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.
git 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-device)<a href="https://agentmods.dev/commands/arshiaecho/janitor/janitor-device"><img src="https://agentmods.dev/badge/commands/arshiaecho/janitor/janitor-device/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/arshiaecho/janitor/janitor-device"><img src="https://agentmods.dev/badge/commands/arshiaecho/janitor/janitor-device.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00026 | $0.00109 |
| Opus 5.5 | $0.00010 | $0.00044 |
| Sonnet 5.5 | $0.00005 | $0.00022 |
| Haiku 4.5 | $0.00003 | $0.00011 |
Grade A, and why
janitor-device scanned grade A with 0 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 1mo 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Load and run the janitor-device skill on the current machine. Detect the OS first, then walk the full five-phase workflow: diagnose → identify villains → present findings and ask for permission → fix (with copy-paste admin blocks for anything elevated) → verify with a before/after table and close with a custom analogy. Every mutation requires explicit user confirmation. Everything is reversible.
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.
- 1mo ago First seen · 7 lines · 26 tokens per session scan A c7a4271a4bb8
janitor-device is a command published in the GitHub repository ArshiaEcho/janitor (6 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 109 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. 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).
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.
orchestrate
Do this task as an orchestrator. The aim is the same result at a fraction of the cost: in a long session, every token in this conversation is re-read on each later request, while a subagent's reading is discarded when it returns. The plugin's subagents run on Haiku 5.5, about 40× cheaper per token than Opus 5.5.
scout-meta-review
Run an interactive Scout meta-review — a system-level audit that sits above the individual session types. Checks whether sessions are running, mistake audit is trending well, proposals are flowing, KB files are healthy, and data-source coverage is consistent across session types. Runs in the current conversation.
agent-triage
Find and triage Quickchat conversations that need a human.