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/magarcia/mcp-server-linearapp/cursorrulesgit clone --depth 1 https://github.com/magarcia/mcp-server-linearappWhat 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 | $0.00643 | $0.00643 |
| Opus 5 | $0.00321 | $0.00321 |
| Sonnet 5 | $0.00129 | $0.00129 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
cursorrules 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 yesterday.
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
89% identical to cursorrules — 6 lines differ, 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert in TypeScript, Node.js, and RESTful API development.
TypeScript Standards
- Use TypeScript for all new code; avoid any
anytypes - Prefer interfaces over types for API response objects
- Use type predicates and guards to handle nullable values rather than type assertions
- Export well-defined response types for all API endpoints
- Use descriptive variable names that reflect the API terminology
Code Structure
- Keep files focused on a single responsibility
- Separate API endpoint functions by category (search, trending, random, etc.)
- Use async/await for all API requests, not Promises with .then()
- Handle rate limiting and error responses consistently
- Include JSDoc comments for all public methods and interfaces
API Client Design
- Ensure all API endpoints support the full range of parameters from API
- Include proper pagination support for endpoints that return multiple results
- Use reasonable defaults for optional parameters
- Make the client configurable with options like rating, language, etc.
- Implement proper error handling with custom error types
Testing Standards
- Write unit tests for all API endpoint functions
- Use mocks for external API calls in tests
- Include integration tests that validate against real API responses
- Test error handling scenarios like rate limiting and invalid API keys
- Ensure all public interfaces have test coverage
Performance Considerations
- Implement request caching where appropriate
- Support both ESM and CommonJS module formats
- Keep dependencies minimal and up-to-date
- Ensure the package has a small bundle size
- Support tree-shaking for modular imports
Documentation
- Keep README examples up-to-date with the current API
- Include TypeDoc documentation for all public interfaces
- Document rate limiting considerations
- Provide usage examples for each API endpoint category
- Include sample response objects in documentation
Best Practices
- Favor immutable objects over mutable ones
- Use private class fields to hide implementation details
- Implement proper parameter validation before making API requests
- Use URL builder helper functions to construct API URLs
- Apply consistent error handling patterns throughout the codebase
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.
- yesterday First seen · 90 lines · 643 tokens per session scan A 3bc48dbb3e8f
cursorrules is a cursor rule published in the GitHub repository magarcia/mcp-server-linearapp (1 stars, last pushed 1y ago), licensed MIT. It adds 643 tokens to every session, about $0.0032 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to cursorrules, differing in 6 lines, and is treated as a copy.
Other cursor rules, from other repositories
development-conventions
Development conventions, code style, and best practices for the Kaneo project.
docs
This file provides guidelines for working with the documentation in the /docs directory.
architecture
Architecture of openapi-to-cli (ocli).
architecture-constraints
GolemBot architecture hard constraints — must check before modifying any src/ code.
app_feature_first_architecture
Feature-first architecture is a design pattern that organizes code by business features rather than technical layers. This approach promotes better maintainability, scalability, and team collaboration by keeping related functionality together and reducing coupling between different parts of the application.
best_practices
Advanced Best Practices covering Error Handling, Environment Variables, Performance, and Accessibility rules.