modelfetch CLAUDE.md

Repository instructions for working on ModelFetch, a TypeScript and JavaScript SDK for building and deploying MCP servers. They describe the repository, its Nx workspace, packages, and development procedures.

In plain words
What is it for?
Use them when modifying ModelFetch, navigating its runtime-specific packages, understanding its workspace configuration, or following its development guidelines.
Why use it?
They give the coding agent context about the project’s purpose, package layout, workspace setup, and expected ways of working.

Instructions file

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/phuctm97/modelfetch/claude-md
Clone the repo
git clone --depth 1 https://github.com/phuctm97/modelfetch
Per session 3,340 This file is loaded in full into every session.
When invoked 3,340 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 $0.03340 $0.03340
Opus 5 $0.01670 $0.01670
Sonnet 5 $0.00668 $0.00668
Haiku 4.5 $0.00334 $0.00334

Measured 2d ago against content hash 21b7cb45fa65, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

modelfetch 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 2d 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 · 404 lines

How it starts

The opening of the file, as written. The whole thing — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Repository Overview

This repository contains the source code of ModelFetch: a TypeScript/JavaScript SDK for building MCP (Model Context Protocol) servers with a delightful developer experience and deploying them anywhere TypeScript/JavaScript runs.

The SDK is built as a thin wrapper on top of hono and @hono/mcp, leveraging Hono's runtime-agnostic capabilities. The SDK provides runtime-specific packages to handle all runtime-specific details:

  • @modelfetch/node - Node.js runtime support
  • @modelfetch/next - Next.js runtime support
  • @modelfetch/bun - Bun runtime support
  • @modelfetch/deno - Deno runtime support
  • @modelfetch/vercel - Vercel runtime support
  • @modelfetch/cloudflare - Cloudflare runtime support
  • @modelfetch/netlify - Netlify runtime support
  • @modelfetch/fastly - Fastly runtime support
  • @modelfetch/supabase - Supabase runtime support
  • @modelfetch/gcore - Gcore runtime support
  • @modelfetch/aws-lambda - AWS Lambda runtime support
  • @modelfetch/azure-functions - Azure Functions runtime support

Each package acts as a thin wrapper around the equivalent Hono package, ensuring optimal performance and compatibility. Additionally, each package maintains a consistent API across different runtimes.

The modelfetch CLI provides an exceptional developer experience with:

  • dev command for running MCP servers in development mode with hot reload
  • Integration with the MCP inspector for a seamless testing and debugging experience

Goal: To become the world's most popular TypeScript/JavaScript SDK for building MCP servers.

Workspace Overview

This workspace follows Nx best practices as outlined in @.cursor/rules/nx-rules.mdc

Workspace Configurations

  • Node.js version: @.nvmrc
  • TypeScript configurations: @tsconfig.base.json @tsconfig.node.json @tsconfig.next.json @tsconfig.bun.json @tsconfig.deno.json
  • TypeScript project references are used to improve the performance of TypeScript-related features
    • All TypeScript projects are referenced in the root @tsconfig.json
    • When adding or removing a TypeScript project as a local dependency to another TypeScript project, update the target project's tsconfig.json to add or remove the dependency project in its references
  • Only TypeScript projects have ESLint configurations
  • All JavaScript projects have no ESLint configurations
  • All Nx projects use automatic configuration provided by Nx plugins instead of individual project.json files
  • All local dependencies use workspace:^ version specifier
  • dependencies and devDependencies that are already available in the root @package.json should NOT be included in individual project package.json files. This includes common dependencies like typescript, @types/node, eslint, prettier, nx, @nx/*, @swc/*, etc.

Read the full file on GitHub · 404 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. 2d ago First seen · 404 lines · 3,340 tokens per session scan A 21b7cb45fa65

Subscribe to this mod's changes

modelfetch CLAUDE.md is an instructions file published in the GitHub repository phuctm97/modelfetch (145 stars, last pushed 8mo ago), licensed MIT. It adds 3,340 tokens to every session, about $0.0167 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 2026-08-30.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 6,785 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens