dementev-dev/adversarial-review
Developer toolsこのページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。 原文を見る
Claude Code skill for adversarial AI code & plan review. One AI writes, another tears it apart. Iterative fix loop until approved.
概要
Claude Code skill for adversarial AI code and plan review. One AI writes the code. Another tears it apart. Iterate until approved. Most AI code review tools validate your changes — "looks good, maybe add tests." Adversarial review does the opposite: the reviewer 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). - — review the plan BEFORE writing code. Catch architecture mistakes, missing steps, and risks early - — review the implementation. Bugs, security, data loss - — verify the implementation matches the plan - — Claude fixes issues based on reviewer feedback and resubmits for re-review. Up to 5 rounds until approved - — SKILL.md + one references/runner.
README
以下は原文 README の抜粋です。原文を見る。
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+ onereferences/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 | What it reviews | When to use |
|---|---|---|
plan |
Implementation plan | Before writing code |
code |
Git diff (unstaged, staged, or branch) | After writing code |
code-vs-plan |
Code changes against the plan | Verify implementation matches plan |
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_KEYenv var for non-interactive use
推奨ツール
別のキーワードを試すか、フィルタを外してください。
インストール
npx skillfish add dementev-dev/adversarial-review