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 Mizoreww/awesome-claude-code-config --skill storage-analyzergit clone --depth 1 https://github.com/Mizoreww/awesome-claude-code-configWrote 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/mizoreww/awesome-claude-code-config/storage-analyzer)<a href="https://agentmods.dev/skills/mizoreww/awesome-claude-code-config/storage-analyzer"><img src="https://agentmods.dev/badge/skills/mizoreww/awesome-claude-code-config/storage-analyzer.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Privilege Escalation · line 47 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 112 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 118 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 | $0.00334 | $0.04383 |
| Opus 5 | $0.00167 | $0.02191 |
| Sonnet 5 | $0.00067 | $0.00877 |
| Haiku 4.5 | $0.00033 | $0.00438 |
Grade B, and why
storage-analyzer scanned grade B with 1 finding 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 9d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
**Linux 另有 `accounting` 字段(缺口对账),必须读**:Linux 上 `du` 对 root 目录是**静默低估**(读不到算作 0 还返回成功),不对账就会把大户报错。对账**按文件系统分别进行**(`per_filesystem` 数组),因为 `/home` 独立分区极常见,合并算会捏造出巨额假重叠。每项的 `gap_kb` 归入该盘蓝色「系统及其他」并提示可用 sudo 核实;若出现 `overlap_k How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Storage Analyzer
源自 KKKKhazix/khazix-skills(MIT,见
LICENSE), 本仓库在其基线上增加了 Linux 支持并加固了安全模型 —— 详见 UPSTREAM.md。
对 macOS / Windows / Linux 做一次只读存储分析,产出交互式 HTML 报告。流程:扫描 → 分析分级 → 生成网页 → 打开。
铁律
- 全程只读。 只能跑扫描/统计/列目录/读元信息(df、du、diskutil、stat、ls)。绝对禁止 rm、mv、rmdir、清空回收站、改权限等任何写操作。
- 删除命令只展示,不执行。 报告里给出的清理命令是供用户自己在终端确认后运行的。即使用户在对话里说"帮我删",也要先停下确认(命中全局红线:删除文件必须先问),不要直接代跑。
- 估算标注清楚。 涉及"可释放空间"一律说明是估算值。
- 路径、命令保留原文不翻译。
执行流程
Step 1 扫描(只读)
python3 scripts/scan.py > /tmp/storage_scan.json
scan.py 自动识别系统(sys.platform):
- macOS:扫 home、library、caches、containers、group_containers、app_support、applications、downloads、dev_caches,用
du算大小。 - Windows:扫 user_profile、appdata_local、appdata_roaming、temp、downloads、program_files(_x86)、dev_caches,用
os.scandir算大小;system.disks含所有盘符。 - Linux:扫 home、cache、local_share、config、downloads、flatpak_apps、snap_home、opt、usr_local、dev_caches,用
du -x算大小(-x不跨挂载点,否则外置盘会被算进主盘)。另有两组 Linux 专有:sudo_targets(/var/lib/docker、/var/log 等 root 大户,读不到就标denied)和uncategorized($HOME 与 /var 各一层兜底下钻,捞出目标表没覆盖到的大目录)。system.disks含所有本地挂载点(已滤掉 tmpfs / squashfs / 网络盘)。
