What is skill-cleaner?

A tool for checking a collection of coding-agent skills. It reports duplicates, unused skills, enabled or disabled skill folders, long descriptions, and the prompt space they consume.

Use it to audit skill folders, find skills that have not been used recently, compare similar skills, and estimate their prompt-budget cost.

Large or duplicated skill collections can waste context space and make it harder to manage what the agent can use. This gives you a report to guide cleanup.

skill-cleaner — Skill for Claude Code and Codex by iurysza/android-use

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.

Any agent

npx skills add iurysza/android-use --skill skill-cleaner

Clone the repo

git clone --depth 1 https://github.com/iurysza/android-use

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/iurysza/android-use/skill-cleaner/github.svg)](https://agentmods.dev/skills/iurysza/android-use/skill-cleaner)

Your own site

<a href="https://agentmods.dev/skills/iurysza/android-use/skill-cleaner"><img src="https://agentmods.dev/badge/skills/iurysza/android-use/skill-cleaner/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/iurysza/android-use/skill-cleaner"><img src="https://agentmods.dev/badge/skills/iurysza/android-use/skill-cleaner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 949 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.

Model	Per session	Once invoked
Fable 5.1	$0.00033	$0.00949
Opus 5.5	$0.00013	$0.00380
Sonnet 5.5	$0.00007	$0.00190
Haiku 4.5	$0.00003	$0.00095

Measured 1mo ago against content hash 257c5385462e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skill-cleaner 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/skill-cleaner.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/skill-cleaner/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Cleaner

Use this when trimming skill prompt budget, finding duplicate skills, auditing enabled/disabled skill roots, or deciding which skills/plugins to remove.

Workflow

Resolve this skill's directory from the loaded SKILL.md, then run its bundled analyzer:

node ./scripts/skill-cleaner.mjs --no-logs

Useful variants:

node ./scripts/skill-cleaner.mjs --months 3
node ./scripts/skill-cleaner.mjs --months 6 --max-log-mb 800 --deep-logs
node ./scripts/skill-cleaner.mjs --context-tokens 200000 --budget-percent 2 --no-logs
node ./scripts/skill-cleaner.mjs --root /path/to/another/skills-directory --no-logs
node ./scripts/skill-cleaner.mjs --json --no-logs

Read the report in this order:

Skill Budget: GPT-5.5 context size, 2% skills budget, Codex-budgeted usage, and pre-budget full-list pressure.
Description candidates: long descriptions where relaxed grammar saves prompt budget.
Duplicates: same skill name or near-identical description/body across Codex, plugin cache, repo siblings, and personal skill roots.
Unused candidates: no recent $skill mention, SKILL.md read, or explicit skill-use trace in recent Codex/OpenClaw logs.
Root summary: where skills came from and whether config marks them disabled.

Before deleting or editing:

Verify the kept copy exists and is loaded.
Treat cross-runtime duplicates as informational: separate runtimes may legitimately need separate copies.
Never delete managed plugin-cache files directly; use the runtime's plugin manager.
Delete a suggested duplicate only after verifying the kept path exists and the same runtime loads it.
Keep repo-local OpenClaw maintainer skills when they encode repo policy or live operations.
Preserve trigger nouns in descriptions: product, tool, action, object.

Analyzer Notes

The script mirrors Codex's model-visible line shape: - name: description (file: path).
It applies Codex-like frontmatter rules: YAML frontmatter only, default name from parent dir, single-line sanitized name and description.
It follows Codex core-skills/src/render.rs: 2% of raw context_window, token cost ceil(utf8_bytes / 4), then full descriptions -> equal description truncation -> omitted minimum lines.
It reads ~/.codex/models_cache.json for the selected model's context_window; fallback is 200,000 tokens and 2%. Pass --context-tokens for an exact budget.
It scans common global roots for .agents, Pi, Codex, Claude Code, OpenCode, and OpenClaw, plus skill roots in the current project and its ancestors.
Extra folders are included only with repeatable --root <path> flags.
It realpath-dedupes roots, so agent-specific symlinks to a shared skill directory do not create false duplicates.
For duplicate names, it reports description/body similarity and suggests deletion candidates only when bodies are near copies. Keep priority defaults to direct Codex system skills, then direct Codex skills, then plugin skills, then personal/repo copies.
It scans ~/.codex/history.jsonl and recent ~/.codex/sessions/**/*.jsonl by default. Add --deep-logs for archived sessions and common OpenClaw/Clawd log folders.
Usage evidence is heuristic: $skill, Use $skill, and paths like skills/<name>/SKILL.md.

Read the full file on GitHub · 67 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.

scripts/skill-cleaner.mjs 36 KB runs code

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.

1mo ago First seen · 67 lines · 33 tokens per session scan A 257c5385462e

Subscribe to this mod's changes

skill-cleaner is a skill published in the GitHub repository iurysza/android-use (21 stars, last pushed 16d ago), licensed MIT. It adds 33 tokens to every session and 949 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 2026-09-15.

Building agents LLM agentic-ai agents android skill

babysit

Use when a user asks to babysit, monitor, keep checking, keep an eye on, or report when a pull request, CI run, ticket, deployment, or other changing target reaches an outcome.

kirodotdev/KiroCrew · 45 tokens

rubber-duck

Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…

kirodotdev/KiroCrew · 161 tokens

building-agents

Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…

ericrisco/rsc-harness · 85 tokens

agent-eval

Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…

ericrisco/rsc-harness · 79 tokens

browser-qa

Testing web apps through a real browser: reconnaissance before acting, selector discovery, state capture, console errors and screenshot evidence. Use on a web surface end to end, or to reproduce a front-end bug.

damianvtran/local-operator · 45 tokens

code-review

Reviewing code for defects: diff-first reading, severity classification, evidence over inference, finding caps, and terminal verdicts. Use when reviewing a diff, PR, or patch, or auditing someone else's work.