guidelines

A set of coding rules for an Air Jam project, including its tools, libraries, naming conventions, and refactoring practices.

In plain words
What is it for?
Use it when choosing package, styling, frontend, state, validation, form, data-fetching, linting, formatting, and TypeScript tools or conventions.
Why use it?
It gives contributors one consistent way to build, validate, organize, and refactor the code.

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/vucinatim/air-jam/guidelines
Clone the repo
git clone --depth 1 https://github.com/vucinatim/air-jam

Made for: Cursor.

Per session 397 This file is loaded in full into every session.
When invoked 397 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 $0.00397 $0.00397
Opus 5 $0.00198 $0.00198
Sonnet 5 $0.00079 $0.00079
Haiku 4.5 $0.00040 $0.00040

Measured 2d ago against content hash ee2ae663fc34, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

guidelines 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.

.cursor/rules/guidelines.mdc · 39 lines

What it actually says

Tooling

  • Use pnpm for package manager
  • Use Tailwind CSS for styling
  • Use Shadcn UI for components
  • Use React for the frontend
  • Use TypeScript for everything
  • Use Vite or Next.js for the build
  • Use ESLint for linting
  • Use Prettier for formatting
  • Use zustand for state management
  • Use zod for validation
  • Use react-hook-form for form handling
  • Use tanstack-query for data fetching

Conventions

  • Use camelCase for variables
  • Use PascalCase for components
  • Use kebab-case for files
  • Use "const ComponentName = (props: Props) => {}" for components (not React.FC or function component)
  • Do NOT use index.ts files for aggregating multiple exports
  • Do NOT pass props when they can be accessed through a zustand store or a provider context

Refactoring

  • When extracting components:
    • Create a new file in the components folder if the component is reused across multiple files
    • Write the component in the same file if the component is only used in one file

Tips

  • When writing tool / util functions use JSDoc to add a description and maybe example if needed (without @param and @returns)
  • Use tsc for typechecking.

Notes

  • We are using a monorepo with pnpm and vite and next.js
  • Shared package is used to share schemas and types between the packages
  • We are using R2 for cloud storage
  • We are using postgres with drizzle for the database

Instructions

  • Always use the latest version of the libraries and tools - by installing them with pnpm
  • Write clean, readable, logical, structured, extensible and maintainable codebase.
  • NEVER think or design for backwards compatibility! Always rewrite and change all usages in code to the new system.
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. 2d ago First seen · 39 lines · 397 tokens per session scan A ee2ae663fc34

Subscribe to this mod's changes

guidelines is a cursor rule published in the GitHub repository vucinatim/air-jam (5 stars, last pushed 3d ago), licensed MIT. It adds 397 tokens to every session, about $0.0020 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.