clean

clean is a skill for Claude Code, Codex from OutThisLife/brooklyn-skills. It costs 70 tokens per session (398 once invoked), scanned A, original, MIT.

A manual code-polishing pass based on simple design, avoiding duplication, and the surrounding project's style. It removes dead code and leftover debugging while keeping the change focused.

In plain words
What is it for?
Use it to tidy a change, simplify code, remove duplication, and prepare a pull request. It also helps organize commits and describe the overall change clearly.
Why use it?
It catches unnecessary complexity and inconsistent code before handoff. It is for improving the diff itself, not for running the test suite or other broad checks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to tidy a change, simplify code, remove duplication, and prepare a pull request. It also helps organize commits and describe the overall change clearly.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/outthislife/brooklyn-skills/clean
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 OutThisLife/brooklyn-skills --skill clean
Clone the repo
git clone --depth 1 https://github.com/OutThisLife/brooklyn-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/outthislife/brooklyn-skills/clean/github.svg)](https://agentmods.dev/skills/outthislife/brooklyn-skills/clean)
Your own site
<a href="https://agentmods.dev/skills/outthislife/brooklyn-skills/clean"><img src="https://agentmods.dev/badge/skills/outthislife/brooklyn-skills/clean/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 clean

Your own site · 80×15
<a href="https://agentmods.dev/skills/outthislife/brooklyn-skills/clean"><img src="https://agentmods.dev/badge/skills/outthislife/brooklyn-skills/clean.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 398 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00070 $0.00398
Opus 5 $0.00035 $0.00199
Sonnet 5 $0.00014 $0.00080
Haiku 4.5 $0.00007 $0.00040

Measured 9d ago against content hash d66551a3a858, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

clean 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 9d 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.

skills/clean/SKILL.md · 42 lines

What it actually says

Clean

KISS/DRY and copy the local code style. Be elitist, shorthand, clever, concise, efficient, and elegant.

"Clean" means polishing the code — it does NOT mean running the test suite, tsc, or lint as the task. Run a check only if it's genuinely needed to confirm the polish is safe.

Clean is a standalone pass, not just a pre-PR step — run it whenever things get messy, including mid-work. Also run it automatically before any PR handoff (creating, updating, automerging, or moving to the next PR) without being told each time.

Do

  1. Re-read your diff. Cut dead code, leftover debug logging, and duplication.
  2. Extend existing helpers — don't parallel-implement.
  3. Match neighboring style (names, imports, file layout, comment density).
  4. Prefer the small sharp version over ceremony.
  5. UI work: only after they like the UI (ui-only). Use ui-system for primitives.
  6. On the PR: title/body describe the change as a whole (a short intro), not a changelog of steps. Split into topical commits (pr-update), run no-tropes on the text, and link the PR.

Don't

  • Run the test suite / tsc / lint just because you were told to "clean"
  • Unrelated refactors
  • New abstractions with one caller
  • Scope creep dressed up as cleanup
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. 9d ago First seen · 42 lines · 70 tokens per session scan A d66551a3a858

Subscribe to this mod's changes

clean is a skill published in the GitHub repository OutThisLife/brooklyn-skills (191 stars, last pushed 22d ago), licensed MIT. It adds 70 tokens to every session and 398 once invoked, about $0.0003 per session on Opus 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 2026-08-30.