clean

clean is a skill for Claude Code, Codex from andalabx/skills. It costs 77 tokens per session (4,005 once invoked), scanned C, original, MIT.

A cleanup tool for removing common development leftovers from a computer, such as temporary files, caches, build folders, and installed package folders.

In plain words
What is it for?
Use it to run a standard cleanup on Windows, macOS, or Linux, or to scan for larger hidden space users and approve items before deletion.
Why use it?
It helps recover disk space that has been consumed by development tools and files that are usually safe to recreate.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/andalabx/skills/clean
Any agent
npx skills add andalabx/skills --skill clean
Clone the repo
git clone --depth 1 https://github.com/andalabx/skills

Made for: Claude Code, Codex.

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 clean

README.md
[![agentmods](https://agentmods.dev/badge/skills/andalabx/skills/clean.svg)](https://agentmods.dev/skills/andalabx/skills/clean)
Your own site
<a href="https://agentmods.dev/skills/andalabx/skills/clean"><img src="https://agentmods.dev/badge/skills/andalabx/skills/clean.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,005 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
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 $0.00077 $0.04005
Opus 5 $0.00039 $0.02003
Sonnet 5 $0.00015 $0.00801
Haiku 4.5 $0.00008 $0.00400

Measured 4d ago against content hash 7cb34cae4812, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

clean scanned grade C 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 4d 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 deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "$TMPDIR/claude/"* 2>/dev/null
clean/SKILL.md · 466 lines

How it starts

The opening of the file, as written. The whole thing — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/clean — Dev Environment Cleanup

Frees disk space across your dev environment. Works on Windows, macOS, and Linux.

Arguments: $ARGUMENTS

  • (none) — ask the user whether they want Quick or Super mode
  • quick — full standard cleanup, no questions asked
  • super — interactive deep-clean: discovers everything, user approves before anything is deleted

No Argument — Ask First

If no argument is given, ask the user before doing anything:

How would you like to clean?

  quick — fast cleanup of known junk (caches, temp, node_modules, builds)
          no questions, runs immediately

  super — deep scan of everything on your system, ranked by size
          you decide what goes and what stays before anything is deleted

Type "quick" or "super":

Wait for their answer, then proceed to the matching mode below.


Quick Mode (/clean quick)

Rule: always measure size BEFORE deleting. Never delete first and report after — sizes will be wrong or unavailable.


Step 0 — Detect environment

Run these two commands and record the values for use in every step below:

uname -s 2>/dev/null || echo "Windows"
echo $HOME

Resolve OS-specific variables:

  • Windows: HOME=$USERPROFILE, TMPDIR=$LOCALAPPDATA/Temp, APPDATA, LOCALAPPDATA
  • macOS: HOME=$HOME, TMPDIR=$TMPDIR
  • Linux: HOME=$HOME, TMPDIR=/tmp

Project roots to scan (use whichever exist): $HOME/Documents, $HOME/Projects, $HOME/code, $HOME/dev, current directory

Record baseline disk free now — use this exact command, once, and store the result:

df -h / 2>/dev/null || df -h "$HOME"

Step 1 — Claude temp dir

Measure size first using du, then delete contents:

# measure
du -sh "$TMPDIR/claude" 2>/dev/null || echo "0"

# delete contents only, not the directory itself
rm -rf "$TMPDIR/claude/"* 2>/dev/null

Use the du result as the reported size — do not try to read output after deletion, the file may be gone.


Read the full file on GitHub · 466 lines

Files

What ships with it

1 file 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.

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. 4d ago First seen · 466 lines · 77 tokens per session scan C 7cb34cae4812

Subscribe to this mod's changes

clean is a skill published in the GitHub repository andalabx/skills (2 stars, last pushed 15d ago), licensed MIT. It adds 77 tokens to every session and 4,005 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C 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.

Related

Other skills, from other repositories

adhd

Formats output for ADHD-friendly action — lead with the next step, number tasks, restate state, cut fluff. Use when named (adhd), when the user mentions ADHD or focus/executive-function constraints, or when they ask for steps they can execute immediately.

nateslabach/skills · 57 tokens

peon-ping-toggle

Toggle peon-ping sound notifications on/off. Use when user wants to mute, unmute, pause, or resume peon sounds during a Claude Code session. Also handles config changes like volume, pack rotation, categories — any peon-ping setting.

PeonPing/peon-ping · 58 tokens

peon-ping-log

Log exercise reps for the Peon Trainer. Use when user says they did pushups, squats, or wants to log reps. Examples - "/peon-ping-log 25 pushups", "/peon-ping-log 30 squats", "log 50 pushups".

PeonPing/peon-ping · 64 tokens

linkedin-job-scraper

Scrapes LinkedIn job postings using the JobSpy library (python-jobspy). Use this skill whenever the user wants to find jobs on LinkedIn, search for open roles, pull job listings, build a job pipeline, source job targets for GTM research, or monitor hiring signals. Even if the user just says "find me some jobs" or…

gooseworks-ai/goose-skills · 121 tokens

planning-with-files

Persistent file-based planning for multi-step AI-agent work. Keeps taskplan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and…

mxyhi/ok-skills · 117 tokens

save-progress

Save current project task progress to local task state file for cross-session continuity. Use when the user asks to save progress, uses an equivalent localized trigger phrase, the session is interrupted, or the user wants to resume work later. Writes to .claude/project-task-state.json so next session can load it via…

KimYx0207/Meta_Kim · 65 tokens