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/nextjs-vercel-supabase-cursorrules-prompt-file)<a href="https://agentmods.dev/rules/patrickjs/awesome-cursorrules/nextjs-vercel-supabase-cursorrules-prompt-file"><img src="https://agentmods.dev/badge/rules/patrickjs/awesome-cursorrules/nextjs-vercel-supabase-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 | $0.01530 | $0.01530 |
| Opus 5 | $0.00765 | $0.00765 |
| Sonnet 5 | $0.00306 | $0.00306 |
| Haiku 4.5 | $0.00153 | $0.00153 |
Grade A, and why
nextjs-vercel-supabase-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 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cursorrules
Intro
I am building 'BA Copilot', where BA stands for Business Analysts. I will sometimes refer to it as bacp.
BA Copilot MVP
Overview
It is an assistant for business analysts. The MVP will be a an ai chatbot type tool, which will render BPMN diagrams using bpmn-js. The user can then iterate on them either with:
- additional discussion
- editing the diagram directly (bpmn-js supports this)
UI Description
Here is a hierarchical, indented bullet description of the BA Copilot MVP, focusing on its functionality for creating and iterating on BPMN diagrams:
BA Copilot Interface
Question Input Section
Users can input questions or requests related to business processes. Example: "Based on the doc content what have I missed?"
Process Section (Optional)
Allows users to upload or view BPMN diagrams in formats like .png, .vsdx, etc. Users can visualize and edit existing diagrams or create new ones. Example: A BPMN diagram showing a flow of "Register expense report", "Approve", and "Deny" processes.
Documents Section (Optional)
Users can upload relevant documents, such as PDFs, that might contain process details. Example: "Shelter - employee handbook.pdf" uploaded to provide context for the BPMN diagram.
Artifacts Section
Provides a space for related outputs or references to be displayed. Example: Diagram suggestions based on uploaded content.
Iterative BPMN Diagram Creation and Modification
Input Process
Users can pose questions or requests for modifications to existing processes. Example: Asking for missing steps in the process based on document content.
AI-Powered Suggestions
The system suggests additions or modifications to the BPMN diagram based on the content of uploaded documents or user queries. Example: Suggestion to add a task for checking the expense policy, citing specific sections from the uploaded handbook.
Diagram Editing
Users can interactively edit the BPMN diagram based on suggestions. Example: Adding a task "Check expense policy" with inputs and outputs like "Expense report" and "Checked expense report".
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 · 142 lines · 1,530 tokens per session scan A a357f10f08a9
nextjs-vercel-supabase-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 1,530 tokens to every session, about $0.0076 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
t3-stack
T3 Stack: tRPC + Prisma + NextAuth integration patterns.
mern-stack
MERN Stack best practices with MongoDB, Express, React, and Node.js.
t3-stack
T3 Stack best practices with Next.js, tRPC, Prisma, Tailwind CSS, and TypeScript.
data-fetching-rules-for-server-components
description: Rules for data fetching in server components in Next.js 14. globs: /app//.tsx.
htmx-and-django-best-practices---general
description: Applies best practices for HTMX and Django integration, focusing on template usage within the 'templates' directory. It encourages using Django's templating engine with HTMX attributes. globs: /templates//.
additional-htmx-and-flask-instructions
Provides additional instructions for HTMX and Flask, primarily related to templating.