approve the task and move it to APPROVED",
"should_trigger": true,
"note": "flipped: negative for os-control-signing-setup, now a mode of running-control-plane"
},
{
"prompt": "log this friction to map debt",
"should_trigger": false,
"note": "from os-control-signing-setup"
},
{
"prompt": "generate an ssh key for my github account",
"should_trigger": false,
"note": "belongs to setting-up-agentic-os"
},
{
"prompt": "Simulate the INTAKE -> INTERVIEW transition to make sure it's followable and checks pass.",
"should_trigger": true,
"note": "from os-control-simulator"
},
{
"prompt": "Did I break the transition guidance or edge rules for VERIFY_EXIT -> RETROSPECTIVE?",
"should_trigger": true,
"note": "from os-control-simulator"
},
{
"prompt": "Explain how Python decorators work.",
"should_trigger": false,
"note": "from os-control-simulator"
},
{
"prompt": "Run the autoresearch loop to optimize this skill's wording.",
"should_trigger": false,
"note": "from os-control-simulator"
},
{
"prompt": "Use the confirmed native worktree capability and report activation guidance.",
"should_trigger": true,
"note": "from os-control-worktree"
},
{
"prompt": "Explain a Python list comprehension.",
"should_trigger": false,
"note": "from os-control-worktree"
},
{
"prompt": "What is the Agentic OS plugin?",
"should_trigger": false,
"note": "from plugin-level evals (generic negative)"
},
{
"prompt": "Fix the syntax error in my Python script",
"should_trigger": false,
"note": "from plugin-level evals (generic negative)"
},
{
"prompt": "Review my pull request for the auth service",
"should_trigger": false,
"note": "from plugin-level evals (generic negative)"
}
]
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 |