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/architecture.md
View on GitHub# Agentic OS Architecture
The Agentic OS is not a binary - it is a directory structure and behavioral convention that turns an LLM into a persistent, self-managing entity.
## Core Components
**1. Kernel (`CLAUDE.md`)** - Root system instruction file. Defines core identity, non-negotiable standards, and delegates deeper knowledge down the directory tree.
**2. RAM & Persistence (`context/`)** - `context/memory/`: dated markdown files storing daily events parsed by `SessionStart` / `PostToolUse` hooks via `update_memory.py`. `context/memory.md`: long-term curated memory promoted from daily logs. `context/status.md`: active register with current tasks, blockers, and loop state (see `status-file-spec.md`).
**3. Standard Library (`skills/`)** - Reusable procedural modules defined in YAML+Markdown (`SKILL.md`). Define triggers and execution paths. Extend agent capabilities without bloated context.
**4. Processes (`agents/`)** - Standalone sub-agents optimized for narrow execution (e.g. the `init` interview, `Triple-Loop Retrospective`).
---
## Initialization Architecture
Init uses the Sub-Agent Orchestration pattern (the `init` interview.md`) to isolate scaffolding complexity from the primary context window.
**State Transitions:**
1. **Discovery** - Agent interviews the user to understand the project environment (Python, Node, generic).
2. **Merge vs Overwrite** - If `CLAUDE.md` exists, agent MUST use safe append strategy. Destructive overwrite of pre-existing prompt logic is strictly forbidden.
3. **Hook Wiring** - `hooks.json` mapping is mandatory. `SessionStart` and `PostToolUse` must fire `update_memory.py` to bridge stateless sessions. Init is responsible for clean wiring.
---
## Memory Architecture
The Session Memory Manager acts as the garbage collector and long-term storage controller.
**Memory Tiers:**
- **L1 (Cache)** - Current active context window. Highly transient.
- **L2 (Daily Logs)** - `context/memory/YYYY-MM-DD.md`. Populated asynchronously by `hooks/update_memory.py` on file-write events. Semi-transient.
- **L3 (Permanent Record)** - `context/memory.md`. Curated facts. Permanent.
**Conflict Resolution (Dementia Guard):** No blind appends to L3. If a promoted fact contradicts an existing fact in `memory.md`, the agent will experience conflicting rules. Architecture mandates a `Read` scan of L3 before appending, pausing for user intervention if a conflict is detected.
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 |