A set of Cursor rules for a demonstration project that uses several coding-agent CLIs, dev containers, and Marp for slides. It defines coding, documentation, dependency, and prompting conventions.

Use it to guide work in the repository, including TypeScript choices, error handling, API documentation, dependency versions, and agent prompts.

It gives coding assistants shared project context and consistent rules for writing, organizing, documenting, and testing code.

How wandb/vibes configures Cursor

Reuse

Borrowing it

Nothing to install: this file belongs to wandb/vibes. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/wandb/vibes/main/.cursorrules

Clone the repo

git clone --depth 1 https://github.com/wandb/vibes

Made for: Cursor.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/wandb/vibes/cursorrules.svg)](https://agentmods.dev/rules/wandb/vibes/cursorrules)

Your own site

<a href="https://agentmods.dev/rules/wandb/vibes/cursorrules"><img src="https://agentmods.dev/badge/rules/wandb/vibes/cursorrules.svg" alt="Measured on agentmods" height="20"></a>

Per session 444 This file is loaded in full into every session.

When invoked 444 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00444	$0.00444
Opus 5	$0.00222	$0.00222
Sonnet 5	$0.00089	$0.00089
Haiku 4.5	$0.00044	$0.00044

Measured 5d ago against content hash 8203e01479cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

cursorrules 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 5d 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.

.cursorrules · 67 lines

What it actually says

Cursor Rules for Vibes Project

Project Context

This is a demonstration repository showing AI coding assistant capabilities using dev containers. The project includes:

Claude Code CLI (@anthropic-ai/claude-code)
Gemini CLI (@google/gemini-cli)
OpenAI Codex (@openai/codex)
Marp for slide generation

Coding Standards

General

Use TypeScript when possible
Prefer functional programming patterns
Write clear, self-documenting code
Include proper error handling

File Structure

Keep related files in logical directories
Use descriptive filenames
Create README files for complex directories

Documentation

Document all public APIs
Include usage examples
Keep documentation up to date with code changes
Use JSDoc for TypeScript/JavaScript functions

Dependencies

Prefer well-maintained packages
Keep dependencies minimal and focused
Use exact versions in package.json for reproducibility

AI Assistant Guidelines

Prompting Best Practices

Provide clear context about the project structure
Specify which CLI tool you're using (Claude, Gemini, or Codex)
Reference the appropriate prompting guide (CLAUDE.md, GEMINI.md, AGENTS.md)

Code Generation

Generate code that follows the project's existing patterns
Include appropriate TypeScript types
Add error handling and edge case considerations
Provide explanations for complex logic

Testing

Include tests for new functionality
Follow existing test patterns in the project
Test edge cases and error conditions

Dev Container Specifics

Use the configured environment variables
Leverage the pre-installed tools and CLIs
Follow the setup instructions in README.md

Commands

pnpm slides - Generate presentation slides using Marp
claude - Start Claude Code CLI
gemini - Start Gemini CLI
codex - Start OpenAI Codex CLI

Notes

This project focuses on demonstration and education
Prioritize clarity and learning over optimization
Include examples that showcase AI assistant capabilities
Keep the codebase accessible to developers of all skill levels

Changes

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.

5d ago First seen · 67 lines · 444 tokens per session scan A 8203e01479cf

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository wandb/vibes (37 stars, last pushed 1y ago), licensed Apache-2.0. It adds 444 tokens to every session, about $0.0022 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 2026-09-02.

Building agents Writing and docs

vibes: Cursor rule for Cursor