Cloudflare Hyperdrive

What it does

When your agent uses it

• PostgreSQL/MySQL
• Encountering pool errors
• Connection refused

Example prompts

• “/cloudflare-hyperdrive”

Requirements

• Node.js
• A Bash shell

Workflow steps

4 steps, taken from the step headings in SKILL.md.

1. 1Create Hyperdrive Config
2. 2Configure Binding
3. 3Install Driver
4. 4Query Database

What it can do on your machine

Read from SKILL.md and the folder at commit 8837836. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (TypeScript and Shell, from the files we listed), which the agent can run.

  Shell commands in SKILL.md call:

  • bunx
  • bun

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • developers.cloudflare.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cloudflare Hyperdrive loads about 1.8k tokens when it runs, and up to ~27k if it reads all its reference files. Until then it costs about 52 tokens; SKILL.md has 372 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~52

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~27k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from secondsky/claude-skills at commit 8837836, republished under its MIT licence (© secondsky). 372 words, ~1,845 tokens.

name

cloudflare-hyperdrive

description

Cloudflare Hyperdrive for Workers-to-database connections with pooling and caching. Use for PostgreSQL/MySQL, Drizzle/Prisma, or encountering pool errors, TLS issues, connection refused.

license

MIT

metadata.version

2.0.0

metadata.last_verified

2025-11-18

metadata.production_tested

true

metadata.token_savings

~58%

metadata.errors_prevented

6

metadata.templates_included

0

metadata.references_included

1

metadata.keywords

hyperdrive, cloudflare hyperdrive, workers hyperdrive, postgres workers, mysql workers, connection pooling, query caching, node-postgres, pg, postgres.js…

bunx wrangler hyperdrive create my-db \
  --connection-string="postgres://user:pass@host:5432/database"

{
  "name": "my-worker",
  "main": "src/index.ts",
  "compatibility_date": "2024-09-23",
  "compatibility_flags": ["nodejs_compat"],  // REQUIRED!
  "hyperdrive": [
    {
      "binding": "HYPERDRIVE",
      "id": "<ID_FROM_STEP_1>"
    }
  ]
}

bun add pg  # or postgres, or mysql2

import { Client } from 'pg';

export default {
  async fetch(request, env, ctx) {
    const client = new Client({ connectionString: env.HYPERDRIVE.connectionString });
    await client.connect();

    const result = await client.query('SELECT * FROM users LIMIT 10');
    await client.end();

    return Response.json(result.rows);
  }
};

import { Client } from 'pg';

const client = new Client({ connectionString: env.HYPERDRIVE.connectionString });
await client.connect();
const result = await client.query('SELECT * FROM users');
await client.end();

import postgres from 'postgres';

const sql = postgres(env.HYPERDRIVE.connectionString);
const users = await sql`SELECT * FROM users`;

import mysql from 'mysql2/promise';

const connection = await mysql.createConnection(env.HYPERDRIVE.connectionString);
const [rows] = await connection.execute('SELECT * FROM users');
await connection.end();

import { drizzle } from 'drizzle-orm/node-postgres';
import { Client } from 'pg';

const client = new Client({ connectionString: env.HYPERDRIVE.connectionString });
await client.connect();

const db = drizzle(client);
const users = await db.select().from(usersTable);

await client.end();

export default {
  async fetch(request, env, ctx) {
    const client = new Client({ connectionString: env.HYPERDRIVE.connectionString });
    await client.connect();

    const users = await client.query('SELECT * FROM users WHERE active = true');
    await client.end();

    return Response.json(users.rows);
  }
};

const userId = new URL(request.url).searchParams.get('id');

const client = new Client({ connectionString: env.HYPERDRIVE.connectionString });
await client.connect();

const result = await client.query(
  'SELECT * FROM users WHERE id = $1',
  [userId]
);

await client.end();

const client = new Client({ connectionString: env.HYPERDRIVE.connectionString });
await client.connect();

try {
  await client.query('BEGIN');
  await client.query('UPDATE accounts SET balance = balance - 100 WHERE id = $1', [1]);
  await client.query('UPDATE accounts SET balance = balance + 100 WHERE id = $1', [2]);
  await client.query('COMMIT');
} catch (e) {
  await client.query('ROLLBACK');
  throw e;
} finally {
  await client.end();
}

© secondsky, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 19 other files (scripts, references) in plugins/cloudflare-hyperdrive/skills/cloudflare-hyperdrive of secondsky/claude-skills.

• SKILL.md
• references/connection-pooling.md
• references/drizzle-integration.md
• references/prisma-integration.md
• references/query-caching.md
• references/setup-guide.md
• references/supported-databases.md
• references/tls-ssl-setup.md
• references/troubleshooting.md
• references/wrangler-commands.md
• scripts/check-versions.sh
• templates/drizzle-mysql.ts
• templates/drizzle-postgres.ts
• templates/local-dev-setup.sh
• templates/mysql2-basic.ts
• templates/postgres-basic.ts
• templates/postgres-js.ts
• templates/postgres-pool.ts
• … and 2 more

Open the folder on GitHubat commit 8837836