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 staruhub/ClaudeSkills --skill geek-skills-c-drive-cleanergit clone --depth 1 https://github.com/staruhub/ClaudeSkillsWrote 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/staruhub/claudeskills/geek-skills-c-drive-cleaner)<a href="https://agentmods.dev/skills/staruhub/claudeskills/geek-skills-c-drive-cleaner"><img src="https://agentmods.dev/badge/skills/staruhub/claudeskills/geek-skills-c-drive-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/skills/staruhub/claudeskills/geek-skills-c-drive-cleaner"><img src="https://agentmods.dev/badge/skills/staruhub/claudeskills/geek-skills-c-drive-cleaner.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 | $0.00103 | $0.01126 |
| Opus 5 | $0.00051 | $0.00563 |
| Sonnet 5 | $0.00021 | $0.00225 |
| Haiku 4.5 | $0.00010 | $0.00113 |
Grade A, and why
c-drive-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 13d 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
C盘清理大师
安全导向的 Windows 磁盘清理：分析 → 模拟 → 执行 → 验证，破坏性操作永远先预览。
验收标准（清理任务完成前自查）
- 实际删除前完成过一次模拟运行，并把预览结果给用户看过
-
--execute前用户明确确认过（清理不经过回收站，不可恢复） - 已提醒用户创建系统还原点和关闭浏览器（清缓存时）
- 未触碰"禁删清单"中的任何目录
- 清理后重跑分析,回报实际释放的空间数字,不是"应该清理了"
- 用户个人大文件（视频/压缩包等）只报告位置与大小，删除由用户自己决定
禁删清单（碰到即停）
C:\Windows\System32— 核心系统文件C:\Windows\WinSxS— Windows 组件存储（要瘦身走 DISM，不许直接删）C:\Program Files/C:\ProgramData— 已装程序及数据C:\Windows\Prefetch— 预读取文件，删了拖慢启动- 休眠文件与虚拟内存 — 走系统设置调整，不手动删文件
工作流程
1. 分析占用
python scripts/analyze_disk.py C:\ 2 20 # 路径 深度 显示前N项
2. 查找大文件（只报告，不删）
python scripts/find_large_files.py C:\ 100 50 # 路径 最小MB 最大结果数
python scripts/find_large_files.py C:\Users 200 100 .mp4,.avi,.mkv # 按类型过滤
常见大文件类型：视频 .mp4,.mkv,.mov；安装包 .iso,.exe,.msi；压缩包 .zip,.rar,.7z；备份 .bak,.sql。
3. 清理（默认模拟模式）
python scripts/clean_temp.py # 模拟：只预览
python scripts/clean_temp.py --execute # 实际执行：需二次确认
覆盖范围：%TEMP%、C:\Windows\Temp、浏览器缓存（Chrome/Edge/Firefox）、.log/.etl/.old 日志、回收站。
4. 验证
重跑 analyze_disk.py，对比前后数字回报实际效果。
已知陷阱
| 陷阱 | 具体表现 | 应对 |
|---|---|---|
| 无权限静默漏扫 | 非管理员运行，扫描结果偏小误导判断 | 提示以管理员身份运行；脚本会跳过无权目录并计数 |
| 浏览器缓存清理失败 | 浏览器进程占用文件 | 先关闭所有浏览器窗口再清 |
| 清完没效果 | 临时文件本来就不大，大头是个人文件或程序 | 回到大文件报告和目录排行,引导用户决策(卸载/转移) |
| 误以为可恢复 | 脚本删除不经回收站 | 执行前明确告知不可恢复,这也是模拟先行的原因 |
| SSD 清到贴满 | 追求 100% 利用率 | SSD 保留 15-20% 空间维持性能;低于 20% 时才建议清理 |
权限与配套
- 部分系统文件需管理员权限（右键"以管理员身份运行"）
- 可配合系统自带工具：
cleanmgr、存储感知、DISM 组件清理 - 深入的垃圾文件位置、清理命令、安全实践：
references/windows_cleanup_guide.md
脚本说明
| 脚本 | 功能 | 安全特性 |
|---|---|---|
scripts/analyze_disk.py |
目录占用排行 + 大文件列表 | 只读；自动跳过无权目录 |
scripts/find_large_files.py |
按大小/类型查找文件 | 只读；显示访问时间辅助判断 |
scripts/clean_temp.py |
清理临时文件/缓存/日志/回收站 | 默认模拟；--execute 二次确认；跳过系统关键目录 |
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago First seen · 75 lines · 103 tokens per session scan A ee4d1a99b376
c-drive-cleaner is a skill published in the GitHub repository staruhub/ClaudeSkills (712 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 1,126 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
report-helper
A Chinese-language research workflow that searches the internet and produces a formatted PDF report about a specified topic.
giasip-dispatch
A skill for sending a task to other AI models and collecting their results. It supports direct API calls, command-line tools and built-in internal agents, depending on the model.
searchcans-deep-research
Conduct bounded, evidence-led, account-aware web research with SearchCans SERP API and Reader API. Use for cited-source research that needs current localized web evidence, such as market, competitor, technology, policy, company, or product research; plan 3–5 subquestions, set a source budget, read selected pages…
searchcans-serp-content-gap
Analyze a current, geo-targeted Google or Bing SERP with SearchCans and turn observed result features, People Also Ask questions, related searches, knowledge graph, and news signals into an evidence-backed, account-aware content decision brief. Use for localized SEO/GEO planning, keyword research, competitor-page…
searchcans-market-watch
Build a current, geo-targeted market-watch snapshot from Google Search, Google News, Bing Search, and selected Reader extracts. Use for competitor and category monitoring, PR/news tracking, launch intelligence, and URL-level change checks between two bounded runs; reject malformed, placeholder, or un-attributable News…
searchcans-product-serp-brief
Create a localized product-search evidence brief from Google Shopping, Google web results, Google Images, and optional Reader extracts of explicit merchant URLs. Use for e-commerce category research, competitor assortment discovery, product-page planning, and market-specific merchandising briefs.