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-cleaner)<a href="https://agentmods.dev/commands/an8079/take-skills/takes-cleaner"><img src="https://agentmods.dev/badge/commands/an8079/take-skills/takes-cleaner/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/an8079/take-skills/takes-cleaner"><img src="https://agentmods.dev/badge/commands/an8079/take-skills/takes-cleaner.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00049 | $0.01323 |
| Opus 5 | $0.00024 | $0.00661 |
| Sonnet 5 | $0.00010 | $0.00265 |
| Haiku 4.5 | $0.00005 | $0.00132 |
Grade A, and why
takes-cleaner 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 10d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🧹 /takes-cleaner — AI 垃圾代码清理
清理 AI 生成的臃肿代码，删除重复、死代码、无用抽象，保留原有行为。
何时使用
| 场景 | 示例 |
|---|---|
| 代码感觉臃肿 | 太多包装层、重复辅助函数 |
| 重复逻辑 | 复制粘贴的分支、冗余代码 |
| 过度抽象 | 投机性间接层、单用辅助层 |
| 死代码 | 未使用的导出、调试残留、无reachable 分支 |
| 边界违规 | 隐藏耦合、职责错位、跨层导入 |
何时不用
| 场景 | 原因 |
|---|---|
| 主要任务是新功能构建 | 应该用 /code |
| 想要 broad redesign | 范围太大 |
| 通用重构 | 没有 anti-slop 意图 |
清理规则
优先级（从高到低）
- 死代码删除 — 最安全，先删
- 重复代码移除 — 提取公共逻辑
- 命名和错误处理清理 — 提高可读性
- 测试加固 — 补充缺失的测试
分类处理
| 类型 | 特征 | 处理方式 |
|---|---|---|
| Duplication | 重复逻辑、复制粘贴分支 | 提取公共函数 |
| Dead code | 未使用代码、不可达分支 | 直接删除 |
| Needless abstraction | 包装层、单用辅助层 | 展开内联 |
| Boundary violations | 隐藏耦合、跨层导入 | 重构职责 |
| Missing tests | 行为未锁定、回归覆盖弱 | 补充测试 |
工作流程
Step 1: 保护现有行为
- 识别必须保持不变的部分
- 添加或运行最窄的回归测试
- 如无法先测试，记录验证计划
Step 2: 制定清理计划
- 绑定到目标文件或功能区
- 列出具体的代码味道
- 从最安全删除到风险更高的合并
Step 3: 逐个味道清理
- Pass 1: 死代码删除
- Pass 2: 重复移除
- Pass 3: 命名和错误处理
- Pass 4: 测试加固
- 每次后运行验证
Step 4: 质量门禁
- 回归测试保持绿色
- 运行 lint、typecheck
- 失败则回退或修复
Step 5: 输出报告
- 变更文件列表
- 简化内容
- 行为锁定/验证结果
- 剩余风险
触发方式
/takes-cleaner # 清理当前改动
/takes-cleaner <文件> # 清理指定文件
/takes-cleaner src/auth # 清理指定目录
/takes-cleaner --review # 仅审查模式（不修改）
示例
Good 用法
/takes-cleaner src/auth
→ 删除 auth 模块中的死代码、重复逻辑
/takes-cleaner src/utils.ts src/api.ts
→ 清理指定文件的包装层
/takes-cleaner --review
→ 仅审查模式，输出清理计划但不修改
Bad 用法
/takes-cleaner 重构 auth 支持 SSO
→ 范围过大，是新功能不是清理
/takes-cleaner 清理格式
→ 应该用 lint/format 工具
审查模式 (--review)
审查模式不修改文件，只输出清理计划：
- 不从编辑文件开始
- 审查清理计划、变更文件、回归覆盖
- 检查：
- 死代码或未使用导出残留
- 应被整合的重复逻辑
- 仍模糊边界的无用包装层
- 保留行为缺失测试或回归覆盖弱
- 看起来改变了行为但没有意图的清理
- 输出审查意见和需要的跟进
- 将需要的更改交给单独的 writer pass
报告模板
# 🧹 清理报告 — [文件/模块]
## 变更文件
| 文件 | 变更类型 | 说明 |
|------|----------|------|
| src/auth.ts | 删除 | 移除未使用的 validateToken 函数 |
## 简化内容
- 删除 3 个死函数
- 合并 2 个重复辅助函数
- 展开 1 个无用包装层
## 行为锁定
- ✅ 单元测试通过: 42 passed
- ✅ 集成测试通过: 12 passed
- ✅ ESLint: 0 errors
- ✅ TypeScript: 0 errors
## 剩余风险
- [ ] 建议补充 token 刷新的集成测试
## 验证
运行 `npm test` 全部通过 ✅
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.
- 10d ago First seen · 162 lines · 49 tokens per session scan A fbf54a88004c
takes-cleaner is a command published in the GitHub repository an8079/take-skills (4 stars, last pushed 5mo ago), licensed MIT. It adds 49 tokens to every session and 1,323 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.
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.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.
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.