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/pr-pm/prpm/creating-cursor-rulesgit clone --depth 1 https://github.com/pr-pm/prpmWhat 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 | $0.00016 | $0.04043 |
| Opus 5 | $0.00008 | $0.02021 |
| Sonnet 5 | $0.00003 | $0.00809 |
| Haiku 4.5 | $0.00002 | $0.00404 |
Grade A, and why
creating-cursor-rules 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 — 677 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creating Cursor Rules - Meta Rule
Overview
This is a meta-rule for creating effective .cursor/rules files. Apply these principles when writing or improving Cursor IDE rules for your project.
When to Use
Use when:
- Starting a new project and setting up
.cursor/rules - Improving existing project rules
- Converting skills or guidelines to Cursor format
- Team needs consistent coding standards
Don't use for:
- Claude Code skills (those go in
.claude/skills/) - One-time instructions (just ask directly)
- User-specific preferences (those go in global settings)
Core Principles
1. Be Specific and Actionable
# ❌ BAD - Vague
Write clean code with good practices.
# ✅ GOOD - Specific
Use functional components with TypeScript.
Define prop types with interfaces, not inline types.
Extract hooks when logic exceeds 10 lines.
2. Focus on Decisions, Not Basics
# ❌ BAD - Obvious
Use semicolons in JavaScript.
Indent with 2 spaces.
# ✅ GOOD - Decision guidance
Choose Zustand for global state, React Context for component trees.
Use Zod for runtime validation at API boundaries only.
Prefer server components except for: forms, client-only APIs, animations.
3. Organize by Concern
# ✅ GOOD Structure
## Tech Stack
- Next.js 14 with App Router
- TypeScript strict mode
- Tailwind CSS for styling
## Code Style
- Functional components only
- Named exports (no default exports)
- Co-locate tests with source files
## Patterns
- Use React Server Components by default
- Client components: mark with "use client" directive
- Error handling: try/catch + toast notification
## Project Conventions
- API routes in app/api/
- Components in components/ (flat structure)
- Types in types/ (shared), components/*/types.ts (local)
Rule Anatomy
MDC Format and Metadata
Cursor rules are written in MDC (.mdc) format, which supports YAML frontmatter metadata and markdown content. The metadata controls how and when rules are applied.
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 · 677 lines · 16 tokens per session scan A 66af177e160a
creating-cursor-rules is a cursor rule published in the GitHub repository pr-pm/prpm (120 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 4,043 once invoked, about $0.0001 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
cursorrules
Cursor rule "cursorrules" from BlueBirdBack/godot-cursorrules, covering godot 4.4 game development .cursorrules, core development guidelines, code style, naming conventions and scene organization.
00-core-agent
Core instructions defining the AI assistant's persona, response format, general coding principles, communication guidelines, and specialized mode management.
Accessibility-Review
Reviews web interfaces, content, or code snippets for common accessibility (a11y) issues based on WCAG guidelines, ensuring usability for people with disabilities.
Security-Audit
Reviews code, configurations, or architecture designs for common security vulnerabilities and adherence to security best practices, referencing standards like OWASP Top 10.
ShadcnUI
Best practices and guidelines for working with shadcn/ui components across various frameworks.
Supabase
Guidelines for using Supabase Auth, Database (Postgres migrations), Storage, Realtime, Edge Functions, and AI/Vectors.