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/eugeneyvt/logseq-mcp-server/cursorrulesgit clone --depth 1 https://github.com/eugeneyvt/logseq-mcp-serverWhat 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 | $0.02085 | $0.02085 |
| Opus 5 | $0.01043 | $0.01043 |
| Sonnet 5 | $0.00417 | $0.00417 |
| Haiku 4.5 | $0.00209 | $0.00209 |
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 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Logseq AI MCP Server - Cursor Rules
Common Commands
# Development
npm run dev # Start development server
npm run build # Build the project
npm run type-check # Run TypeScript type checking
npm run lint # Run ESLint
npm run test # Run test suite
npm run test:watch # Run tests in watch mode
# Package management
npm install # Install dependencies
npm audit # Check for security vulnerabilities
Code Quality & Maintainability Principles
- ALWAYS use TypeScript with strict mode enabled
- Prefer explicit types over
anyorunknown - Enforce consistent code style with ESLint + Prettier (or Biome)
- Keep functions small and single-purpose (SRP)
- Use clear naming for handlers, schemas, and RPC methods
- Organize code into modules (
/handlers,/schemas,/utils,/tests) - Document public methods and exported types with JSDoc
- Use named functional components only
- Place hooks above JSX
- Split components >250 LOC
- Avoid
useEffectunless truly needed - Use
memo/useCallback/useMemoonly when necessary
Runtime Safety Requirements
- YOU MUST validate all incoming JSON-RPC requests with Zod (or JSON Schema)
- YOU MUST validate all outgoing responses before sending back
- Always return proper JSON-RPC error codes (-32600, -32601, -32602, -32603)
- Avoid throwing raw errors — wrap them in structured error helpers
- Sanitize and redact sensitive data in logs
Testing & CI Standards
- Write unit tests for each handler (Vitest/Jest)
- Add at least one integration test that spins up the server and executes RPC calls
- Use mocked inputs/outputs for edge cases (empty data, invalid payloads, timeouts)
- Run
tsc --noEmit, lint, and test in CI pipeline - Ensure 100% type-check clean (no ts-ignore)
Build & Tooling
- Bundle with tsup or esbuild for small, fast CLI output
- Expose CLI entry via bin in package.json
- Use
#!/usr/bin/env nodein CLI entry point - Ensure build outputs both CJS and ESM (for compatibility)
- Add
"type": "module"in package.json if using ESM - Automate versioning and changelogs with Changesets (optional)
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 · 228 lines · 2,085 tokens per session scan A c4dc3a67ebf4
cursorrules is a cursor rule published in the GitHub repository eugeneyvt/logseq-mcp-server (7 stars, last pushed 1y ago), licensed MIT. It adds 2,085 tokens to every session, about $0.0104 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
cursorrules
Always write tests before implementation code. Every feature and bugfix must be covered by a test that fails before the change and passes after it. Keep the test suite fast and deterministic.
joplin-brain-config
joplin-llm-wiki 設定與測試中的 knowledge flow／notebook export／agent compile／joplinwikiwriteback 慣例.
cursorrules
This project uses Spectra for Spec-Driven Development(SDD).
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.
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.