agentleFS
OutThisLifeOutThisLife/brooklyn-skills/skills/free-disk-space/SKILL.md

free-disk-space

Skill207 starsChanged 4 months agoMITView on GitHub

Safely reclaim disk space on macOS without touching personal or agent data. Use when the user asks to free disk space, clear caches, or investigate a nearly full Mac.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Never inspect, delete, or modify the data of the IDE or agent you're running inside — its application-support dir, caches, globalStorage, …

    line 15
  2. Distinctive:

    Never delete browser history, extensions, cookies, credentials, local storage, IndexedDB, bookmarks, passwords, or user-created files.

    line 20
  3. Distinctive:

    Ask before destructive cleanup such as deleting Docker images, containers, volumes, or virtual disks.

    line 22
  4. Very specific:

    Do not represent the sealed / system volume as the Mac's usable data-volume capacity.

    line 45

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Free Disk Space

Investigate first. Delete only regenerable data the user has authorized.

Safety

  • Never inspect, delete, or modify the data of the IDE or agent you're running inside — its application-support dir, caches, globalStorage, databases, extensions, or logs — unless the user explicitly names it as a cleanup target. On macOS that lives under ~/Library/Application Support/<app>/ (e.g. .../Cursor/).
  • Never delete browser history, extensions, cookies, credentials, local storage, IndexedDB, bookmarks, passwords, or user-created files.
  • Ask before destructive cleanup such as deleting Docker images, containers, volumes, or virtual disks.

Workflow

  1. Record current usage from the macOS data volume:

    df -h /System/Volumes/Data
  2. Find the largest consumers before deleting anything. Use du, package manager diagnostics, and application-specific storage commands. Do not descend into protected agent/IDE data.
  3. Explain what is large, whether it is regenerable, and the expected impact.
  4. Clean only safe targets:
    • contents of ~/Library/Caches/
    • unused package-manager cache entries, such as pnpm store prune
    • known browser model/GPU caches, never browser profile data
  5. For sparse files such as Docker's virtual disk, report actual disk use from du, not apparent size from ls.
  6. Record usage again and report space freed.

Do not represent the sealed / system volume as the Mac's usable data-volume capacity.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.