mac-cleanup

mac-cleanup is a skill for Claude Code, Codex from MSApps-Mobile/claude-plugins. It costs 0 tokens per session (1,833 once invoked), scanned D, original, MIT.

A Mac cleanup workflow that measures available storage, clears specified safe cache locations, reports the space freed, and flags unusually large folders for review.

In plain words
What is it for?
For responding to a full or slow Mac by cleaning selected caches and identifying folders that may need further attention.
Why use it?
It provides before-and-after storage information and keeps potentially important large folders for manual checking.

Skill for Claude CodeCodex

Part of the mac-disk-cleaner plugin — 2 skills shipped together

Install

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.

agentmods
npx agentmods add skills/msapps-mobile/claude-plugins/mac-cleanup
Any agent
npx skills add MSApps-Mobile/claude-plugins --skill mac-cleanup
Clone the repo
git clone --depth 1 https://github.com/MSApps-Mobile/claude-plugins

Made for: Claude Code, Codex.

Or install mac-disk-cleaner, the plugin that ships this one along with the rest of its 2 skills.

Wrote 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.

agentmods badge for mac-cleanup

README.md
[![agentmods](https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/mac-cleanup.svg)](https://agentmods.dev/skills/msapps-mobile/claude-plugins/mac-cleanup)
Your own site
<a href="https://agentmods.dev/skills/msapps-mobile/claude-plugins/mac-cleanup"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/mac-cleanup.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,833 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01833
Opus 5 $0.00000 $0.00916
Sonnet 5 $0.00000 $0.00367
Haiku 4.5 $0.00000 $0.00183

Measured 3d ago against content hash d4ae10f41bdd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

mac-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 3d 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.

3. **Any errors** — caches that couldn't be cleaned and why (e.g. "node-gyp: permission denied — can be removed with sudo if needed")

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf ~/Library/Caches/Google/ 2>/dev/null; true
plugins/mac-disk-cleaner/skills/mac-cleanup/SKILL.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mac Disk Cleanup

Clean up safe Mac cache locations, report how much space was freed, and flag any oversized folders worth reviewing manually.

Use this skill when the user says things like: "clean my Mac", "free up disk space", "clear cache", "my Mac is slow", "running out of space", "Mac cleanup", "disk cleanup", "tidy up my Mac", "ניקוי מק", "פנה מקום", "המק שלי מלא", "nettoyage Mac", "limpiar Mac", or any similar request about freeing storage on a Mac.

Also runs automatically when triggered as a scheduled task.


How to run this skill

Work through each phase in order. Communicate with the user in whatever language they used.

Environment note: This skill works in both Claude Code (native Bash tool) and Cowork (Desktop Commander). Use whichever shell execution method is available in your environment to run the bash commands below.


Phase 1 — Measure before

Run these two commands and record the results:

df -h / | tail -1
du -sh \
  ~/Library/Caches/Google/ \
  ~/Library/Caches/pip/ \
  ~/Library/Caches/node-gyp/ \
  ~/Library/Caches/org.swift.swiftpm/ \
  ~/.gradle/caches/ \
  ~/Library/Caches/Homebrew/ \
  2>/dev/null

Note the "Avail" column from df as before_avail and record each cache size.


Phase 2 — Clean

Run each command. If a command fails (permission denied, not found), note it and continue — do not abort.

# Google Chrome disk cache (passwords/history/bookmarks are in Application Support, NOT here — safe to delete)
rm -rf ~/Library/Caches/Google/ 2>/dev/null; true
# npm cache
npm cache clean --force 2>/dev/null; true
# Yarn cache
yarn cache clean 2>/dev/null; true
# pip cache
rm -rf ~/Library/Caches/pip/ 2>/dev/null; true
# Swift Package Manager cache (auto-regenerated on next build)
rm -rf ~/Library/Caches/org.swift.swiftpm/ 2>/dev/null; true
# Gradle caches (auto-regenerated on next build)
rm -rf ~/.gradle/caches/ 2>/dev/null; true

Read the full file on GitHub · 187 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 3d ago First seen · 187 lines · 0 tokens per session scan D d4ae10f41bdd

Subscribe to this mod's changes

mac-cleanup is a skill published in the GitHub repository MSApps-Mobile/claude-plugins (9 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,833 tokens. 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.

Related

Other skills, from other repositories

collab-conflict

까다로운 동료·소통빌런과 부딪힐 때 감정 상하지 않게 대응하고 거리를 지키도록 도와주는 스킬입니다. '이 사람 어떻게 대하지', '자꾸 떠넘기는 동료', '거절하는 법', '직장 인간관계 스트레스', '갈등 대응'처럼 말하면 됩니다. 유형별 대응 전략, 감정과 사안 분리, 정중한 거절, 관계 거리 두기로 직장 갈등을 소모전이 아니라 관리 가능한 문제로 바꿉니다.

modu-ai/moai-cowork · 126 tokens

collab-negotiation

1:1 면담을 준비하고, 상대를 설득하거나 무언가를 요청·협상할 때 대화를 설계해 주는 스킬입니다. '면담 준비해줘', '이거 어떻게 설득하지', '연봉 협상 어떻게', '부탁하는 법', '정중하게 요청하고 싶어'처럼 말하면 됩니다. 면담 목표 설정 → 상대 입장 파악 → 설득 구조 → 요청·거절 화법 → 합의·후속의 5단계로 관계를 지키며 원하는 걸 얻는 대화를 만듭니다.

modu-ai/moai-cowork · 132 tokens

collab-feedback-loop

피드백을 건설적으로 주고, 받은 피드백을 감정 상하지 않게 소화하도록 도와주는 스킬입니다. '피드백 어떻게 줘야 해', '부정적 피드백 받았는데 속상해', '피드백 전달하는 법', '중간 점검 요청하고 싶어'처럼 말하면 됩니다. SBI 구조로 건설적 피드백을 설계하고, 받은 피드백을 사실과 감정으로 분리해 소화하며, 먼저 피드백을 요청하는 법까지 다룹니다.

modu-ai/moai-cowork · 127 tokens

collab-meeting

회의가 산으로 가지 않게 아젠다를 짜고 결론까지 끌고 가는 진행을 도와주는 스킬입니다. '회의 아젠다 짜줘', '이 회의 어떻게 진행하지', '회의가 자꾸 산으로 가', '의사결정 회의 준비', '회의록 정리'처럼 말하면 됩니다. 목적 정의 → 아젠다 설계 → 진행 규칙 → 의사결정 → 회의록·후속 액션의 5단계로 결론이 남는 회의를 설계합니다.

modu-ai/moai-cowork · 125 tokens

collab-productivity-report

직장에서 제출하는 주간업무보고를 빠르게 작성해주는 스킬입니다. '주간보고 작성해줘', '이번 주 한 일 정리', '주간업무보고', '팀장님께 보낼 보고', '한 주 업무 리뷰'처럼 말하면 됩니다. 한 주 성과·진행 중 일·이슈·다음 주 계획을 정해진 틀로 정리하고, 격식체/구어체 톤까지 맞춰 보고서 초안을 만들어줍니다.

modu-ai/moai-cowork · 118 tokens

agentic-os-obsidian

Set up an agentic OS inside an Obsidian vault — a configurable command-center dashboard with 5 auto-installed, bundled plugins (Dataview, CustomJS, Shell-commands, Terminal, Homepage), Home + per-profile + Vault Overview pages, KPI cards, sparklines, heatmap, task rollup, and a button bar wired to user-defined Claude…

naveedharri/benai-skills · 154 tokens