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.
npx skills add yunshu0909/yunshu_skillshub --skill organizegit clone --depth 1 https://github.com/yunshu0909/yunshu_skillshubWrote 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/skills/yunshu0909/yunshu_skillshub/organize)<a href="https://agentmods.dev/skills/yunshu0909/yunshu_skillshub/organize"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/organize/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/skills/yunshu0909/yunshu_skillshub/organize"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/organize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00062 | $0.01180 |
| Opus 5.5 | $0.00025 | $0.00472 |
| Sonnet 5.5 | $0.00012 | $0.00236 |
| Haiku 4.5 | $0.00006 | $0.00118 |
Grade A, and why
organize 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 1mo 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.
What it actually says
文件夹整理助手
功能说明
帮助用户梳理混乱的文件夹,按归属分类、统一命名、清理冗余,让目录结构一目了然。
/organize→ 整理当前工作目录/organize [路径]→ 整理指定目录
工作流程
第1步:扫描全貌
ls -la查看根目录所有文件和文件夹(包括隐藏文件)- 对子目录做一层展开,了解内容
- 记录文件总数、目录总数、散落文件数
关注点:
- 散落在根目录的文件(没有归入任何子目录的)
- 命名风格不统一的目录(如有的带前缀有的不带)
- 隐藏目录/文件(判断是工具产物还是用户文件)
- 疑似重复的文件(文件名相似的用 md5 比对)
第2步:分析归属
把所有文件和目录按归属方分类。常见的归属维度:
- 按所有者:客户的 / 内部的 / 个人的
- 按类型:文档 / 代码 / 设计 / 数据 / 媒体
- 按状态:活跃的 / 归档的 / 可删除的
分类原则:
- 优先按归属方分,同一归属方的东西放一起
- 已经成体系的目录结构不动(如有明确组织的子目录)
- 工具产生的临时文件/缓存/日志,归为"可清理"类
判断"可清理"的标准:
- 隐藏目录中只有 .DS_Store 或日志文件
- 工具运行产生的缓存/临时目录(如 .playwright-mcp、node_modules 等)
- 评测/调试的中间产物,已无后续使用价值
- 重复文件中较旧的那份(需 md5 确认后才算重复)
第3步:制定方案
输出整理方案,包含:
- 目标结构:用树形图展示整理后的目录结构
- 操作清单:
- 新建哪些目录
- 哪些文件/目录移动到哪里
- 哪些目录/文件重命名
- 哪些可以删除
- 不动的部分:明确哪些保持不变、为什么
方案格式:
整理后结构:
目标目录/
├── 分类A/
│ ├── ...
├── 分类B/
│ ├── ...
└── 保留不动的/
操作清单:
- [新建] 分类A/
- [移动] xxx → 分类A/xxx
- [重命名] yyy → zzz(统一命名风格)
- [删除] .cache/(工具缓存,无保留价值)
- [不动] 保留不动的/(已有结构,无需调整)
第4步:确认后执行
必须等用户确认后再执行。用户可能:
- 同意全部 → 直接执行
- 部分调整 → 按调整后的方案执行
- 只做清理不做分类 → 只执行删除部分
执行顺序:
- 先建目录
- 再移动文件(并行移动无依赖的文件)
- 再重命名
- 最后删除
- 执行完
ls -la验证结果
第5步:展示结果
输出整理后的目录树,标注变化。
核心原则
1. 按归属分,不按格式分
"客户A的方案.pptx" 应该放在 客户A/ 下面,而不是放在 PPT/ 下面。归属比格式重要。
2. 确认再动,不自作主张
整理方案必须给用户看过、确认后才执行。尤其是删除操作,宁可多问一句。
3. 统一命名风格
同级目录的命名风格要一致:
- 要么都带前缀,要么都不带
- 要么都用中文,要么都用英文
- 日期格式统一
4. 不动已有结构
如果某个子目录内部已经组织得很好,不要拆散重组。整理的目标是根目录清晰,不是追求完美对称。
5. 疑似重复先验证
文件名相似不代表内容相同。必须用 md5 比对确认后才能判定为重复。
6. 隐藏文件谨慎处理
以 . 开头的目录可能是工具配置(如 .claude、.git),不要随意移动或删除。只清理明确是缓存/日志的。
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.
- 1mo ago Changed · +3 lines de84cffaa48c
- 2mo ago First seen · 129 lines · 62 tokens per session scan A bbd513b9b674
organize is a skill published in the GitHub repository yunshu0909/yunshu_skillshub (789 stars, last pushed 26d ago), licensed MIT. It adds 62 tokens to every session and 1,180 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
organize compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| organizeyunshu0909/yunshu_skillshub | Skill | 789 | 26d ago | MIT | A | 62 | Claude Code, Codex |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 111k | yesterday | MIT | A | 30 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 33 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |