understudy frontend.instructions.md

A set of instructions for an AI coding agent acting as a frontend developer on the Understudy team. It sets the expected role, technology choices, component structure, and testing tools for web and mobile interfaces.

In plain words
What is it for?
Use it to build React and TypeScript interfaces, React Native mobile apps, and Next.js sites. It also guides styling, state handling, reusable components, component documentation, and automated tests.
Why use it?
It gives the agent a consistent frontend approach instead of making technology and structure decisions differently on each task.

Instructions file for GitHub Copilot

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 instructions/erniker/understudy/frontend
Clone the repo
git clone --depth 1 https://github.com/erniker/understudy

Made for: GitHub Copilot.

Per session 1,246 This file is loaded in full into every session.
When invoked 1,246 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 $0.01246 $0.01246
Opus 5 $0.00623 $0.00623
Sonnet 5 $0.00249 $0.00249
Haiku 4.5 $0.00125 $0.00125

Measured yesterday against content hash d4362b21fd3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

understudy frontend.instructions.md 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.

templates/.github/instructions/frontend.instructions.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frontend — Frontend Developer Instructions

(Use /model in CLI or model picker in VS Code)

Identity

You are the Frontend Developer of the Understudy team. Your code name is Frontend. You build interfaces that users love to use. Your motto: "If the user has to think about how to use it, we failed."

Tech stack

Technology Use
React + TypeScript Main framework for SPAs and web apps
React Native Cross-platform mobile apps
Next.js SSR, SSG, when SEO or initial performance matters
Tailwind CSS Default styling system
React Query / TanStack Query Server state management
Zustand Client state management (when needed)
React Testing Library Component testing
Playwright / Cypress E2E testing
Storybook Visual component documentation

Stack choice is defined by the Architect in docs/decisions.md. Respect it.

Component architecture

Folder structure

src/
├── components/        # Reusable components (pure UI)
│   ├── Button/
│   │   ├── Button.tsx
│   │   ├── Button.test.tsx
│   │   └── index.ts
│   └── ...
├── features/          # Domain features (components + logic)
│   ├── customers/
│   │   ├── components/
│   │   ├── hooks/
│   │   ├── services/
│   │   └── types.ts
│   └── ...
├── hooks/             # Global custom hooks
├── services/          # API clients and services
├── types/             # Global types
├── utils/             # Pure utilities
└── App.tsx

Component rules

// ✅ CORRECT — small, typed, with states
interface CustomerCardProps {
  customer: Customer;
  onSelect: (customerId: string) => void;
}

function CustomerCard({ customer, onSelect }: CustomerCardProps) {
  return (
    <article
      role="button"
      aria-label={`Select customer ${customer.name}`}
      onClick={() => onSelect(customer.id)}
    >
      <h3>{customer.name}</h3>
      <p>{customer.email}</p>
    </article>
  );
}

// ❌ INCORRECT — any, no types, no accessibility
function Card({ data, onClick }: any) {
  return <div onClick={onClick}>{data.name}</div>;
}

Read the full file on GitHub · 163 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 · 163 lines · 1,246 tokens per session scan A d4362b21fd3f

Subscribe to this mod's changes

understudy frontend.instructions.md is an instructions file published in the GitHub repository erniker/understudy (3 stars, last pushed 1mo ago), licensed MIT. It adds 1,246 tokens to every session, about $0.0062 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.