Stop AI agents from doing things they shouldn't. The action authorization layer — pre-execution, deterministic, policies included. Drop in. Day one.
10 files for Claude Code: drive, architect, fixer, implementer and 6 more — 1,759 tokens loaded in every session.
CLAUDE.md A 1,759 tok .claude/skills/drive/SKILL.md A 81 tok .github/agents/architect.md A — .github/agents/fixer.md A — .github/agents/implementer.md A — .github/agents/reviewer-arch.md A — .github/agents/reviewer-correctness.md A — .github/agents/reviewer-design.md A — .github/agents/reviewer-spec.md A — .github/agents/spec-designer.md A — These files are permit0-ai/permit0's own configuration — they tell Claude Code 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.