Borrowing it
Nothing to install: this file belongs to Hertwill/hw-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Hertwill/hw-mcp/master/CLAUDE.mdgit clone --depth 1 https://github.com/Hertwill/hw-mcpWrote 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.
[](https://agentmods.dev/instructions/hertwill/hw-mcp/claude-md)<a href="https://agentmods.dev/instructions/hertwill/hw-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hertwill/hw-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.06105 | $0.06105 |
| Opus 5 | $0.03053 | $0.03053 |
| Sonnet 5 | $0.01221 | $0.01221 |
| Haiku 4.5 | $0.00611 | $0.00611 |
Grade A, and why
hw-mcp 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project
Hertwill MCP
A public Model Context Protocol (MCP) server that wraps the Hertwill dropshipping API, plus a bundled Claude Skill encoding the Hertwill sourcing playbook. It lets any MCP-capable AI agent (Claude Desktop, Cursor, Cline, Continue, Windsurf, Zed, VS Code + Copilot, Goose, OpenCode, Replit) discover Hertwill products, manage an import list, and trigger syncs to Shopify/WooCommerce — turning product sourcing for dropshippers from a multi-step manual workflow into a conversational one.
Core Value: Make sourcing Hertwill products as simple as a single natural-language request from any AI agent. Every scope decision should reduce the friction between "I need winning EU-shippable products under €30" and "they're in my Shopify import list."
Constraints
- Tech stack: TypeScript +
@modelcontextprotocol/sdk(official TS SDK) — biggest community, smallest install footprint, fastest ecosystem updates - Transport: stdio only for v1 — zero infra cost, no uptime burden on Hertwill
- Distribution: npm (public) + GitHub (public repo) — required for directory listings
- Auth model: env var (
HERTWILL_API_KEY) for authenticated endpoints — matches stdio convention, no OAuth infra required - Rate limits: 60 req/min public, 300 req/min authenticated — client must throttle and return structured errors when limits hit
- API compatibility: must stay in sync with Hertwill API changes — versioning strategy needed so the MCP can deprecate tools gracefully
- Security: never log or persist API keys; never ship a default key in the package
Technology Stack
Executive Recommendation
@modelcontextprotocol/sdk@^1.29with the high-levelMcpServer+registerToolAPI overStdioServerTransportzod@^4.3for tool input schemas, leveraging the SDK's built-in Zod-v4 → JSON Schema bridge (nozod-to-json-schemaneeded)- Native
fetch(Node 20+ built-in, undici under the hood) wrapped in a thin client — noaxios, noky, noofetch openapi-typescript@^7.13to generate types from Hertwill's OpenAPI 3.1 spec, consumed viaopenapi-fetch@^0.17for a 6 KB fully-typed clientbottleneck@^2.19for rate limiting (60/min public, 300/min authenticated) +p-retry@^6.2for exponential backoffpino@^10.3piped topino.destination(2)(stderr) — stdout is reserved for JSON-RPCtsup@^8.5for ESM-only build with shebang-injectedbinentryvitest@^4.1for unit/integration tests,@modelcontextprotocol/inspector@^0.21for interactive debugging- Claude Skill bundled as
skills/hertwill-sourcing/SKILL.mdin the same repo, distributed via the same npm package plus a separate "plugin" artifact for Claude Code users
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.
- 8d ago First seen · 207 lines · 6,105 tokens per session scan A 56785ba83af4
hw-mcp CLAUDE.md is an instructions file published in the GitHub repository Hertwill/hw-mcp (5 stars, last pushed 2mo ago), licensed MIT. It adds 6,105 tokens to every session, about $0.0305 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.
Other instructions, from other repositories
vibetags com-example-service-OrderService.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for orderservice, rules for method calculatetax, rules for method processpayment, rules for method validateorder and context & focus.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.