codec-loop
claudeAdversarial review and build loops between Claude and OpenAI Codex: codec-review has Codex critique a plan or codebase read-only while Claude judges and rewrites; codec-build hands a frozen spec to a second model to implement, then runs a bounded review-and-fix loop over the diff. Needs the Codex CLI and codex login; without them, an opt-in same-family mode uses a different Claude model as the critic (weaker, still independent). Windows and macOS (macOS untested).
5 skills