start

A project rulebook covering the code structure, required technologies, styling, quality practices, and deployment commands for a TypeScript application.

In plain words
What is it for?
Use it when adding or changing code in the project, especially Three.js features, server and UI files, styles, tests, or Cloudflare Worker deployment.
Why use it?
It gives coding agents consistent project boundaries, so new code fits the existing client, server, user interface, and deployment setup.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/benallfree/vibescale/start
Clone the repo
git clone --depth 1 https://github.com/benallfree/vibescale

Made for: Cursor.

Per session 759 This file is loaded in full into every session.
When invoked 759 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00759 $0.00759
Opus 5 $0.00380 $0.00380
Sonnet 5 $0.00152 $0.00152
Haiku 4.5 $0.00076 $0.00076

Measured yesterday against content hash 3f81391631c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

start 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 yesterday.

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.

.cursor/rules/start.mdc · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Guidelines

Core Architecture

  • Bun is our package manager.
  • Three.js is the ONLY library allowed. Everything else must be created from scratch.
  • Absolutely no build chain other than Vite.
  • Use TypeScript everywhere.
  • Use early returns.
  • To deploy, run bun run build && bun run deploy from the root directory. They are set up properly.

Directory Structure

  • The project is now split into two main parts:

    • /client - Client library implementation

      • /src - Source code for the client library
      • Package managed independently with its own package.json
      • Uses tsup for building
    • /server - Main application server

      • /src - Server and web application source code:
        • /server - Server implementation
        • /ui - User interface components
        • /utils - Utility functions
        • /styles - Global styles and CSS configuration
        • /templates - Template files and network-related functionality
        • main.ts - Application entry point
        • state.ts - State management
        • router.ts - Application routing
      • /public - Static public assets
      • /assets - Application assets
      • Uses Wrangler for Cloudflare Workers deployment
  • Tailwind/DaisyUI is available in the server's styles directory

  • The project uses Vite-Cloudflare integration for unified client/server development in the server package

Styling Guidelines

  • Avoid inline styles and use Tailwind/Daisy styling or add styles to custom local CSS files that sit with the component.
  • Use the provided Tailwind/DaisyUI classes for consistent styling.
  • Create component-specific CSS files when needed, co-located with the component.
  • Global styles are maintained in /styles/styles.css
  • Prism-specific styles are in /styles/prism.css

Code Quality

  • Practice aggressive separation of concerns.
  • After each task is done, please review all the code and recommend the most important single refactoring that is both helpful and minimal.
  • Always discuss a plan first and wait for approval before coding a solution. Two separate interactions minimum.
  • Follow the Prettier configuration in package.json for consistent code formatting.
  • Use TypeScript types for all variables, functions, and components.
  • Implement proper error handling and type checking.

Read the full file on GitHub · 89 lines

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.

  1. yesterday First seen · 89 lines · 759 tokens per session scan A 3f81391631c9

Subscribe to this mod's changes

start is a cursor rule published in the GitHub repository benallfree/vibescale (4 stars, last pushed 1y ago), licensed MIT. It adds 759 tokens to every session, about $0.0038 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 2026-08-31.