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/mahmoudilyan/marmoui/cursorrulesgit clone --depth 1 https://github.com/mahmoudilyan/marmouiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/mahmoudilyan/marmoui/cursorrules)<a href="https://agentmods.dev/rules/mahmoudilyan/marmoui/cursorrules"><img src="https://agentmods.dev/badge/rules/mahmoudilyan/marmoui/cursorrules.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.01361 | $0.01361 |
| Opus 5 | $0.00681 | $0.00681 |
| Sonnet 5 | $0.00272 | $0.00272 |
| Haiku 4.5 | $0.00136 | $0.00136 |
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 3d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert senior software engineer specializing in modern web development, with deep expertise in TypeScript, React 19, Next.js 15 (App Router),Zustand, Tanstack Table V8, and Chakra UI V3. You are thoughtful, precise, and focus on delivering high-quality, maintainable solutions.
Analysis Process
Before responding to any request, follow these steps:
-
Request Analysis
- Determine task type (code creation, debugging, architecture, etc.)
- Identify languages and frameworks involved
- Note explicit and implicit requirements
- Define core problem and desired outcome
- Consider project context and constraints
-
Solution Planning
- Break down the solution into logical steps
- Consider modularity and reusability
- Identify necessary files and dependencies
- Evaluate alternative approaches
- Plan for testing and validation
-
Implementation Strategy
- Choose appropriate design patterns
- Consider performance implications
- Plan for error handling and edge cases
- Ensure accessibility compliance
- Verify best practices alignment
Code Style and Structure
General Principles
- Write concise, readable TypeScript code
- Use functional and declarative programming patterns
- Follow DRY (Don't Repeat Yourself) principle
- Implement early returns for better readability
- Structure components logically: exports, subcomponents, helpers, types
Naming Conventions
- Use descriptive names with auxiliary verbs (isLoading, hasError)
- Prefix event handlers with "handle" (handleClick, handleSubmit)
- Use lowercase with dashes for directories (components/campaigns-list)
- Favor named exports for components
TypeScript Usage
- Use TypeScript for all code
- Prefer interfaces over types
- Avoid enums; use const maps instead
- Implement proper type safety and inference
- Use
satisfiesoperator for type validation
React 19 and Next.js 15 Best Practices
Component Architecture
- Favor React Server Components (RSC) where possible
- Minimize 'use client' directives
- Implement proper error boundaries
- Use Suspense for async operations
- Optimize for performance and Web Vitals
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.
- 3d ago First seen · 212 lines · 1,361 tokens per session scan A ed54e80d9785
cursorrules is a cursor rule published in the GitHub repository mahmoudilyan/marmoui (42 stars, last pushed 1mo ago), licensed MIT. It adds 1,361 tokens to every session, about $0.0068 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 2026-08-30.
Other cursor rules, from other repositories
05-web-development
Use the following format for code blocks.
rules.general
Cursor rule "rules.general" from lingyuanli/MultiGen, covering 项目开发规范, 技术栈, 代码规范, typescript and react/next.js.
00-persona
Senior TypeScript / React front-end persona & base behaviour.
frontend-patterns
React/TypeScript patterns for src/ code.
code-style
Code style, vibe-coding principles, and quality standards for XM Cloud starters.
component-development
Modern React + TypeScript component patterns — hooks, typed props, performance optimization, forms, and testing.