sdk: Instructions file for Claude Code

CLAUDE.md

sdk CLAUDE.md is an instructions file for Claude Code from vargHQ/sdk. It costs 1,212 tokens per session, scanned A, original, Apache-2.0.

Project instructions for a media-generation SDK that uses Bun, a JavaScript runtime and toolkit, instead of Node.js or npm. They describe the command-line actions, providers, file locations, and test and build commands.

In plain words
What is it for?
Use them to run image, video, voice, music, transcription, caption, synchronization, upload, editing, and other listed actions, using local files or URLs.
Why use it?
They give contributors one consistent way to run the SDK and prevent confusion between similar JavaScript tools and commands.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: positional $N argument.

This is vargHQ/sdk's own configuration. It tells Claude Code how to work on sdk itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sdk configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vargHQ/sdk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vargHQ/sdk/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/vargHQ/sdk

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for sdk CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/varghq/sdk/claude-md/github.svg)](https://agentmods.dev/instructions/varghq/sdk/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/varghq/sdk/claude-md"><img src="https://agentmods.dev/badge/instructions/varghq/sdk/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for sdk CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/varghq/sdk/claude-md"><img src="https://agentmods.dev/badge/instructions/varghq/sdk/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,212 This file is loaded in full into every session.
When invoked 1,212 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01212 $0.01212
Opus 5.5 $0.00485 $0.00485
Sonnet 5.5 $0.00242 $0.00242
Haiku 4.5 $0.00121 $0.00121

Measured 2mo ago against content hash 61204f7b56dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sdk CLAUDE.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 2mo 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.

CLAUDE.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Default to using Bun instead of Node.js.

Working with this SDK

  • Use the varg CLI: Run actions via bun run src/cli/index.ts run <action> [options]

    • Use --quiet for minimal output (recommended for scripts)
    • Use --json for JSON output
    • Example: bun run src/cli/index.ts run video --prompt "sunset over ocean" --quiet
  • Available actions: image, video, voice, music, transcribe, captions, sync, upload, edit

  • List actions: bun run src/cli/index.ts list

  • Action help: bun run src/cli/index.ts run <action> --help

  • Media folders: Store input files in media/ folder, outputs go to output/ folder

  • Local file support: Actions support local file paths (e.g., media/image.png) in addition to URLs

  • Providers: Located in src/providers/ (fal, elevenlabs, replicate, groq, etc.)

  • Action definitions: Located in src/definitions/actions/

  • Use bun <file> instead of node <file> or ts-node <file>

  • Use bun test instead of jest or vitest

  • Use bun build <file.html|file.ts|file.css> instead of webpack or esbuild

  • Use bun install instead of npm install or yarn install or pnpm install

  • Use bun run <script> instead of npm run <script> or yarn run <script> or pnpm run <script>

  • Bun automatically loads .env, so don't use dotenv.

APIs

  • Bun.serve() supports WebSockets, HTTPS, and routes. Don't use express.
  • bun:sqlite for SQLite. Don't use better-sqlite3.
  • Bun.redis for Redis. Don't use ioredis.
  • Bun.sql for Postgres. Don't use pg or postgres.js.
  • WebSocket is built-in. Don't use ws.
  • Prefer Bun.file over node:fs's readFile/writeFile
  • Bun.$ls instead of execa.

Testing

Use bun test to run tests.

import { test, expect } from "bun:test";

test("hello world", () => {
  expect(1).toBe(1);
});

Frontend

Use HTML imports with Bun.serve(). Don't use vite. HTML imports fully support React, CSS, Tailwind.

Server:

import index from "./index.html"

Bun.serve({
  routes: {
    "/": index,
    "/api/users/:id": {
      GET: (req) => {
        return new Response(JSON.stringify({ id: req.params.id }));
      },
    },
  },
  // optional websocket support
  websocket: {
    open: (ws) => {
      ws.send("Hello, world!");
    },
    message: (ws, message) => {
      ws.send(message);
    },
    close: (ws) => {
      // handle close
    }
  },
  development: {
    hmr: true,
    console: true,
  }
})

Read the full file on GitHub · 140 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. 2mo ago First seen · 140 lines · 1,212 tokens per session scan A 61204f7b56dd

Subscribe to this mod's changes

sdk CLAUDE.md is an instructions file published in the GitHub repository vargHQ/sdk (341 stars, last pushed 6d ago), licensed Apache-2.0. It adds 1,212 tokens to every session, about $0.0048 per session on Opus 5.5. 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 2026-08-30.

Related

sdk CLAUDE.md compared with instructions from other repositories

sdk CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
sdk CLAUDE.mdvargHQ/sdkInstructions file3416d agoApache-2.0A1,212Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k2d agoMITA4,313Codex, OpenCode