Agent Audit scans AI agent skills for security vulnerabilities, scores them against the OWASP Agentic Skills Top 10, and generates actionable compliance reports.
3 files for Claude Code, Codex and OpenCode: agentsec, agentsec AGENTS.md, agentsec CLAUDE.md — 2,614 tokens loaded in every session.
AGENTS.md A 2,609 tok CLAUDE.md A 5 tok .claude/settings.json A — These files are semiotic-ai/agentsec'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.