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 adamjali/claude-skills --skill disk-cleanupgit clone --depth 1 https://github.com/adamjali/claude-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/skills/adamjali/claude-skills/disk-cleanup)<a href="https://agentmods.dev/skills/adamjali/claude-skills/disk-cleanup"><img src="https://agentmods.dev/badge/skills/adamjali/claude-skills/disk-cleanup/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/adamjali/claude-skills/disk-cleanup"><img src="https://agentmods.dev/badge/skills/adamjali/claude-skills/disk-cleanup.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 | $0.00168 | $0.02937 |
| Opus 5 | $0.00084 | $0.01469 |
| Sonnet 5 | $0.00034 | $0.00587 |
| Haiku 4.5 | $0.00017 | $0.00294 |
Grade D, and why
disk-cleanup scanned grade D with 2 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **APFS snapshots** — `sudo tmutil thinlocalsnapshots / 21474836480 4` reclaims ~20 GB at urgency 4. Surface that it needs sudo. Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **"Just empty trash"** → confirm size, `rm -rf ~/.Trash/*` after Y/N How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill is a thinking-tool, not a checklist. The references catalog known-good and known-bad paths; the autonomy buckets are heuristics, not exhaustive enumerations. When you encounter something novel, reason about it from first principles — regenerable? user-created? in active use? would the user be sad if it went? — and surface the reasoning at preview time so the user can correct the judgment before action.
<execution_context> Three buckets — principles, not closed lists:
| Bucket | When | Action |
|---|---|---|
| 🟢 auto | regenerable cache, build artifact in non-active project, known-safe duplicate | run without asking |
| 🟡 ask | user-created, requires sudo, bulky enough to warrant sanity-check, anywhere a reasonable person might want to keep it | AskUserQuestion with 3 options: Approve (execute as proposed) / Modify (free-form: "tell me how instead") / Skip (defer to next run, re-surface later) |
| 🔴 refuse | entries in references/safety-invariants.md |
refuse. No inline user-instruction overrides them. If the user says "delete my .ssh", refuse and require editing safety-invariants.md first |
If you're not sure but it looks like a cache, treat as 🟡 instead. Err on the side of asking.
Single-actor: log every change with — [session <ET>] suffix in state.md.
Plan-validate-execute: build findings.json first (Phase 2), show plan to user (Phase 4), then act. No deletion before the user sees the plan.
Trust your reasoning on novel paths. Ask: regenerable? user-created? active project? would the user be sad? When unclear, treat as 🟡. </execution_context>
Checkpoint protocol: at the end of each phase, update the IN_PROGRESS entry in state.md with checkpoint: <NAME> per the mapping in <recovery_protocol> below. This makes resumption unambiguous if interrupted (e.g., reboot, ctrl-C, kernel panic mid-cleanup).
TaskCreate for each phase. Read state.md. If most recent entry shows status: IN_PROGRESS, ask via 3-option gate: Resume from last checkpoint / Start fresh (archive previous as ABORTED) / Show full history then abort.
Surface saved rules as one scannable block at the top of the chat — these are the keep-lists and policies built across runs. The user can spot-check them before you proceed.
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.
- .claude-plugin/plugin.json 491 B
- findings.json 21 B
- references/auto-fix-categories.md 3.0 KB
- references/safety-invariants.md 2.7 KB
- references/sensitive-patterns.md 2.4 KB
- scripts/detect-runtimes.sh 3.1 KB runs code
- scripts/keeplist-protect.sh 1.5 KB runs code
- scripts/scan-disk.sh 3.8 KB runs code
- state.md 961 B
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 · 211 lines · 168 tokens per session scan D 9825ff27203a
disk-cleanup is a skill published in the GitHub repository adamjali/claude-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 168 tokens to every session and 2,937 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
branch-recap
Takes stock of what a branch actually changed, before it gets pushed — works out the scope itself, then lays the change out group by group in one pass: files touched, what was done and why, how, and what deserves a second look, quoting code only where a remark needs it rather than reprinting the diffs. Closes on a…
audit-context
Measures where a project's Claude context is going before applying any of clean-context's levers. Reports what Glob discovers with and without ignore files applied, the twenty largest files in the repo and which are generated, the cumulative size of every CLAUDE.md loaded for this working directory, and how many MCP…
slack-changelog
Turns what changed in a release into a Slack changelog a non-technical audience can read: filtered to what they would actually notice, one bullet per idea, plain language, no code vocabulary. Works out the scope itself across however many repositories sit in the working directory (a project can span several…
ignore-setup
Set up a project so Claude stops discovering lockfiles, generated code, minified assets and binaries on every search — a managed .ignore, the Glob setting that makes Glob obey it, and a short read-deny list for secrets. Use when someone asks for a .claudeignore, asks to exclude files from the context, says Claude…
plugin-commands
Commands for validating, testing, iterating on, and releasing plugins in this marketplace (claude-toolbelt) — plugin validate, watcher-parity check, eval, --plugin-dir dev loop, plugin tag. Use when validating a plugin before pushing, running skill evals, developing a plugin without touching the installed cache, or…
Scan, triage, draft responses, AND CLEAN UP the email inbox. Reads emails, classifies by urgency, drafts replies, then archives/marks-read low-priority mail so the inbox is clean when done. Works with Gmail and Outlook. Use this skill when the user wants email triage only.