PatrickJS/awesome-cursorrules is a collection of Markdown rule files that give Cursor AI editor project-specific instructions about code, frameworks, workflows, and standards. Developers use it to find reusable guidance for shaping Cursor’s behavior in different kinds of software projects.
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/PatrickJS/awesome-cursorrulesWrote 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/patrickjs/awesome-cursorrules/readme-best-practices-cursorrules-prompt-file)<a href="https://agentmods.dev/rules/patrickjs/awesome-cursorrules/readme-best-practices-cursorrules-prompt-file"><img src="https://agentmods.dev/badge/rules/patrickjs/awesome-cursorrules/readme-best-practices-cursorrules-prompt-file.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 5.1 | $0.00238 | $0.00238 |
| Opus 5 | $0.00119 | $0.00119 |
| Sonnet 5 | $0.00048 | $0.00048 |
| Haiku 4.5 | $0.00024 | $0.00024 |
Grade A, and why
readme-best-practices-cursorrules-prompt-file 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 4d 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.
What it actually says
Write READMEs like landing pages, not API docs. The reader decides in 3-5 seconds.
Start with a bold one-liner saying what it does and why someone should care. Not "A tool that..." - a punchline. Put a working code example in the first 5 lines. Show the value prop immediately. Use feature tables (two columns) instead of Feature: bullet lists. Tables scan faster. Quick Start must be copy-paste ready. No $ prefix on bash commands. Zero to running in 30 seconds. Vary sentence lengths and structure. Mix one-liners with short paragraphs and tables. Not walls of same-length bullets. Never use "seamless", "robust", "comprehensive", "cutting-edge", or other AI marketing words. Never open with "In today's..." or close with "Happy coding!" Check that referenced assets (demo.gif, screenshots) actually exist on disk before adding image links. Author section should include a visual card or badge, not just plain text "Made by username".
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.
- 4d ago First seen · 17 lines · 238 tokens per session scan A 3f65a946db00
readme-best-practices-cursorrules-prompt-file is a cursor rule published in the GitHub repository PatrickJS/awesome-cursorrules (40,734 stars, last pushed 3mo ago), licensed CC0-1.0. It adds 238 tokens to every session, about $0.0012 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 2026-09-03.
Other cursor rules, from other repositories
documentation
Documentation: code docs, READMEs, ADRs, maintenance.
snyk_rules
Snyk Security At Inception.
Analyze-Data
Analyzes provided datasets, metrics, or structured data files (CSV, JSON, etc.) to identify trends, patterns, summaries, or answer specific questions about the data.
document-dependencies
"Proper specification is 50% of the work" - Once the specification is perfect, building the project becomes easier - it's like a puzzle. Documents must be built in the correct order, with each piece depending on previous ones.
cursorrules
// Good: Use anyhow for application errors use anyhow::{Context, Result}.
database
Drizzle ORM and database conventions for the API package.