Show HN: Claude-plan-reviewer – Rival AI 审核 Claude Code 的计划
Claude-plan-reviewer 是一个工具,用于在 Claude 生成代码计划时,将其发送给其他 AI 模型进行对抗性评审。通过多轮反馈机制,Claude 会根据评审结果调整计划,最终生成代码。该工具旨在利用不同模型的视角提升代码质量,而非比较模型优劣。
2 分•作者: yuu1ch13•大约 2 小时前
Claude Code 有一个计划模式,在编码之前会先编写实现计划。我构建了一个工具,该工具会拦截这些计划,并在允许 Claude 继续之前将其发送给一个竞争的 AI(Codex CLI 或 Gemini CLI)进行对抗性评审。
当 Claude 调用 `ExitPlanMode` 时,会触发一个 `PreToolUse` 钩子,将计划发送给评审者,并返回 `{ permissionDecision: "deny", permissionDecisionReason: "<feedback>" }`。Claude 会收到拒绝信息并根据反馈修改计划,然后再次尝试。经过可配置的多轮(默认:2 轮)后,最终通过。最后你会得到原始计划与最终计划的对比差异。
不同的模型有不同的盲点。价值在于第二视角,而不是某个模型本身更好。
```
npm install -g claude-plan-reviewer
claude-plan-reviewer setup
```
需要 Node.js 18+ 和 Codex CLI 或 Gemini CLI。约 400 行 JavaScript,无依赖。MIT 许可证。
查看原文
Claude Code has a plan mode where it writes implementation plans before coding. I built a tool that intercepts those plans and sends them to a competing AI (Codex CLI or Gemini CLI) for adversarial review before Claude is allowed to proceed.<p>When Claude calls `ExitPlanMode`, a `PreToolUse` hook fires, sends the plan to the reviewer, and returns `{ permissionDecision: "deny", permissionDecisionReason: "<feedback>" }`. Claude receives the denial with the feedback, revises the plan, and tries again. After a configurable number of rounds (default: 2), it passes through. At the end you get a diff of the original vs. final plan.<p>Different models have different blind spots. The value is in the second perspective, not in one model being "better."<p>```
npm install -g claude-plan-reviewer
claude-plan-reviewer setup
```<p>Requires Node.js 18+ and Codex CLI or Gemini CLI. ~400 lines of JS, zero dependencies. MIT licensed.<p><a href="https://github.com/yuuichieguchi/claude-plan-reviewer" rel="nofollow">https://github.com/yuuichieguchi/claude-plan-reviewer</a>