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 ArshiaEcho/janitor --skill janitor-claudegit clone --depth 1 https://github.com/ArshiaEcho/janitorWrote 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/arshiaecho/janitor/janitor-claude)<a href="https://agentmods.dev/skills/arshiaecho/janitor/janitor-claude"><img src="https://agentmods.dev/badge/skills/arshiaecho/janitor/janitor-claude.svg" alt="Measured on agentmods" 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 | $0.00219 | $0.06231 |
| Opus 5 | $0.00110 | $0.03116 |
| Sonnet 5 | $0.00044 | $0.01246 |
| Haiku 4.5 | $0.00022 | $0.00623 |
Grade C, and why
janitor-claude scanned grade C with 3 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 7d 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.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- **No obfuscated commands.** No base64, no `curl | bash`, no minified one-liners. Every command is plaintext and readable. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Claude walks the directory read-only, identifies 3-5 specific villains, shows you what it found, and asks permission per-fix. Nothing is mutated without explicit consent. Everything is reversible (files go to Trash, neve Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **No network calls.** No `curl`, `wget`, `Invoke-WebRequest`, `Invoke-RestMethod`. No version-check pings, no GitHub API calls, no telemetry. Offline-only. How it starts
The opening of the file, as written. The whole thing — 406 lines — stays where its author put it; the contents beside it link to each section on GitHub.
janitor-claude
A read-first audit of the current working directory. Finds clutter, broken links, stale CLAUDE.md facts, and token-wasting patterns — then asks the user per-fix before doing anything.
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"
Claude walks the directory read-only, identifies 3-5 specific villains, shows you what it found, and asks permission per-fix. Nothing is mutated without explicit consent. Everything is reversible (files go to Trash, never to rm -rf).
Philosophy
A messy Claude Code working directory has the same underlying pattern as a slow Mac: 3-5 specific villains, not some general decay. The difference is that on a working directory, every mutation risks destroying in-progress work. So the defaults are much stricter:
- Read-only by default. Diagnostics walk the filesystem and git state without writing anything.
- Only machine-generated cruft can be batch-cleaned.
.DS_Store,__pycache__, broken symlinks — these have no information content. Everything else requires a per-item ask. - Never rewrites user-authored files. Not
CLAUDE.md, not a markdown note, not a config file. Never wholesale, never silently. - Never runs destructive git. No
git add,git rm,git commit,git push,git reset,git branch -D,git clean. Read-only git only.
If the janitor-device philosophy is "the user's machine has villains and we can disable them together," the janitor-claude philosophy is "the user's working directory has clutter and we can catalog it together, then let them decide."
Personality and voice
Janitor is warm, cheerful, observational, and unfazed. Not a stern linter or a sterile audit tool — more like the friendly librarian who knows where everything is, isn't surprised by a messy desk, and will quietly help put things back in order if you ask. Lead every reply with 🧹 to signal Janitor's arrival, and let tidying metaphors run gently through the whole response. Janitor is someone the user wants to come back to.
What ships with it
5 files 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.
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.
- 7d ago First seen · 406 lines · 219 tokens per session scan C ef484e638227
janitor-claude is a skill published in the GitHub repository ArshiaEcho/janitor (6 stars, last pushed 2mo ago), licensed MIT. It adds 219 tokens to every session and 6,231 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it C with 3 findings (downloads and executes remote code, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
i-have-adhd
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".
storage-analyzer
A read-only disk-space scanner for macOS and Windows that groups files into categories such as caches, personal data, and files to keep. It produces an HTML report with commands you can review before cleanup.
avatar-contribution-pr
Turn an avatar GitHub issue (from the in-app avatar-editor easter egg) into a merged sprite — validate the art, then either add a new module or replace an existing one, and open a PR that closes the issue. Handles both "Avatar contribution: " (a brand-new sprite) and "Avatar edit: " (a hand-redraw of an existing…
sitrep-panel
Keep a live local HTML report updated as you work on a task — a status board, a running "what's happening now" narrative, screenshots, and a newest-first log — served on localhost so the user can watch progress in a browser tab instead of reading the transcript. Use when the user invokes /sitrep-panel, asks for a…
git-workflow
Use when starting feature work that needs a branch, creating worktrees for isolation, making atomic commits during development, or completing a development branch via merge, PR, preserve, or discard. Also use when the user says "set up worktree", "create PR", "finish this branch", "start feature", or when you need an…
parallel-dispatch
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies. Also use when multiple test files fail with different root causes, multiple subsystems are broken independently, or you want agents to work concurrently on separate problem domains. If tasks touch different…