An LLM-powered security auditing tool for Arch User Repository (AUR) packages with yay integration.
3 files for Claude Code, Codex and OpenCode: self-improve, aur-sleuth AGENTS.md, aur-sleuth CLAUDE.md — 5,112 tokens loaded in every session.
AGENTS.md A 4 tok CLAUDE.md A 5,108 tok .claude/skills/self-improve/SKILL.md A — These files are mgalgs/aur-sleuth's own configuration — they tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.