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 agentmods add skills/iziqing/-disk-cleaner/disk-cleanernpx skills add iziqing/-disk-cleaner --skill disk-cleanergit clone --depth 1 https://github.com/iziqing/-disk-cleanerWrote 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/iziqing/-disk-cleaner/disk-cleaner)<a href="https://agentmods.dev/skills/iziqing/-disk-cleaner/disk-cleaner"><img src="https://agentmods.dev/badge/skills/iziqing/-disk-cleaner/disk-cleaner.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 | $0.00081 | $0.01916 |
| Opus 5 | $0.00041 | $0.00958 |
| Sonnet 5 | $0.00016 | $0.00383 |
| Haiku 4.5 | $0.00008 | $0.00192 |
Grade A, and why
clean-c-drive 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 5d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/clean-c-drive Skill
利用 WizTree 的快速扫描能力和 AI 的智能分析能力,安全清理 C 盘垃圾文件。
安全铁律(任何情况下不可违背):
- 不确定用途的文件一律不动;用户说"不认识"的软件 → 列入红线并向用户询问。
- 任何权限模式下,清理方案都必须经用户确认后才执行——管理员权限只是免去手动跑脚本,不免审查(模式库认不出"用户常用但长得像垃圾"的东西)。
- 清理前必须备份(backup.py),备份失败则中止清理。
- 分析与出方案时必须对照
references/knowledge.md(安全红线清单 / 分层惯犯表 / 执行守则)。
工作流程
阶段 1: 检查权限和扫描数据
-
检查管理员权限:
powershell -Command "([Security.Principal.WindowsPrincipal] [Security.Principal.WindowsIdentity]::GetCurrent()).IsInRole([Security.Principal.WindowsBuiltInRole]::Administrator)" -
如果有管理员权限(返回 True):
- 检查技能目录
data/下是否有 24 小时内的扫描文件 - 没有则自动扫描(WizTree 路径自动探测:环境变量
WIZTREE_PATH→ 技能目录WizTree\→ Program Files → PATH):python "<技能目录>/scan.py" C:
- 检查技能目录
-
如果没有管理员权限(返回 False):
data/有现成数据就用;没有则提示用户:当前没有管理员权限,无法自动扫描。 请选择: 1. 以管理员权限重新启动 Claude Code(推荐,扫描/执行全自动) 2. 手动以管理员身份运行 WizTree,导出数据到 data 目录后再次运行此命令 (导出时"文件"和"文件夹"都要勾选;CSV 别存C盘)
阶段 2: 分析扫描数据
python "<技能目录>/analyze.py" "<csv_file>" --min-size 50
两层分析,缺一不可:
- 模式库快筛(analyze.py 自动完成):识别已知缓存/垃圾目录,按 高🔴/中🟡/低🟢 分级,红线目录已自动排除;
- 知识库逐案研判(AI 来做):模式库实测只能覆盖约 1/3 的可清理空间,剩下的大头——单个巨型转储、Chrome 端侧AI模型、软件多重安装、废弃应用数据、DISM 等系统官方机制可回收的空间——需要对照
references/knowledge.md对目录/大文件排行逐案判断。 - 预估要保守:WinSxS 与 System32 之间大量硬链接,目录合计大于实际占用是正常现象。
阶段 3: 生成清理方案(必须等用户批复)
向用户展示:
- 磁盘概况:总容量、已用、可用
- 可清理项分级列表:每项写清 路径 / 大小 / 是什么 / 删了会怎样 / 清理方式,逐条编号方便逐条批复
- 红线清单:明确列出本次绝不碰的内容
- 询问用户选择清理级别或逐条批复。未批复 = 不执行;沉默 ≠ 同意。
阶段 4: 备份待清理目录
在执行任何清理操作之前,必须先备份!
- 检查备份驱动器(自动选非C盘剩余空间最大的,最少需要 5GB):
python "<技能目录>/backup.py" drive - 创建备份(小于1GB直接复制,大于等于1GB压缩;生成 manifest.json):
注意:robocopy 备份会保留隐藏/系统属性,核对备份目录时要用python "<技能目录>/backup.py" create --paths "路径1" "路径2" --priority highGet-ChildItem -Force。 - 备份失败(空间不足等)→ 中止清理,提示用户处理。
阶段 5: 执行清理
- 有管理员权限:按批复方案执行,显示进度和逐项释放量
- 无管理员权限:生成
clean_<level>.ps1到技能目录,提示用户以管理员身份运行 - 执行前检查进程(生成的脚本已内置警告):浏览器 / VS Code / java(Gradle 守护进程)运行中会导致对应缓存清理不完整
- 生成的脚本已自动处理:清空目录时保留目录本身、排除
claude*(Claude Code 会话自身临时文件)、支持单文件目标
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.
- 5d ago First seen · 127 lines · 81 tokens per session scan A 3b8b1b6a7dc2
clean-c-drive is a skill published in the GitHub repository iziqing/-disk-cleaner (33 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 1,916 once invoked, about $0.0004 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
janitor-swipe
Tinder for your Claude Code skills. Reviews a sorted deck of every installed skill and lets you swipe keep / delete / skip on each one. Use when the user wants to bulk-clean their skill collection, triage unused skills, or do interactive skill cleanup. Trigger with '/janitor-swipe'.
disk-space-analyzer
Analyze disk space and find cleanable files. Use when user wants to clean disk, free up space, find large files, analyze disk usage, or asks about what's taking up space. Triggers on requests like "clean my disk", "free up space on C:", "find large files", "what's using my disk space", "disk cleanup".
meeting-note-summarizer
Turn meeting notes or transcripts into factual summaries, decisions, questions, and action items. Use when a user wants a concise recap or needs explicit owners and deadlines extracted without filling in missing details.
daily-standup-journal
Generate concise daily standups, reflection prompts, and weekly retrospectives for individuals or teams. Use for planning a day, surfacing blockers, reviewing user-provided entries, or drafting a check-in without assuming prior history.
happiness-skill
当用户问「怎么才能更幸福/为什么得到了还不满足/怎么减少焦虑」时调用。 核心理念: 幸福是缺憾感清空的默认状态, 是可训练的技能; 欲望是与自己的契约(得到前不快乐), 同时只留一个重大欲望; 活在当下。 不适用于: 临床抑郁等需要专业治疗的场景(本书方法不能替代医疗)。 Triggers: 幸福/不快乐/欲望/焦虑/知足/活在当下/happiness/desire/anxiety.
add-teams
Adds Microsoft Teams connector to a Power Apps code app. Use when sending Teams messages, posting to channels, or integrating with Teams chat.