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