Ask Claude to Write a Cloudflare Worker from Scratch

Cloudflare Workers run at the edge with zero cold starts — but setting up routing, environment bindings, and TypeScript types still takes more than a few minutes. Let Claude scaffold it.

Write a Cloudflare Worker that acts as an API proxy. Route GET /api/users to my origin at https://api.example.com. Add an Authorization header using an API_KEY environment variable. Return a 404 JSON response for unknown routes.

Claude produces a clean Worker with a router pattern, a typed Env interface, and a wrangler.toml with the binding already defined:

export interface Env {
  API_KEY: string;
}

export default {
  async fetch(request: Request, env: Env): Promise<Response> {
    const url = new URL(request.url);

    if (url.pathname === '/api/users') {
      return fetch('https://api.example.com/users', {
        headers: { Authorization: `Bearer ${env.API_KEY}` },
      });
    }

    return Response.json({ error: 'Not Found' }, { status: 404 });
  },
};

From there, ask Claude to add Cloudflare KV caching, Durable Objects for stateful coordination, D1 for a SQLite database at the edge, or a rate limiter using the Workers Rate Limiting API.

# Deploy with Wrangler once your Worker is ready
npx wrangler deploy

Ship logic to the edge without fighting the boilerplate.