#ai-code-review

AI PR Gate for Claude Code + Codex: one model implements, a different model reviews the exact diff, and a signed, tamper-evident evidence trail opens as a real GitHub PR for a human to merge — plus live cross-model token/quota awareness.

Kill-tested guard skills for AI coding agents , self-invoking quality gates that catch AI failure modes in security, tests, docs, dependencies, and diffs before the agent says "done." Works with Claude Code, Codex, and Cursor.

Make agents prove their work. Independent verification, deterministic quality gates, and signed evidence for AI-generated code.

Your engineering crew for AI-written code.

All CLI Council for Claude Code — ask five models across four vendors the same hard question, let them rank each other anonymously, then decide yourself. Runs on the CLIs you already have. No API keys.

Evidence-first AI code review for Codex and Claude Code