Agentic Os

This turns Claude Code into a persistent multi-agent operating system instead of treating it as a disposable chat. You get a kernel in CLAUDE.md that routes tasks to specialist agents (a @dev for code, a @writer for docs, a @researcher for analysis), slash commands for recurring workflows like /daily-sync or /outreach, and file-based memory in a data/ directory so state survives across sessions. No external databases, just markdown and JSON. It's overkill for one-off scripts but makes sense if you're building something like a personal automation system or a long-running project where you need agents to hand off work to each other and remember what happened yesterday. The architecture mirrors production agentic setups with clean separation between routing logic, agent definitions, and persistent state.

Install to Claude Code

npx -y skills add affaan-m/ecc --skill agentic-os --agent claude-code