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.

GitHub stars: 492
last updated: Jun 11, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Skip for subagents.

If activation mode is explicit and this request did not explicitly invoke Aegis or a named skill, stay on the fast path; do not route to any Aegis skill. Explicit invocation proceeds normally. You have Aegis. Load explicit/relevant Aegis skill before response/action; otherwise proceed normally.

Outcome Anchor

Understand the requested object, scope, actions, conditions, and deliverables from the conversation. Complete the authorized task within business constraints and deliver a usable, verifiable result. Project goals guide durable choices; they do not override the user's current scope. Preserve outstanding intent across follow-ups; clarify material ambiguity before dependent action and continue independent authorized work. Do not repeat satisfied approvals.

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly