janitor-claude SKILL.md skillB
janitor-claude from arshiaecho/janitor is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add arshiaecho/janitor/janitor-claude@git:20261104.53a09bbPins git:20261104.53a09bb in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- arshiaecho/janitor
- Path
plugins/janitor/skills/janitor-claude/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261104.53a09bb, committed Nov 4, 2026
- First version recorded
- Apr 13, 2026
- Size
- 30,974 bytes
- Repository stars
- 6
- License
- MIT
Audit and clean up a Claude Code working directory or Obsidian vault. Use this skill when the user asks to "clean up my session", "clean this directory", "tidy this up", "audit my CLAUDE.md", "is my CLAUDE.md stale", "scaffold a CLAUDE.md", "find broken wiki-links", "find dead files", "find orphaned notes", "what's wasting tokens in this repo", "what's slowing Claude down in here", "clean up this vault", "find cruft", "find .DS_Store files", "find stale branches", "clean up my .claude folder…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# janitor-claude A read-first audit of the current working directory. Finds clutter, broken links, stale or overlapping instruction files (`CLAUDE.md`, `AGENTS.md`, `CLAUDE.local.md`, `.claude/rules/`), broken Claude Code config (settings, hooks, `.mcp.json`, skills, agents), stale worktrees, and token-wasting patterns — then asks the user per-fix before doing anything. On request it also measures user-level `~/.claude` weight. **Last verified:** 2026-11, against code.claude.com/docs (memory, settings, permissions, hooks, mcp, skills, sub-agents, worktrees, claude-directory, plugins/loading, costs) and the Claude Code changelog through v2.1.318. Paths and limits cited here come from those pages; re-verify before changing them. ## How to use this You don't need to remember any commands. The skill triggers automatically when you describe your problem: > "clean up this directory" > "audit my CLAUDE.md" > "find broken wiki-links in this vault" > "Claude keeps re-reading the same files, what's going on" > "/janitor-claude" …
Read the whole file at its exact version.
How to install
mdr add arshiaecho/janitor/janitor-claude@sha256:77fe30ed2b689aafThe line at the top of this page pins the label git:20261104.53a09bb, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_e573avcis3a5amvz)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Apr 13, 2026 and Nov 4, 2026, about one every 51 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261104.53a09bb latest | 2026-11-04 | 53a09bb | 30,974 B | B | view · diff |
| git:20261104.db9f76f | 2026-11-04 | db9f76f | 30,516 B | B | view · diff |
| git:20260611.74b4201 | 2026-06-11 | 74b4201 | 23,935 B | B | view · diff |
| git:20260413.1cccbdd | 2026-04-13 | 1cccbdd | 19,273 B | B | view · diff |
| git:20260413.924cc81 | 2026-04-13 | 924cc81 | 22,498 B | B | view |
Audit of the latest version
- fail: No curl or wget piped into a shell (matched: curl | bash)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (30974 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
arshiaecho/janitor · 6 stars · license MIT · pushed 2026-11-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_e573avcis3a5amvz GET https://markdownregistry.com/api/v1/resolve?ref=arshiaecho/janitor/janitor-claude GET https://markdownregistry.com/api/v1/blob/77fe30ed2b689aaf1d08f0340be0b13e06c210dd87d5f033485b07885bdc0bde
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.