A two-person rule for AI coding agents

说明与用途

通过实现本地、SHA绑定的审批账本，确保 AI 代理生成的代码在经过适当审查后才能推送，防止过期审批和未经授权的推送，即使代理在无人监控的情况下运行。

问题

Ensuring that AI coding agents only ship code after a proper review, preventing stale approvals and unauthorized pushes in unattended multi-agent workflows.

结果

The twoperson workflow enforces commit-bound reviews, preventing stale approvals and unauthorized pushes, even when agents run unattended.

工作流

• Run twoperson install-hook to add a Claude Code Stop hook for the reviewer.
• Configure each agent to run in its own git worktree so inboxes resolve to the main tree.
• Builder writes a JSON review packet (goal, head SHA, files, tests) and publishes it.
• Reviewer claims the packet, records a verdict in the ledger.
• Twoperson enforces rules: rejects verdicts for unpublished packets, mismatched commit SHAs, or pushes without a matching approval.
• When a commit is rebased or amended, the approval becomes stale and is automatically refused.
• The builder cannot ship code until a valid, current review is present.
• The system logs all actions locally, providing an offline gate before any remote PR or branch protection.

证据

It records that a review happened, pins the verdict to one commit, and refuses to let the builder call anything "shipped" without one.

来源

The Stop hook. twoperson install-hook adds a Claude Code Stop hook so the reviewer wakes when the builder's session ends, instead of polling on a timer.

来源