输出 JSON:system(系统/磁盘信息,含 disk_name 主盘名 + disks 全部盘)+ groups(各组子目录大小,已降序、过滤 50MB 以下)。扫描较慢,耐心等。读不到的目录标 denied,需在报告里列出并提示遗漏体量。
Linux 另有 accounting 字段(缺口对账),必须读:Linux 上 du 对 root 目录是静默低估(读不到算作 0 还返回成功),不对账就会把大户报错。对账按文件系统分别进行(per_filesystem 数组),因为 /home 独立分区极常见,合并算会捏造出巨额假重叠。每项的 gap_kb 归入该盘蓝色「系统及其他」并提示可用 sudo 核实;若出现 overlap_kb(合计超过实际已用),说明有硬链接缓存被重复计数(也可能是压缩/reflink/稀疏文件),相关项的"可释放空间"要注明实际释放量可能更小。条目上的 partial: true 表示 du 没读全、实际更大;mountpoint: true 表示该子目录是另一块盘的挂载点,不计入本盘。
Step 2 分析与分级
先看 system.os 判断系统,读对应的数据布局参考:macOS 读 references/macos.md,Windows 读 references/windows.md,Linux 读 references/linux.md(讲该系统东西存哪、怎么辨认、归哪一级)。然后读 /tmp/storage_scan.json 做这几件事:
- 挑 Top 5 占用大户,判定类型(系统资产/应用本体/应用数据/应用缓存/开发缓存/用户文件/媒体内容/下载内容/虚拟机镜像/回收站/其他)。
- 识别"神秘大目录":UUID 命名的 Container、不明的隐藏目录,要追查它属于哪个 App、装的是什么(例如某 97GB 的 UUID Container 实为 Bilibili 离线视频缓存)。必要时
ls/du深入一层看清楚,但仍只读。 - 三级分类 = 清理决策清单,不是全盘点。 只把"存在'要不要动它'这个决策"的项放进三灯;日常在用的正常应用、操作系统本身、海量零碎小文件没有清理决策,不进三灯,它们落在磁盘条的蓝色"系统及其他"里。判定标准:
- 🟢 可自动清理:纯缓存、临时文件、安装包残留、明确可再生且不影响功能、不丢用户数据(pip/uv/npm/Xcode DerivedData 等开发缓存、浏览器缓存)。
- 🟡 需人工判断:含用户数据或有判断成本(离线视频、文档、项目代码 node_modules、聊天记录、设计稿)。给内容画像 + 至少 3 句处置路径(应用内清理 / 系统工具 / 文件管理器手动审查,三选最合适)+ 风险提示。所有橙灯项在服务模式下自动有「在访达/资源管理器打开」按钮(跳过去自己审查删);如果该项有一个核实过、删了不破坏 App 的安全子路径(如 B站离线视频的
.Downloads目录、旧备份目录),给它trash_paths→ 网页出现「移到废纸篓」按钮(橙灯只准移废纸篓、可逆,绝不给"直接删除")。App 托管又无安全子路径的(Chrome/微信)只给打开按钮、不给 trash_paths。按钮下方会自动写明注意事项(打开只查看不删、移废纸篓可逆需清空才释放等);如果某项在文件管理器里是 App 内部格式、不方便手动挑选,给它一个open_note字段做客观说明(会显示在注意事项里)。口吻要中性、像产品说明:直接描述"这里是什么结构、为什么不好手动删、想精细操作该去哪",不要写成"我发现/提醒注意/看着像没视频"这种暴露开发者踩坑视角的话。 - 🔴 谨慎清理(有决策但不建议手删):你可能想动、但建议别手删的具体项——重复安装的应用、想卸载的大应用、运行中应用的核心数据等。给"为什么不建议手删" +
indirect_release写具体卸载步骤(自带卸载器 / 启动台长按 / 右键移废纸篓 / AppCleaner 清残留 / App Store 可重装等,要可照做不是空话)。应用项给app_paths(真实.app绝对路径数组)→ 网页出现「在文件管理器打开(去卸载)」按钮,定位到 App 让用户自己正规卸载。红灯不给删除/卸载按钮(应用在系统目录、可能要管理员密码、可能有自带卸载器和残留,后台代删不稳妥)。纯系统文件、APFS 快照不要单独列红卡(没有清理决策),归蓝色即可;系统层面的释放技巧(重启释 swap、Time Machine 快照策略、可清除空间自动回收)写进summary.long_term长期建议。
What ships with it
9 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.
- 9d ago First seen · 120 lines · 334 tokens per session scan B 270fdf1bf08d
storage-analyzer is a skill published in the GitHub repository Mizoreww/awesome-claude-code-config (258 stars, last pushed 5d ago), licensed MIT. It adds 334 tokens to every session and 4,383 once invoked, about $0.0017 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…