agentmods.dev

janitor

janitor is a command for Claude Code from MSApps-Mobile/claude-plugins. It costs 23 tokens per session (307 once invoked), scanned A, original, MIT.

A command for cleaning safe-to-remove clutter from Claude's data folder, including old backups, empty session folders, stale cache files, and transcripts for projects that no longer exist.

In plain words
What is it for?
Use `/janitor` for a dry run and `/janitor apply` only when you want to delete exactly the listed items.
Why use it?
It shows what could be removed before deleting anything, helping free disk space without manually searching through the folder.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claude-folder-janitor plugin — 1 skill, 1 command shipped together

not rated 10repo yesterday A scan 23 tokens original MIT

Good fit Use /janitor for a dry run and /janitor apply only when you want to delete exactly the listed items.

Compare 6 commands from other repositories ↓
View source ↗ MSApps-Mobile/claude-plugins msapps.mobi
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add MSApps-Mobile/claude-plugins
Claude Code
/plugin install claude-folder-janitor

Made for: Claude Code.

Or install claude-folder-janitor, the plugin that ships this one along with the rest of its 1 skill, 1 command.

Wrote 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.

agentmods badge for janitor

README.md
[![agentmods](https://agentmods.dev/badge/commands/msapps-mobile/claude-plugins/janitor/github.svg)](https://agentmods.dev/commands/msapps-mobile/claude-plugins/janitor)
Your own site
<a href="https://agentmods.dev/commands/msapps-mobile/claude-plugins/janitor"><img src="https://agentmods.dev/badge/commands/msapps-mobile/claude-plugins/janitor/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.

agentmods 80×15 button for janitor

Your own site · 80×15
<a href="https://agentmods.dev/commands/msapps-mobile/claude-plugins/janitor"><img src="https://agentmods.dev/badge/commands/msapps-mobile/claude-plugins/janitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 307 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00023 $0.00307
Opus 5.5 $0.00009 $0.00123
Sonnet 5.5 $0.00005 $0.00061
Haiku 4.5 $0.00002 $0.00031

Measured 10d ago against content hash 3f348318e7c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

janitor 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 10d 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.

plugins/claude-folder-janitor/commands/janitor.md · 30 lines

What it actually says

Run the janitor script. The text the user typed after /janitor is data, never shell input: do not paste it, or any part of it, into a command.

  • If that text is exactly apply (nothing before or after it), run this command and nothing else:
bash "${CLAUDE_PLUGIN_ROOT}/scripts/janitor.sh" apply
  • For anything else, including no text at all, run this command and nothing else (the dry run):
bash "${CLAUDE_PLUGIN_ROOT}/scripts/janitor.sh"

Each output line is rule<TAB>KB<TAB>path<TAB>reason, followed by one summary line.

  • Dry run: group the candidates by rule (backup, session-env, changelog, orphan) and show for each rule the count, the total size and up to five example paths with their reasons. End with the reclaimable total and say that /janitor apply deletes exactly this list.
  • Apply: report removed, failed, the space freed and the elapsed time from the summary line. If anything failed, show those lines from stderr.

Never run apply unless the user typed it. Do not delete anything by hand that the script did not list.

Changes

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.

  1. 10d ago First seen · 30 lines · 23 tokens per session scan A 3f348318e7c4

Subscribe to this mod's changes

janitor is a command published in the GitHub repository MSApps-Mobile/claude-plugins (10 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 307 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 2026-10-27.

Claude CodeProductivityagent-safetyai-agentsai-governanceclaudeclaude-plugins
Related

janitor compared with commands from other repositories

janitor next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
janitorMSApps-Mobile/claude-pluginsCommand10yesterdayMITA23Claude Code
listAbilityai/trinityCommand741yesterdayApache-2.0A0Claude Code
pauseAbilityai/trinityCommand741yesterdayApache-2.0A0Claude Code
execute-parallel-cleanupai-sdlc-framework/ai-sdlcCommand434yesterdayApache-2.0A40Claude Code
searchtractorjuice/arc-kitCommand2.3k2d agononeA14Claude Code
starttractorjuice/arc-kitCommand2.3k2d agononeB16Claude Code
working-contexts977043/PlanGateCommand3yesterdayMITA0Claude Code