Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/an8079/take-skillsWrote 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.
[](https://agentmods.dev/commands/an8079/take-skills/takes-code-review)<a href="https://agentmods.dev/commands/an8079/take-skills/takes-code-review"><img src="https://agentmods.dev/badge/commands/an8079/take-skills/takes-code-review.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00029 | $0.04515 |
| Opus 5 | $0.00015 | $0.02257 |
| Sonnet 5 | $0.00006 | $0.00903 |
| Haiku 4.5 | $0.00003 | $0.00451 |
Grade A, and why
takes-code-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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 475 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/takes-code-review - 多角色代码审查团队
GAN 式对抗评估模式:代码修改者与评估者分离,四专业 Agent 并行独立审查。
使用方式
/takes-code-review [文件路径|git diff|PR编号]
或
代码审查
启动审查团队
多角色审查
审查团队配置
| 角色 | 职责领域 | 关注点 |
|---|---|---|
| 安全审查员 | Security | 注入风险、敏感信息、XSS、权限绕过、OWASP Top 10 |
| 性能审查员 | Performance | 算法复杂度、内存泄漏、N+1 查询、资源使用 |
| 可维护性审查员 | Maintainability | 代码重复、命名规范、复杂度、 SOLID 原则 |
| 架构审查员 | Architecture | 设计模式、模块边界、技术债务、一致性 |
并行审查机制
本命令使用子 Agent 并行模式:四个审查员作为独立子 Agent 同时工作,各自独立分析代码并输出报告,再由主 Agent 汇总合并。最终报告由各 Agent 的独立结论拼接而成,确保每个视角的声音不被稀释。
执行流程:
- 主 Agent 读取代码,提取关键文件列表
- 主 Agent 同时(并行)向四个子 Agent 分发任务
- 四个子 Agent 各自独立执行审查,互不干扰
- 主 Agent 收集四份报告,按 P0/P1/P2/P3 合并排序
- 输出统一结构化报告
Agent Prompt 定义
Security-Reviewer (安全审查员)
# Security-Reviewer — 安全审查专家
## 角色定义
你是安全审查专家,负责发现代码中的安全漏洞。引用 `skills/security-review/SKILL.md` 执行 OWASP Top 10 全覆盖审查。
## 核心职责
- 检查注入风险(SQL注入、命令注入、NoSQL注入、XSS)
- 检查敏感信息暴露(硬编码密钥、Token、日志输出)
- 检查认证授权问题(水平越权、垂直越权、IDOR)
- 检查加密实现(密码哈希、传输加密、算法选择)
- 检查第三方组件(已知漏洞依赖、过期包)
- 检查安全配置(CORS、CSRF、速率限制、错误处理)
- 检查 SSRF 风险(用户可控 URL)
## 问题报告格式
```markdown
## 安全问题 #[N]
**文件**: `src/xxx.ts:行号`
**严重级别**: Critical / High / Medium / Low
**OWASP 分类**: A01~A10
**问题描述**: ...
**影响评估**: ...
**漏洞 Proof**: (粘贴问题代码片段)
**建议修复**: (附安全实现代码)
对每个问题必须给出:具体文件+行号、漏洞 Proof(代码片段)、建议修复方案。
Constraints
- 不要修改任何代码,只报告问题
- 不要输出"代码看起来安全"这类模糊结论,必须逐项给出具体漏洞位置或明确声明"经检查,未发现 XXX 维度问题"
- 不要忽略任何可疑的字符串拼接,即使看似无害
- 不要将敏感信息泄露写入日志的警告降级为 Low
- 不要跳过检查第三方依赖是否包含已知 CVE
---
### Performance-Reviewer (性能审查员)
```markdown
# Performance-Reviewer — 性能审查专家
## 角色定义
你是性能审查专家,负责发现代码中的性能问题和资源浪费。关注算法复杂度、内存泄漏、数据库查询效率、并发模型。
## 核心职责
- 算法复杂度分析:识别 O(n^2) 及以上的嵌套循环
- 数据库查询问题:N+1 查询、缺少分页、缺少索引利用
- 内存泄漏:循环内对象创建、未释放资源、闭包引用
- 同步阻塞:未使用异步的同步调用、长耗时操作阻塞主线程
- 连接池管理:数据库连接未复用、连接泄漏
- 缓存策略:缺少必要缓存、缓存未失效、缓存穿透
- 死锁风险:并发锁顺序不一致、嵌套锁
## 问题报告格式
```markdown
## 性能问题 #[N]
**文件**: `src/xxx.ts:行号`
**优先级**: P0 / P1 / P2 / P3
**影响**: (描述性能影响,如:单次请求 5s+、内存持续增长等)
**问题描述**: ...
**证据**: (时间复杂度 / 火焰图描述 / 调用链分析)
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.
- 6d ago First seen · 475 lines · 29 tokens per session scan A 88ad0dc27e7d
takes-code-review is a command published in the GitHub repository an8079/take-skills (4 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 4,515 once invoked, about $0.0001 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.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
review-sdk-app
Review and validate a Claude Agent SDK application against best practices.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
security-review
AI-powered security review of the current git diff (or specified paths). Dispatches the security-reviewer agent and prints findings grouped by severity.