Claude 代码技能，用于对抗性 AI 代码和计划审查。

一个AI编写代码。另一个AI拆解代码。迭代直到批准。

这是什么

大多数AI代码审查工具都会验证你的更改——“看起来不错，也许可以加测试。” 对抗性审稿则相反：审稿人默认持怀疑态度 并试图打破对变革的信心。它寻找失败的部分 在生产环境中，而不是什么值得改进的地方。

这是克劳德密码技能 — 一个SKILL.md文件加上一个小的references/runner.md] 教Claude如何通过外部AI模型进行对抗性评审 （目前为OpenAI手册）。

主要特征

• 图纸审查 — 在编写代码前先审查图纸。捕捉架构 错误、遗漏步骤以及早期风险
• 代码审查 — 审查实现。漏洞、安全、数据丢失
• 代码与计划 — 验证实现与计划相符
• 迭代 — Claude根据评审反馈修复问题并重新提交 供重新审核。最多可进行5轮审核，直到批准
• 轻量级 — SKILL.md + 一 references/runner.md）（细长跑者 子代理规范），没有服务器，没有代理，也没有外部运行时 DEPS。比较 使用 Codex-plugin-cc：

Adversarial Review

Claude Code skill for adversarial AI code and plan review.

One AI writes the code. Another tears it apart. Iterate until approved.

What is this

Most AI code review tools validate your changes — “looks good, maybe add tests.” Adversarial review does the opposite: the reviewer defaults to skepticism and tries to break confidence in the change. It looks for what will fail in production, not what might be nice to improve.

This is a Claude Code skill — a SKILL.md file plus a small references/runner.md that together teach Claude how to run adversarial reviews through an external AI model (currently OpenAI Codex).

Key features

• Plan review — review the plan BEFORE writing code. Catch architecture mistakes, missing steps, and risks early
• Code review — review the implementation. Bugs, security, data loss
• Code-vs-plan — verify the implementation matches the plan
• Iterative — Claude fixes issues based on reviewer feedback and resubmits for re-review. Up to 5 rounds until approved
• Lightweight — SKILL.md + one references/runner.md (thin runner subagent spec), no server, no broker, no external runtime deps. Compare with codex-plugin-cc: ~15 JS modules, App Server, JSON-RPC broker, lifecycle hooks

How it works

┌─────────┐     ┌──────────┐     ┌─────────┐
│  Claude  │────>│ Reviewer  │────>│  Claude  │
│  (code)  │     │ (Codex)   │     │  (fix)   │
└─────────┘     └──────────┘     └─────────┘
     ^                                 │
     │         ┌──────────┐            │
     └─────────│ Reviewer  │<───────────┘
               │(re-review)│
               └──────────┘
                    │
              VERDICT: APPROVED

Three modes

Mode is auto-detected from context, or you can force it with an argument.

Quick start

1. Prerequisites

Claude Code and OpenAI Codex CLI must be installed.

Verify both are available:

claude --version   # Claude Code CLI
codex --version    # OpenAI Codex CLI (>= 0.115.0)

If Codex is missing: npm install -g @openai/codex

Authentication. Codex needs an OpenAI account. Either:

• Sign in interactively: codex (opens browser)
• Or set CODEX_API_KEY env var for non-interactive use