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.
git clone --depth 1 https://github.com/Renvia-code/best-cursor-rulesWrote 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/renvia-code/best-cursor-rules/00-project-core)<a href="https://agentmods.dev/rules/renvia-code/best-cursor-rules/00-project-core"><img src="https://agentmods.dev/badge/rules/renvia-code/best-cursor-rules/00-project-core/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/renvia-code/best-cursor-rules/00-project-core"><img src="https://agentmods.dev/badge/rules/renvia-code/best-cursor-rules/00-project-core.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00617 | $0.00617 |
| Opus 5.5 | $0.00247 | $0.00247 |
| Sonnet 5.5 | $0.00123 | $0.00123 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
00-project-core 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- 00-project-core — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Best Cursor Rules - Project Core
Critical Rules
NO UNNECESSARY FILES - Don't create files outside the defined structure.
FOLLOW MDC FORMAT - All rules must use proper frontmatter (see 01-rule-format.mdc).
Current Date: December 2025
Overview
Purpose: Comprehensive collection of Cursor AI rules for developers Format: MDC files with frontmatter metadata License: CC0 (Public Domain) Maintainer: Renvia Technologies (community-focused)
Project Structure
best-cursor-rules/
├── .github/assets/ # Logos for README (not for users)
├── .cursor/rules/ # THIS repo's own rules
├── rules/
│ ├── frameworks/ # Next.js, React, Vue, Svelte, etc.
│ ├── languages/ # TypeScript, Python, Go, Rust
│ ├── backends/ # Supabase, FastAPI, Node.js
│ ├── mobile/ # React Native, Flutter, SwiftUI
│ ├── styling/ # Tailwind, shadcn/ui
│ ├── testing/ # Vitest, Playwright, Jest
│ ├── best-practices/ # Clean code, security, a11y
│ └── stacks/ # Combined presets (T3, etc.)
├── SETUP-WIZARD.md # Master prompt for users
├── README.md
├── CONTRIBUTING.md
└── LICENSE
Key Files
| File | Purpose |
|---|---|
SETUP-WIZARD.md |
Master prompt users paste into Cursor |
README.md |
Project documentation |
CONTRIBUTING.md |
How to add/edit rules |
rules/**/*.mdc |
Individual cursor rules |
Naming Conventions
Rule Files
- Use lowercase with hyphens:
nextjs-15.mdc,react-native.mdc - Include version only for major versions:
nextjs-15.mdcnotnextjs-15.1.0.mdc - Keep names short but clear
Directories
- Lowercase, plural:
frameworks/,backends/ - No version numbers in directories
Core Principles
- Quality over Quantity - Each rule should be well-tested and useful
- Current Versions - Rules should target 2025 framework versions
- Practical Examples - Include real code examples, not just theory
- User-Friendly - Rules should help, not overwhelm
- No AI Slop - Write like a human, avoid corporate/AI clichés
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.
- 1mo ago First seen · 82 lines · 617 tokens per session scan A 7e1988947f1d
00-project-core is a cursor rule published in the GitHub repository Renvia-code/best-cursor-rules (13 stars, last pushed 11mo ago), licensed CC0-1.0. It adds 617 tokens to every session, about $0.0025 per session on Opus 5.5. 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
project-epic-template-cursorrules-prompt-file
Cursor rules for project development with epic template integration.
ankra-cli
Ankra CLI rules and best practices for managing Kubernetes clusters via the Ankra platform.
kotlin-springboot-rules
A set of coding rules for Kotlin applications built with Spring Boot, a Java-based framework for web services. It covers project layout, naming, Kotlin style, and common design patterns.
angular-novo-elements-cursorrules-prompt-file
Cursor rules for Angular development with Novo Elements UI library.
python-llm-ml-workflow-cursorrules-prompt-file
Cursor rules for Python LLM & ML development with workflow integration.
snowflake-cortex-ai-cursorrules-prompt-file
Cursor rules for Snowflake Cortex AI Functions (AICOMPLETE, AICLASSIFY, AIEXTRACT, etc.) and Cortex Search for RAG applications.