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/kpritam/gremlin-mcp/03-clean-codegit clone --depth 1 https://github.com/kpritam/gremlin-mcpWhat 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 | $0.00000 | $0.00736 |
| Opus 5 | $0.00000 | $0.00368 |
| Sonnet 5 | $0.00000 | $0.00147 |
| Haiku 4.5 | $0.00000 | $0.00074 |
Grade A, and why
03-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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Guidelines
Core Principles
- KISS: Keep code simple, avoid over-engineering
- YAGNI: Don’t add features until they are needed
- DRY: Eliminate duplication via abstraction or reuse
- Small Functions: Each function should do one thing well
- No Side Effects: Prefer pure functions; isolate effects at the edges
Naming & Structure
- Use meaningful, self-explanatory names
- Group related code logically; use barrel exports for modules
- Keep types/interfaces close to where they’re used; extract only when shared
- Constants should replace all magic numbers and strings
Comments & Documentation
- Document public APIs and complex logic only
- Use comments to explain why, not what
- For tricky/effects-heavy code, describe gotchas and assumptions
- Use TypeDoc (
/** ... */) format
TypeScript Practices
- Enable strict mode in
tsconfig.json - Avoid
any; preferunknownwith type guards - Use
interfacefor objects,typefor unions/intersections - Always type public function signatures explicitly
- Prefer readonly types for immutability
- Use discriminated unions for safer branching
- Avoid type assertions except at clear boundaries (e.g., parsing JSON)
Error Handling
- Never throw — instead:
- Use
Either/Option/Resulttypes from effect libraries - Represent expected failures in the type system
- Use
- Always handle errors at the boundary of the system (e.g., API layer)
- Include contextual information in error values (not stack traces)
Effect-TS / Functional Code
- Model side effects with typed effects, not untyped Promises
- Prefer composition over nesting (
pipe,flatMap,mapError) - Use
Layerfor dependency injection - Always annotate effect return types for clarity
- Avoid calling
unsafeRun*in core logic; restrict it to the application entrypoint
Testing
- Write tests for public APIs and critical logic
- Include edge cases, failure cases, and effectful code
- Keep test code clean and readable; use descriptive test names
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 · 91 lines · 736 tokens per session scan A 1c7b23f1dacc
03-clean-code is a cursor rule published in the GitHub repository kpritam/gremlin-mcp (9 stars, last pushed 11mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 736 tokens. 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.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.