cleaning-code

A code-cleanup workflow that simplifies recently changed code, removes repetition, improves names and error handling, and checks that tests stay clean.

In plain words
What is it for?
Use it during feature work, bug fixes, or refactoring to reduce nesting, apply focused refactorings, and review the affected tests.
Why use it?
It helps reduce unnecessary complexity and code smells while preserving the intended behavior.

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/rootbr/rooted/cleaning-code
Any agent
npx skills add rootbr/rooted --skill cleaning-code
Clone the repo
git clone --depth 1 https://github.com/rootbr/rooted

Made for: Claude Code, Codex.

Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,377 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00154 $0.04377
Opus 5 $0.00077 $0.02188
Sonnet 5 $0.00031 $0.00875
Haiku 4.5 $0.00015 $0.00438

Measured yesterday against content hash ad716b01f52a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cleaning-code 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 yesterday.

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/code-quality/skills/cleaning-code/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clean Code

Evidence base: Robert C. Martin, Clean Code: A Handbook of Agile Software Craftsmanship (2008) and Clean Architecture (2017); Martin Fowler, Refactoring: Improving the Design of Existing Code (1999); cleancoder.com. Chapter references cite Clean Code unless noted otherwise.

Load-bearing rule — maximum simplicity

Boy Scout Rule: leave every piece of code cleaner than you found it (Clean Code, Preface). Simple is the default; complexity earns its place against a specific constraint.

Functions (Ch 3)

  • Small — "first rule: functions must be compact; second rule: functions must be even more compact." Aim 5–10 lines; 20 is already large; blocks inside if/else/while should be one line, ideally a function call (Ch 3 "Small!" + "Blocks and Indenting", p. 34–35)
  • One thing — operational test: try to extract another function whose name isn't a paraphrase of the body. If the extraction is meaningful, the original did more than one thing (Ch 3 "Do One Thing" / "One Level of Abstraction", p. 36)
  • 0–2 arguments ideal; 3 requires justification; more → group into an object ("Function Arguments")
  • No boolean flags — a flag argument hides two functions in one; split them ("Flag Arguments")
  • No side effects — what the name doesn't promise, the body doesn't do ("Side Effects")
  • Descriptive name — a long, clear verb beats a short, vague one ("Use Descriptive Names")
  • Return the transformed value; don't mutate the argument — Buffer transform(Buffer in) beats void transform(Buffer out) (Ch 3 "Standard Unary Forms", p. 66)
  • Separate command from query — a method either does or answers, never both (Ch 3 "Command Query Separation", p. 45; Fowler Ch 10 "Separate Query from Modifier", p. 282)
  • Treat parameters as final; if you need to change the value, copy into a local (Fowler Ch 6 "Remove Assignments to Parameters", p. 144)

Names (Ch 2)

  • Reveal intent — the name answers why this variable exists and how it is used
  • Pronounceable — generationTimestamp, not genymdhms
  • No type encodings — name, not strName / m_name / userObj
  • Named constants — DAYS_IN_WEEK beats the literal 7 (magic numbers have no search anchor)
  • Searchable — the identifier is distinctive enough that grep finds exactly the intended use
  • Don't disinform — never reuse l/O (look like 1/0); never name a thing accountList unless it is a List (Ch 2 "Avoid Disinformation", p. 19–20)
  • Pick one word per concept — fetch OR retrieve OR get, not all three (Ch 2 "Pick One Word per Concept", p. 26)
  • Class names are nouns; method names are verbs — a Manager / Processor class name hints at an SRP violation (Ch 2 "Class Names" / "Method Names", p. 25)

Read the full file on GitHub · 198 lines

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. yesterday First seen · 198 lines · 154 tokens per session scan A ad716b01f52a

Subscribe to this mod's changes

cleaning-code is a skill published in the GitHub repository rootbr/rooted (21 stars, last pushed 26d ago), licensed Apache-2.0. It adds 154 tokens to every session and 4,377 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens