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 mtarcure/claude-vibe-squad --skill disk-cleanupgit clone --depth 1 https://github.com/mtarcure/claude-vibe-squadWrote 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/mtarcure/claude-vibe-squad/disk-cleanup)<a href="https://agentmods.dev/skills/mtarcure/claude-vibe-squad/disk-cleanup"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/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/mtarcure/claude-vibe-squad/disk-cleanup"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/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 | $0.00092 | $0.01917 |
| Opus 5.5 | $0.00037 | $0.00767 |
| Sonnet 5.5 | $0.00018 | $0.00383 |
| Haiku 4.5 | $0.00009 | $0.00192 |
Grade A, and why
disk-cleanup 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 yesterday.
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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Disk cleanup (measure first, then reclaim in tiers)
This skill measures reclaimable pools, then reclaims the safe ones in tiers.
One command does the survey and the apply; it is dry-run by default and deletes
nothing until you pass an apply flag.
When to run
- Session start, and before any build, release, or large-media job.
- Whenever free space is under 40 GB (survey) — act before the 25 GB floor where board builds and media jobs start failing.
- After a burst of board lanes, which leave worktrees,
/tmp/vssandboxes, and caches behind.
1. Measure first — never delete blind
bin/disk-hygiene.sh --plan # full survey + sized plan, deletes NOTHING
--plan prints: APFS container free, staged-update (Preboot) allocation, board
worktrees, the rescued-artifact archive, Chrome clones, the test-Postgres
cluster, the top temp allocations, vault snapshots, docker usage, and the
rescued regenerable-bulk plan. Read it before applying anything. For a raw look:
diskutil apfs list # container free vs ceiling
df -Pk /System/Volumes/Data | tail -n1 # data-volume Available (KiB)
du -sh /private/tmp/* 2>/dev/null | sort -h | tail # tmp hogs
du -sh ~/vault-snapshots/* 2>/dev/null | sort -h # snapshot pile
docker system df # image/container space
2. Tiered reclaim
bin/disk-hygiene.sh --apply-safe # Tier 1 only
bin/disk-hygiene.sh --apply-preserve # Tier 1 + Tier 2
Tier 1 — automatic & safe (--apply-safe). Regenerable or settled only:
- Settled board worktrees (preserve-first via
prune-board-worktrees.sh) and their/tmp/vssandboxes + codex-homes — only when the owning attempt is terminal, not live-referenced, andlsof-idle. - Chrome
code_sign_clone.*, recognised/tmplane caches/scratch older than 12 h, idle per-run test databases older than 6 h, andVACUUM FULLof a bloated idle configured base test database. Direct children of/private/tmp/chrono-scratch/use a 48 h idle TTL; the container stays. - Tool versions (explicit Tier 1): Codex daemon releases keep the
~/.codex/packages/app-server-daemon/currenttarget plus the newest other release by mtime. Claude versions keep the~/.local/bin/claudetarget plus the newest other version.psandlsofmust prove every removed version idle, including mapped binaries. Missing/broken active links or failed censuses retain versions. These pools run only on explicit plan/apply paths. - Vault snapshots: keep the newest 3, delete older tarballs in
~/vault-snapshots. - Docker/colima: prune dangling (untagged) images + stopped containers that
exited over 24 h ago, then
colimafstrim. Neversystem prune -a, and never a container prune while any container is running (a running container means board/release work may be in flight).
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.
- yesterday First seen · 140 lines · 92 tokens per session scan A 1b04d3af009d
disk-cleanup is a skill published in the GitHub repository mtarcure/claude-vibe-squad (211 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 1,917 once invoked, about $0.0004 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 2026-10-29.
Other skills, from other repositories
gmail
Search, read, draft, and send Gmail when the user asks to work with their inbox or email.
google-calendar
Read schedules, check availability, and create or update Google Calendar events when the user asks to work with their calendar.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
openrig-herdr
Use when opening OpenRig fleet terminals as a herdr wall — turning a rig, pod, mission, slice, or saved view into live interactive agent tiles via rig terminal, watching another rig read-only, or driving herdr on an agent's request ("open all my rigs + a mission as views"). Covers the rig terminal open|views|status…
mission-slice-sop
Use when starting, building, handing off, restoring, or closing a mission or slice under the default lightweight SDLC.
claude-code-expert
Especialista profundo em Claude Code - CLI da Anthropic. Maximiza produtividade com atalhos, hooks, MCPs, configuracoes avancadas, workflows, CLAUDE.md, memoria, sub-agentes, permissoes e integracao com ecossistemas.