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/arjshiv/localutils-mcp-server/cursorrulesgit clone --depth 1 https://github.com/arjshiv/localutils-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 | $0.01317 | $0.01317 |
| Opus 5 | $0.00659 | $0.00659 |
| Sonnet 5 | $0.00263 | $0.00263 |
| Haiku 4.5 | $0.00132 | $0.00132 |
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.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cursor Rules for localutils-mcp-server
This document defines the coding standards and rules for the localutils-mcp-server project.
All rules are enforced through the Cursor IDE and are documented in detail in the .cursor/rules/ directory.
MCP Workflow Diagrams
All MCP implementations must include workflow diagrams using Mermaid. Below is the standard MCP workflow:
graph TD
A[Client Request] --> B[MCP Server]
B --> C{Protocol Handler}
C --> D[Execute Command]
C --> E[Process Data]
C --> F[Handle Error]
D --> G[Return Result]
E --> G
F --> G
G --> B
B --> H[Client Response]
style A fill:#f9f,stroke:#333,stroke-width:2px
style B fill:#bbf,stroke:#333,stroke-width:2px
style C fill:#dfd,stroke:#333,stroke-width:2px
Required Workflow Documentation
Each MCP implementation must document:
graph LR
A[Protocol Definition] --> B[Handler Implementation]
B --> C[Error Handling]
B --> D[Data Processing]
B --> E[Command Execution]
style A fill:#f96,stroke:#333,stroke-width:2px
style B fill:#9cf,stroke:#333,stroke-width:2px
Core TypeScript Files
| Pattern | Rule File | Description |
|---|---|---|
*.ts |
typescript.mdc | Core TypeScript source files |
*.tsx |
typescript.mdc | TypeScript React components |
src/**/*.ts |
typescript.mdc | All TypeScript files in src |
src/utils/*.ts |
typescript.mdc | Utility TypeScript files |
src/types/*.ts |
typescript.mdc | Type definition files |
Testing Files
| Pattern | Rule File | Description |
|---|---|---|
*.test.ts |
testing.mdc | Unit test files |
*.spec.ts |
testing.mdc | Integration test files |
src/__tests__/** |
testing.mdc | Test directory and contents |
src/**/*.test.ts |
testing.mdc | Tests throughout source |
src/test-utils/*.ts |
testing.mdc | Test utilities |
Configuration Files
| Pattern | Rule File | Description |
|---|---|---|
*.config.js |
config.mdc | JavaScript config files |
*.config.ts |
config.mdc | TypeScript config files |
tsconfig.json |
typescript-config.mdc | TypeScript configuration |
jest.config.js |
config.mdc | Jest test configuration |
.env* |
config.mdc | Environment configurations |
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 · 133 lines · 1,317 tokens per session scan A 8f39b4806fad
cursorrules is a cursor rule published in the GitHub repository arjshiv/localutils-mcp-server (2 stars, last pushed 8mo ago), licensed MIT. It adds 1,317 tokens to every session, about $0.0066 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.
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.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
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.