GanyuanRan /
Aegis
Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.
Updated 8 min ago
Why now
Version v2.15.0 came out on November 4.
+23 stars gained this week
Stars gained each day, last 30 days
Usual pace · 3 / day
Oct 9Oct 24
This week Before Usual pace
In short
Aegis is a method pack for AI coding agents that makes them plan against the project's real baseline before editing and verify completion with fresh evidence. It is for developers who want fewer reworks and safer changes from agents like Codex or Claude Code.
Summary written by AI from the repository’s description and README.
What this repo contains
- Hooks
- hooks/hooks.json Hook files list commands an agent runs by itself on events.
- Skills
- 23 SKILL.md files
- Scripts
- 2 in skill folders Shell 1 · TypeScript 1
- Files for
- Claude Code, Codex, Cursor
- Its README
- Links a program to download
No executables or MCP settings.
Read from the repository's files and README: facts to check on GitHub, not a review.
GanyuanRan / Aegis
View on GitHub(opens in new tab)