clean-code

A set of code-writing and review principles focused on clear names, small focused functions, limited duplication, and tests. Clean Code means organizing software so its purpose is easy to understand and change.

In plain words
What is it for?
Use it while implementing features and reviewing code. It guides naming, function design, argument counts, error handling, comments, abstractions, and test structure.
Why use it?
It makes code easier to read, test, maintain, and debug. It also helps catch hidden side effects, unclear responsibilities, and comments that merely repeat the code.

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

Made for: Claude Code, Codex.

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 375 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 $0.00052 $0.00375
Opus 5 $0.00026 $0.00187
Sonnet 5 $0.00010 $0.00075
Haiku 4.5 $0.00005 $0.00038

Measured yesterday against content hash d3a35ce41445, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clean-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.

.claude/skills/clean-code/SKILL.md · 27 lines

What it actually says

Write it right the first time. This is the forward constraint; refactor is the recovery one.

Checklist (apply as you write)

  • Names reveal intention. A name should answer why it exists, what it does, how it's used — without a comment. No data, tmp, mgr, doProcess.
  • Functions are small and do one thing. One level of abstraction per function. If you need "and" to describe it, split it.
  • No duplication (DRY). Duplicated logic = a missing abstraction. Extract it into a shared utility (golden principle: invariants live in one place).
  • Few arguments. 0–2 ideal; 3+ suggests a missing object or a function doing too much. No boolean flag args that select behavior — split the function.
  • No side effects hidden behind innocent names. Command/query separation.
  • Comments explain why, not what. The code says what. Delete comments that restate code; they rot. Prefer a clearer name over a comment.
  • Errors over return codes; parse/validate at the boundary; fail loud early.
  • Tests are first-class — readable, one assert-concept each, fast.

Use as a review lens (evaluator)

When grading, cite the specific rule violated and the smallest fix. Don't rewrite — point. The generator applies the fix under green tests via refactor.

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 · 27 lines · 52 tokens per session scan A d3a35ce41445

Subscribe to this mod's changes

clean-code is a skill published in the GitHub repository harness-mini/harness-mini (2 stars, last pushed 21d ago), licensed MIT. It adds 52 tokens to every session and 375 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 2026-08-31.