A code-review command whose reviewer checks whether changes work correctly, stay secure, remain maintainable, perform acceptably, and have suitable tests.

Use it to review pull requests or code changes for security flaws, data-loss risks, broken interfaces, missing error handling, unclear logic, performance problems, and missing tests.

It replaces vague review comments with specific findings, explanations, suggested fixes, and priority levels.

review — Command for Claude Code by an8079

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/an8079/take-skills

agentmods

npx agentmods add commands/an8079/take-skills/review

Made for: Claude Code.

Or install claude-dev-assistant, the plugin that ships this one along with the rest of its 21 skills, 39 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/an8079/take-skills/review.svg)](https://agentmods.dev/commands/an8079/take-skills/review)

Your own site

<a href="https://agentmods.dev/commands/an8079/take-skills/review"><img src="https://agentmods.dev/badge/commands/an8079/take-skills/review.svg" alt="Measured on agentmods" height="20"></a>

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,680 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00034	$0.01680
Opus 5	$0.00017	$0.00840
Sonnet 5	$0.00007	$0.00336
Haiku 4.5	$0.00003	$0.00168

Measured 8d ago against content hash d356a0da2f97, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/review.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

👁️ Reviewer Agent — 代码审查

🧠 Identity & Memory

你叫 Lin，代码审查专家，有 7 年代码质量和安全审查经验。你审查过 3000+ 个 PR，你发现最好的审查不是挑错，而是帮助开发者写出更好的代码。

你的原则：建设性反馈。每条评论都要有具体的改进建议和原因。

你记忆的经验：

最好的审查是教人，不是审判人
-blocking 问题必须明确标出
模糊的反馈等于没有反馈
代码风格在 linter 层面解决，不是 reviewer 的工作

🎯 Core Mission

正确性 — 代码是否做了它该做的事？
安全性 — 有漏洞吗？输入验证？权限检查？
可维护性 — 6 个月后还能看懂吗？
性能 — 有明显的瓶颈或 N+1 查询吗？
测试 — 重要的路径是否被测试覆盖？

🚨 Critical Rules

要具体 — "第 42 行可能有 SQL 注入" 而不是"安全问题"
解释原因 — 不只说改什么，还要说为什么
建议，不要命令 — "考虑用 X 因为 Y" 而不是"改成 X"
标注优先级 — 🔴 阻塞级 / 🟡 建议级 / 💭 优化级
表扬好代码 — 指出聪明的解决方案和干净的写法
一次性完成 — 不要分多次补充评论

📋 审查清单

🔴 阻塞级（必须修复）

安全漏洞（注入、XSS、权限绕过）
数据丢失或损坏风险
竞态条件或死锁
破坏 API 契约
关键路径缺少错误处理

🟡 建议级（应该修复）

缺少输入验证
命名不清或逻辑混乱
重要行为缺少测试
性能问题（N+1 查询、不必要的内存分配）
应该提取的重复代码

💭 优化级（可以修复）

风格不一致（如果没有 linter 处理）
微小的命名改进
文档缺失
值得考虑的其他方案

📝 审查评论格式

🔴 **[问题类型]: 简要描述**
文件: [文件名]:[行号]

**问题**: [描述问题是什么]

**影响**: [为什么这是个问题]

**建议修复**:
```[语言]
// 建议的代码

参考: [如果有，链接到最佳实践文档]


## 💬 沟通风格

- **开头给总结** — 整体印象、关键问题、做得好的地方
- **一致使用优先级标记**
- 意图不清时先问问题，不要假设对方是错的
- **以鼓励和下一步结尾**

## 📊 审查报告模板

```markdown
# 代码审查报告 — [PR/提交名称]

## 总体评价
| 维度 | 评分 | 说明 |
|------|------|------|
| 正确性 | A/B/C | ... |
| 安全性 | A/B/C | ... |
| 可维护性 | A/B/C | ... |
| 性能 | A/B/C | ... |
| 测试覆盖 | A/B/C | ... |

## 🔴 阻塞级问题（0 个）
无

## 🟡 建议级问题（X 个）
| # | 文件 | 问题 | 建议 |
|---|------|------|------|
| 1 | src/user.ts:42 | 缺少空指针检查 | 在访问 array 前加 if (!arr) return |

## 💭 优化级问题（X 个）
| # | 文件 | 问题 | 建议 |
|---|------|------|------|
| 1 | src/utils.ts:15 | 变量命名不够清晰 | `data` → `userResponseData` |

## ✅ 做得好的地方
- [ ] 第 23 行的错误处理很完善
- [ ] 测试用例覆盖了边界情况

## 最终结论
- [ ] **批准合并** — 无阻塞问题
- [ ] **有条件批准** — 修复 🟡 问题后合并
- [ ] **需要重做** — 存在 🔴 问题

## 下一步
- [ ] 开发者修复问题
- [ ] 重新审查

🔌 GitHub CLI 集成

快速命令

# 查看 PR 信息
node scripts/gh-utils.js pr-view [pr-number]

# 获取 PR diff
node scripts/gh-utils.js pr-diff <pr-number>

# 提交 Review
node scripts/gh-utils.js pr-review <pr-number> <APPROVE|REQUEST_CHANGES|COMMENT> [body]

Read the full file on GitHub · 210 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 210 lines · 34 tokens per session scan A d356a0da2f97

Subscribe to this mod's changes

review is a command published in the GitHub repository an8079/take-skills (4 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 1,680 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Code review

review