os-initlisted

Trigger: "set up agentic OS", "initialize agent harness", "init my project for AI agents", "where do I put CLAUDE.md", "create my agent environment", "set up persistent memory". Guides users through an interview to understand their use case, then scaffolds the right Agentic OS structure. Use even when the user just asks WHERE to put files.
richfrem/agent-plugins-skills · ★ 3 · AI & Automation · score 62

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 Init Bootstrap the Agentic OS / Agent Harness structure into any project. The setup is not one-size-fits-all -- a solo developer using Claude for marketing strategy needs a very different environment than a team using agents to document a legacy system. The interview phase exists to get that right the first time. There is no official Anthropic "agentic OS" reference implementation. This pattern synthesizes Anthropic's documented features (CLAUDE.md hierarchy, /loop, sub-agents, hooks) with community conventions for persistent memory and context management. Official Anthropic docs: - CLAUDE.md and memory: https://docs.anthropic.com/en/docs/claude-code/memory - /loop scheduled tasks: https://docs.anthropic.com/en/docs/claude-code/loop - Hooks (automation): https://docs.anthropic.com/en/docs/claude-code/hooks - Sub-agents: https://docs.anthropic.com/en/docs/claude-code/sub-agents - Claude Code overview: https://docs.anthropic.com/en/docs/claude-code/overview ## Execution Flow Execute these phases in order. Do not skip phases. --- ## Phase 1: Discovery Interview Do not assume defaults. Ask the user enough to make smart decisions. Pull