Borrowing it
Nothing to install: this file belongs to Amartuvshins0404/clean-code-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Amartuvshins0404/clean-code-skills/main/CLAUDE.mdgit clone --depth 1 https://github.com/Amartuvshins0404/clean-code-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/instructions/amartuvshins0404/clean-code-skills/claude-md)<a href="https://agentmods.dev/instructions/amartuvshins0404/clean-code-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/amartuvshins0404/clean-code-skills/claude-md/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/instructions/amartuvshins0404/clean-code-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/amartuvshins0404/clean-code-skills/claude-md.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 | $0.00712 | $0.00712 |
| Opus 5 | $0.00356 | $0.00356 |
| Sonnet 5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
clean-code-skills CLAUDE.md 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 8d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Clean-code operating instructions for Claude Code. Merge these with project-specific instructions when installing into another repository.
Always Apply
Use the clean-code skill when writing, editing, reviewing, or refactoring code in any programming language or framework. If the skill is not available by name, read the installed skill file from skills/clean-code/SKILL.md or .github/skills/clean-code/SKILL.md.
When a decision concerns complexity, change, scale, optimization, or interface design, also consult skills/clean-code/references/canon.md. It synthesizes cross-canon principles (Parnas, Dijkstra, Knuth, Brooks, Hickey, Ousterhout, Hunt/Thomas, Martin, Fowler, GoF, McConnell, Software Engineering at Google) with source attribution.
For trivial typo fixes, keep the process light. For any non-trivial behavior change, use the full loop below.
Operating Loop
- Frame the task. State assumptions that affect design, data, safety, or tests. Ask only when ambiguity would change the implementation.
- Read local context. Inspect nearby code, tests, naming, error handling, and framework idioms before editing.
- Prefer the smallest solution. Solve today's requirement. Do not add speculative abstractions, options, dependencies, or future features.
- Edit surgically. Touch only files and lines required by the task. Preserve surrounding formatting and comments unless the task requires changing them.
- Make intent obvious. Favor meaningful names, small functions, cohesive modules, explicit boundaries, and tests that describe behavior.
- Verify before claiming success. Run the narrowest meaningful check first, then broader checks when the change has wider risk. Report what ran and what did not.
- Review the diff. Remove dead code introduced by your change, check for hidden failure paths, and call out unrelated issues instead of fixing them silently.
Clean-Code Rules
- Names should reveal intent, use domain language, and avoid misleading abbreviations.
- Functions should do one thing at one level of abstraction and avoid hidden side effects.
- Comments should explain why, constraints, or non-obvious tradeoffs. They should not narrate unclear code.
- Modules, classes, components, and scripts should be cohesive and have explicit boundaries.
- Error handling should preserve context, avoid swallowed failures, and match language idioms.
- Tests should be deterministic, readable, behavior-focused, and tied to risk.
- Concurrency should make ownership, cancellation, ordering, and shared state explicit.
- Refactors should preserve behavior and be verified before and after when possible.
- Distinguish essential complexity (the problem) from accidental complexity (how it was built); only the second is yours to fix in passing.
- Once an interface has multiple users, every observable behavior gets depended on; change such behavior with care or version the contract.
- Sustained tactical patches in the same area are a strategic problem; name it instead of patching again.
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.
- 8d ago First seen · 48 lines · 712 tokens per session scan A 4011d950eb61
clean-code-skills CLAUDE.md is an instructions file published in the GitHub repository Amartuvshins0404/clean-code-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 712 tokens to every session, about $0.0036 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.