Read-only macOS security audit (27 checks) for humans and AI agents — Claude Code, Codex, OpenCode. Plus a tool that redacts leaked API keys out of AI-agent logs.
1 file for Codex and OpenCode: mac-security-audit-skill AGENTS.md — 618 tokens loaded in every session.
AGENTS.md A 618 tok These files are yanis7774/mac-security-audit-skill's own configuration — they tell 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.