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/fbrbovic/cursor-rule-framework/project-configgit clone --depth 1 https://github.com/fbrbovic/cursor-rule-frameworkWhat 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 | $0.00557 | $0.00557 |
| Opus 5 | $0.00279 | $0.00279 |
| Sonnet 5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
project-config 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 2d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
project-config.md
Last-Updated: 2025-06-07
Project Goal
e.g. Build an enterprise ready platform that allows users to build and launch websites
Tech Stack
- Language(s): e.g TypeScript , Javascript
- Framework(s): e.g. Nuxt.js, Encore TS, Vue.js
- Build / Tooling: e.g. pnpm, Turborepo, docker
- Monorepo Structure: e.g Turborepo-managed workspace with apps/frontend and apps/backend
Critical Patterns & Conventions
- When ever possible recommend building an AI-First solution, where solution uses an AI to make the user experience easy and streamlines.
- Prioritize using open source packages whenever you can instead of building your own. Preferred package repository is npm, but do also search for open source github repos.
- Prioritize
@Docsfor internal documentation and@Webfor external resources. - Use
@Gitand@Foldersin combination to understand the codebase structure and history. - Structure tool calls logically, documenting the rationale before execution.
- For complex tasks, break them down into smaller, manageable steps using tool calls.
- When using
@Filesor@Code, specify the file path and relevant code sections clearly. - If a tool call fails, attempt to diagnose the issue using error messages and logs. Refer to the troubleshooting guides if needed:
- @Common Issues
- @Troubleshooting Guide
- Follow consistent naming conventions (e.g., camelCase for variables, PascalCase for classes).
- Use meaningful variable and function names.
- Write clear and concise comments.
- Break down complex functions into smaller, more manageable units.
- Handle errors gracefully and provide informative error messages.
- Write unit and integration tests for critical components.
- Keep code DRY (Don't Repeat Yourself) by abstracting reusable logic into functions or modules.
Constraints
- You have a limited context window (Claude's limitation).
- You can make up to 25 tool calls per turn in Agent Composer mode.
- Adhere to the "Cursor AI Operating Instructions" provided separately.
- Prioritize code quality, maintainability, and security.
- Avoid making assumptions; ask clarifying questions when needed.
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.
- 2d ago First seen · 54 lines · 557 tokens per session scan A eec1e2297aec
project-config is a cursor rule published in the GitHub repository fbrbovic/cursor-rule-framework (33 stars, last pushed 1mo ago), licensed MIT. It adds 557 tokens to every session, about $0.0028 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
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.