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 agentmods add commands/arshiaecho/janitor/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/commands/arshiaecho/janitor/janitor-claude)<a href="https://agentmods.dev/commands/arshiaecho/janitor/janitor-claude"><img src="https://agentmods.dev/badge/commands/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 | $0.00033 | $0.00161 |
| Opus 5 | $0.00016 | $0.00081 |
| Sonnet 5 | $0.00007 | $0.00032 |
| Haiku 4.5 | $0.00003 | $0.00016 |
Grade B, and why
janitor-claude scanned grade B with 1 finding 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 5d 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Load and run the `janitor-claude` skill on the current working directory. Walk the full five-phase workflow: diagnose read-only → identify villains (missing/stale CLAUDE.md, broken wiki-links, orphaned cruft, oversized f Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
What it actually says
Load and run the janitor-claude skill on the current working directory. Walk the full five-phase workflow: diagnose read-only → identify villains (missing/stale CLAUDE.md, broken wiki-links, orphaned cruft, oversized files) → present findings with specific file paths → fix only after per-item confirmation (move-to-Trash, never rm -rf; diff-gated CLAUDE.md edits; per-link wiki-link fixes) → verify with a before/after count table and close with a custom analogy. Never runs destructive git. Never overwrites CLAUDE.md.
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.
- 5d ago First seen · 7 lines · 33 tokens per session scan B 208091a6051d
janitor-claude is a command published in the GitHub repository ArshiaEcho/janitor (6 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 161 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
config
Configure iterm2-tab-status plugin settings (emoji prefixes, colors, display target, subtitle activity, badge, notifications).
on
Enable Audio Recap for this Claude Code session.
speak
Read your immediately preceding response aloud — local mode (verbatim, mechanical) or llm mode (LLM-written spoken summary).
speak-limit
Get, set, or reset the max byte length spoken before truncating at a sentence boundary.
yank
Copy the last Claude response to clipboard.
paste
Paste text or rich content via peekaboo paste.