cc-pair

About

Hi HN, I built cc-pair because I kept noticing that when a coding agent reviews its own work, it tends to go easy on it. cc-pair pairs the two agents I already use — Claude Code and Codex — so one authors a change and the other reviews it, and they iterate until the reviewer approves or the round limit (default 3) escalates to the human. Roles are symmetric: either agent can be author or reviewer. In auto mode, `pair start --as claude` (or `--as codex`) opens the author and starts the other agent as reviewer for each round — no second terminal needed. In manual mode you run both yourself. They communicate through numbered message files in a shared directory (~&#x2F;.pair&#x2F;<repo>-<hash>&#x2F;), so the whole review thread is inspectable on disk. Install: npm install -g claude-codex-pair (Node 22+, macOS&#x2F;Linux for auto mode; manual mode works on Windows). Both CLIs need to be installed and signed in. Repo: https:&#x2F;&#x2F;github.com&#x2F;leonlee&#x2F;cc-pair — the README has an example review thread in Appendix A, and DESIGN.md specifies the protocol. I&#x27;d love feedback: does cross-model review actually catch things self-review misses in your experience, and what would you want the reviewer to be stricter about?

Discovery history

1. Show HN

   Oct 30, 2026 · 1 observations

2. V2EX·分享创造

   Oct 31, 2026 · 1 observations