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 rules/amartuvshins0404/clean-code-skills/clean-codegit clone --depth 1 https://github.com/Amartuvshins0404/clean-code-skillsWhat 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 | $0.00364 | $0.00364 |
| Opus 5 | $0.00182 | $0.00182 |
| Sonnet 5 | $0.00073 | $0.00073 |
| Haiku 4.5 | $0.00036 | $0.00036 |
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 2d 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.
What it actually says
Clean Code
Use these rules for every coding task in Cursor.
Work Loop
- Clarify assumptions that affect behavior, tests, security, data, or architecture.
- Inspect nearby code and match existing idioms before editing.
- Make the smallest change that solves the request.
- Keep names, functions, modules, tests, and errors readable and explicit.
- Verify with the narrowest meaningful check, then expand checks when risk demands it.
- Review the diff for unrelated edits, speculative abstractions, and hidden failure paths.
Clean-Code Baseline
- Names reveal intent and use domain language.
- Functions and methods do one thing at one abstraction level.
- Comments explain why, constraints, or tradeoffs; they do not excuse unclear code.
- Classes, modules, components, scripts, jobs, and queries stay cohesive.
- Boundaries around external systems are explicit and tested when risk warrants it.
- Errors preserve context and are not swallowed silently.
- Tests are readable, deterministic, and behavior-focused.
- Concurrency makes ownership, ordering, cancellation, and shared state explicit.
- Essential complexity (the problem) and accidental complexity (how it was built) are different; only the second is yours to fix in passing.
- Once an interface has multiple users, every observable behavior is part of the contract.
Do Not
- Do not rewrite unrelated code.
- Do not reformat files outside the touched area.
- Do not add future-proofing that the request did not need.
- Do not impose one language's style on another language.
- Do not claim success without fresh verification evidence.
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.
- 2d ago First seen · 40 lines · 364 tokens per session scan A 1229b5b4edb1
clean-code is a cursor rule published in the GitHub repository Amartuvshins0404/clean-code-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 364 tokens to every session, about $0.0018 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 cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.