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 agentmods add skills/cosmicstack-labs/mercury-agent-skills/clean-codenpx skills add cosmicstack-labs/mercury-agent-skills --skill clean-codegit clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-skillsWrote 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/cosmicstack-labs/mercury-agent-skills/clean-code)<a href="https://agentmods.dev/skills/cosmicstack-labs/mercury-agent-skills/clean-code"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/clean-code.svg" alt="Measured on agentmods" 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 | $0.00018 | $0.01973 |
| Opus 5 | $0.00009 | $0.00986 |
| Sonnet 5 | $0.00004 | $0.00395 |
| Haiku 4.5 | $0.00002 | $0.00197 |
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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean Code
Write code that humans can read, understand, and change with confidence.
Core Principles
1. Mean What You Say — Say What You Mean
Code is communication. Every name, structure, and abstraction should reveal intent. If you need a comment to explain what the code does, the code is failing at communication.
2. Small Things, Done Well
Small functions, small classes, small files. Each unit of code should have one clear responsibility and do it well. Composability beats complexity.
3. The Boy Scout Rule
Leave the code cleaner than you found it. Every commit should improve the codebase incrementally — even if it's just renaming one variable or extracting one function.
4. Testability == Design Quality
If code is hard to test, it has a design problem. Testable code is modular, decoupled, and honest about its dependencies.
Clean Code Scoring Rubric
Use this rubric to evaluate code quality on a scale of 1-5 for each dimension:
| Dimension | 1 (Poor) | 3 (Adequate) | 5 (Excellent) |
|---|---|---|---|
| Naming | Single-letter vars, ambiguous abbreviations | Descriptive but occasionally redundant | Reveals intent, consistent, searchable |
| Function Size | Monolithic 500+ line functions | 50-100 line functions with mixed concerns | <20 lines, one clear level of abstraction |
| Comments | Outdated or redundant comments | Comments explain what not why | Minimal comments, code is self-documenting |
| Error Handling | Silent catches, magic error codes | Basic try/catch, some error types | Rich error types, graceful degradation |
| Testing | No tests or brittle tests | Tests exist but tightly coupled to implementation | Tests specify behavior, not implementation |
| Duplication | Copy-paste everywhere | Some reuse, some DRY violations | DRY with well-abstracted patterns |
Target: 4+ in every dimension for production-grade code.
Actionable Guidance
Naming
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.
- 4d ago First seen · 195 lines · 18 tokens per session scan A 7490cd0ad070
clean-code is a skill published in the GitHub repository cosmicstack-labs/mercury-agent-skills (471 stars, last pushed 10d ago), licensed MIT. It adds 18 tokens to every session and 1,973 once invoked, about $0.0001 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.
Other skills, from other repositories
modern-saas-builder
Founder-minded senior product engineer and SaaS architect skill. Use when building, planning, architecting, validating, designing, testing, securing, deploying, or monetizing modern SaaS products, micro-SaaS, web apps, AI agents, Web3/Base applications, agent commerce, or Telegram bots/Mini Apps. Always active when…
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
atlas-obscura
Search Atlas Obscura for weird, wonderful, and hidden gem places near any destination. Find the interesting stuff, not boring plaques. Search by coordinates, get full details with descriptions and images.
cf-validate
Валидация конфигурации 1С. Используй после создания или модификации конфигурации для проверки корректности.
producthunt-launch-kit
Use when the user asks to prepare a Product Hunt launch or generate Product Hunt listing assets. Generates tagline variants under 60 chars, a 500-char description, a maker comment, launch-day tweet thread, LinkedIn post, and a 4-email launch sequence.