os-guidelisted

Trigger with "explain agentic os", "how do I set up a persistent agent environment", "what is the CLAUDE.md hierarchy", "explain the context folder structure", "how does session memory work", "what is soul.md or user.md", "explain auto-memory or MEMORY.md", "what is a loop scheduler or heartbeat", or when the user asks for the canonical guide.
richfrem/agent-plugins-skills · ★ 3 · Code & Development · score 67

Install: claude install-skill richfrem/agent-plugins-skills

## Dependencies This skill requires **Python 3.8+** and standard library only. No external packages needed. **To install this skill's dependencies:** ```bash pip-compile ./requirements.in pip install -r ./requirements.txt ``` See `../../requirements.txt` for the dependency lockfile (currently empty — standard library only). --- # Agentic OS Guide The core insight: LLMs are stateless functions. `CLAUDE.md` is the only file loaded by default into every conversation. The **Agentic OS** pattern turns this constraint into a full operating system metaphor. | OS Concept | Agent Equivalent | |------------|-----------------| | Kernel | `CLAUDE.md` hierarchy (global -> org -> project -> local) | | RAM | `context/` folder (soul, user prefs, memory) | | Disk | `context/memory/YYYY-MM-DD.md` dated session logs | | Stdlib | `skills/` procedural knowledge bundles | | Processes | `.claude/agents/` sub-agents with isolated context | | Shell | `.claude/commands/` slash commands | | Cron | `/loop` + `heartbeat.md` scheduled background tasks | | Boot | `START_HERE.md` + `MEMORY.md` bootstrap on session start | | Autoresearch Loop | `os-eval-runner` + `improvement-ledger.md` | ## Skill Categories (Mental Model) | Category | Skill | One-liner | |---|---|---| | **Orchestration** | `os-improvement-loop` | Multi-agent concurrent loop: ORCHESTRATOR + PEER + INNER | | **Evaluation** | `os-eval-runner` | Autoresearch eval engine — scores and gates SKILL.md iterations | | **Evaluation** | `os-ev