agentleFS
jqaisystemsjqaisystems/jqai-ai-skills/skills/vault-janitor/SKILL.md

vault-janitor

Skill3 starsChanged 6 months agoMITView on GitHub

Scan a folder tree for accumulated junk (dependency folders, build caches, stray backups, log files, OS litter, duplicate copies) and produce a sized, grouped cleanup report. Report-only by default; it deletes nothing until you approve a specific list, and prefers moving to an archive over hard deletion. Use when the user says "clean up this folder", "what is taking all the space", "find the junk", or "vault cleanup".

  • Reads credentials

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never act on the whole report.

    line 40
  2. Distinctive:

    Prefer moving to a dated archive folder (or the system recycle bin) over hard deletion.

    line 43
  3. Distinctive:

    After cleaning, re-report the headline numbers so the result is visible.

    line 45
  4. Very specific:

    Never touch live .git repositories, .env files, or anything flagged "verify before touching" without the user resolving the flag.

    line 50
  5. Distinctive:

    If something looks like the only copy of user-created work (documents, designs, photos), it is not junk no matter where it sits.

    line 52

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Vault Janitor

You find the junk that working folders accumulate: the node_modules inside an abandoned experiment, the _backup_final_v2 nobody remembers making, the 400 MB of logs. You report it with sizes and let the human decide. You delete nothing on your own.

This skill exists because of a real cleanup: a personal vault that had quietly grown to 325,000 files, of which roughly 290,000 were dependency folders, build caches, and nested backups. The scan is the easy part; the discipline is in what happens after, which is why the report comes first and the deleting comes last, if at all.

Step 1: Scan (read-only)

Take a target folder (default: current directory). Walk it and classify what you find into groups:

GroupPatterns
Dependency foldersnode_modules, venv, .venv, env, vendor, site-packages
Build caches__pycache__, .cache, dist, build, .next, .parcel-cache, *.pyc
Backup litterfolders/files matching *backup*, *_old, *_bk, * copy, *final_v*, dated duplicates of the same name, .zip/.rar siblings of an existing folder
Logs and temp*.log, *.tmp, *.err.log, *.out.log, crash dumps
OS litterThumbs.db, .DS_Store, desktop.ini
Heavyweightsany single file over 100 MB that fits no group above

Measure each group: file count and total size. Note the largest individual offenders.

Things that are NEVER junk, regardless of pattern: anything inside a .git directory that belongs to a live repo, .env files, anything the user's notes or README mark as deliberate, and any folder whose name suggests the user chose to keep it ("dont_delete", "keep", "archive" with a date and intent).

Step 2: Report

Produce cleanup-report.md in the target folder:

  1. Headline numbers: total files, total size, what percentage the junk groups represent.
  2. Per group: count, size, and the top 10 paths by size.
  3. Judgment calls: items that match a junk pattern but might be deliberate (a backup folder with recent edits, a zip with no sibling folder). These get a "verify before touching" flag, not a recommendation.
  4. Recommended actions, most space per least risk first. Dependency folders and caches lead (regenerable by definition); ambiguous backups come last.

Step 3: Clean (only with an approved list)

Never act on the whole report. The flow is:

  1. The user names which groups or paths to clean.
  2. Prefer moving to a dated archive folder (or the system recycle bin) over hard deletion. State where things went.
  3. Hard-delete only if the user explicitly chooses it, and confirm the exact path list once before running.
  4. After cleaning, re-report the headline numbers so the result is visible.

Rules

  • Report-only by default. No file is moved or deleted in a scan.
  • Never touch live .git repositories, .env files, or anything flagged "verify before touching" without the user resolving the flag.
  • One folder tree per run. No "clean the whole drive" sweeps.
  • If something looks like the only copy of user-created work (documents, designs, photos), it is not junk no matter where it sits. Flag it, never recommend deletion.
  • OneDrive and other sync folders: warn that deletions sync to the cloud and other devices before cleaning anything inside one.

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.