Using Aegis

This is the entry point that decides whether Aegis needs to route your request to a specialized skill or just handle it directly. It runs a triage check at the start of each turn: does this need goal framing, baseline documentation, TDD routing, or architecture review? If not, it gets out of the way. The hot path rules are dense but practical. Low complexity tasks get a fast lane with intent plus verification. Medium and high complexity work triggers baseline reads and planning. Cross-module or contract changes always escalate to architecture review. The framework assumes you don't want Aegis writing project files for every tiny question, so workspace support is lazy by default. It's basically traffic control for a larger agent system.

Install to Claude Code

npx -y skills add ganyuanran/aegis --skill using-aegis --agent claude-code