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.
npx skills add markoa/clean-code-skill --skill clean-codegit clone --depth 1 https://github.com/markoa/clean-code-skillWrote 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.
[](https://agentmods.dev/skills/markoa/clean-code-skill/clean-code)<a href="https://agentmods.dev/skills/markoa/clean-code-skill/clean-code"><img src="https://agentmods.dev/badge/skills/markoa/clean-code-skill/clean-code/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.
<a href="https://agentmods.dev/skills/markoa/clean-code-skill/clean-code"><img src="https://agentmods.dev/badge/skills/markoa/clean-code-skill/clean-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00093 | $0.01280 |
| Opus 5.5 | $0.00037 | $0.00512 |
| Sonnet 5.5 | $0.00019 | $0.00256 |
| Haiku 4.5 | $0.00009 | $0.00128 |
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 1mo 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.
This is a copy
100% identical to clean-code, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean Code
These are mandatory engineering standards for any code you write, change, or review while this skill is active. They are language-agnostic: apply them in whatever language the project uses, respecting that language's idioms.
If there is tension between speed and cleanliness, choose the clean solution unless there is a demonstrated operational emergency. If a shortcut is unavoidable, contain it, make it obvious, and leave the code safe to clean up later.
For detailed rationale, examples, and design heuristics, read reference.md — consult it when a rule needs interpretation or when you face a non-obvious design decision.
Core Rules
1. Leave the code cleaner
Every change must improve at least one of: clarity, naming, simplicity, cohesion, testability, error handling, duplication removal, or separation of concerns. Do not add code that is merely functional — add code that is understandable.
2. Optimize for readers
- Write code for the next engineer, not for impressiveness.
- Prefer straightforward code over clever code.
- Keep control flow obvious.
- If code is hard to explain, treat that as a design problem.
3. Use strong names
- Names must reveal intent. Use domain language consistently.
- Prefer specific names over generic ones. Avoid
data,info,thing,stuff,manager,helper,util,misc,handle,temp,objunless they are genuinely correct in the domain or an external protocol. - Boolean names read like predicates (
active?,isActive,hasItems,retryable?), following the language's convention. - Collection names are plural.
- Function names describe the action performed, not vague activity
(
calculate_invoice_total, notdo_invoice).
4. Keep methods small and focused
- A method should do one thing at one level of abstraction.
- Do not mix business rules, formatting, persistence, external calls, and error recovery in one method. Extract helpers when a method grows multiple phases.
- Prefer zero, one, or two parameters; three should trigger scrutiny; more usually means a missing value object or domain object.
- Do not use boolean parameters to switch behavior when separate methods would express intent more clearly.
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.
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 · 145 lines · 93 tokens per session scan A c8a9d0ede73b
clean-code is a skill published in the GitHub repository markoa/clean-code-skill (7 stars, last pushed 5mo ago), licensed MIT. It adds 93 tokens to every session and 1,280 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to clean-code, and is treated as a copy.
Other skills, from other repositories
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
sip
After you create or change an artifact or skill, taste-test it with our own skills instead of trusting your in-session judgment — recursive self-improvement, made automatic. Use right after writing or editing anything, before calling it done, committing, or handing it off.
prism
Split one artifact — a claim, plan, or file — across 2 to 5 independent lenses, one per genuinely distinct failure mode (correctness, security, readability, cost, adversarial-user), and return their convergence: where they agree, where they disagree, and the single next question that resolves the disagreement. Use…
hate
Attack a plan, design, or argument like you want it to fail before you commit real effort — return the single load-bearing objection and the cheapest experiment that would prove it matters, not a checklist. User-invoked on purpose: a hate-it reflex always in the agent's reach would bias it toward demolition. Weighs…
clean-code
Use when writing, editing, reviewing, testing, planning, or refactoring code in any language or framework; creating files or deciding where code and folders belong; designing or changing module boundaries, layers, and dependencies; starting a new project; auditing or cleaning up an existing one; or compressing agent…
solid-interface-segregation
This skill should be used when the user asks about "interface segregation", "ISP", mentions "fat interfaces", discusses clients forced to depend on methods they don't use, or wants to design smaller, focused interfaces.