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/architecture/context-folder-patterns.md
View on GitHub# Context Folder Patterns
The `context/` folder is the persistent RAM of the Agentic OS.
It stores identity, preferences, and memory that survive across sessions.
## Contents
- [Standard File Layout](#standard-file-layout)
- [soul.md - Identity and Values](#soulmd---identity-and-values)
- [user.md - User Preferences](#usermd---user-preferences)
- [memory.md - Long-Term Curated Facts](#memorymd---long-term-curated-facts)
- [Dated Session Logs - `memory/YYYY-MM-DD.md`](#dated-session-logs---memoryyyyy-mm-ddmd)
- [@import Strategy](#import-strategy)
## Standard File Layout
```
context/
soul.md <- Identity, values, tone, personality
user.md <- User preferences, working style, communication prefs
memory.md <- Long-term facts, decisions, project conventions (you curate)
memory/
2026-03-15.md <- Session log: what happened, lessons learned, skills updated
2026-03-14.md
archive/
2026-02.md <- Archived older sessions
```
## soul.md - Identity and Values
Defines WHO the agent is. Written once, rarely updated.
```markdown
# Soul
## Identity
I am [agent name/persona]. My purpose is [mission].
## Values
- [Core principle 1]
- [Core principle 2]
## Tone
- [Communication style]
- [What I avoid]
## Strengths
- [Area of expertise]
```
**When to update**: Only when the agent's fundamental identity or purpose changes.
## user.md - User Preferences
Defines how to work WITH the specific user. Evolves over time.
```markdown
# User Preferences
## Name
[User's preferred name]
## Working Style
- Prefers [concise/detailed] responses
- Timezone: [timezone]
- [Other style notes]
## Communication
- Uses [platform] for questions
- Prefers [format] for code reviews
## Technical Context
- Primary language: [language]
- Stack: [tech stack]
- Editor: [editor]
```
**When to update**: When user expresses a preference, or you notice a consistent pattern.
## memory.md - Long-Term Curated Facts
The "permanent storage" layer. You (the human) curate this.
Only promote facts that are durable and reusable.
```markdown
# Long-Term Memory
## [YYYY-MM-DD] Architecture Decision: [Topic]
[Fact or decision in 1-3 sentences]
## [YYYY-MM-DD] Gotcha: [Short label]
[Bug, quirk, or edge case that bit us]
## [YYYY-MM-DD] Convention: [Topic]
[Team or project convention established]
```
**Size limit**: Keep under 500 lines total. Archive older entries to `memory/archive/`.
## Dated Session Logs - `memory/YYYY-MM-DD.md`
Written at the end of each significant session.
Use the `memory` mode of `improving-skills-in-lab` to create these.
```markdown
# Session Log: 2026-03-15
## Summary
Fixed the authentication bug and updated the login skill.
## Key Decisions
- Chose JWT over session cookies for stateless scaling
## Lessons Learned
- The auth middleware runs BEFORE the skill router
## Open Items
- [ ] Write unit tests for new JWT handler
```
## @import Strategy
Reference `context/` files from CLAUDE.md selectively:
```markdown
# CLAUDE.md
@import context/soul.md <- Always import: identity is always relevant
@import context/user.md <- Always import: working style is always relevant
<!-- memory.md imported on demand, not always -->
```
Do NOT always @import `memory.md` — it grows large. Load it only when you need historical context.
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 |