modelfetch: Instructions file for Claude Code

CLAUDE.md

modelfetch CLAUDE.md is an instructions file for Claude Code from phuctm97/modelfetch. It costs 3,340 tokens per session, scanned A, original, MIT.

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 for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is phuctm97/modelfetch's own configuration. It tells Claude Code how to work on modelfetch 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 modelfetch configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import packageJson from "../package.json" with { type: "json" };.

Reuse

Borrowing it

Nothing to install: this file belongs to phuctm97/modelfetch. 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/phuctm97/modelfetch/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/phuctm97/modelfetch

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 modelfetch CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/phuctm97/modelfetch/claude-md/github.svg)](https://agentmods.dev/instructions/phuctm97/modelfetch/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/phuctm97/modelfetch/claude-md"><img src="https://agentmods.dev/badge/instructions/phuctm97/modelfetch/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 modelfetch CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/phuctm97/modelfetch/claude-md"><img src="https://agentmods.dev/badge/instructions/phuctm97/modelfetch/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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. 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 $0.03340 $0.03340
Opus 5.5 $0.01336 $0.01336
Sonnet 5.5 $0.00668 $0.00668
Haiku 4.5 $0.00334 $0.00334

Measured 2mo ago against content hash 21b7cb45fa65, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 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 · 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. 2mo 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 10mo ago), licensed MIT. It adds 3,340 tokens to every session, about $0.0134 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

modelfetch CLAUDE.md compared with instructions from other repositories

modelfetch CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
modelfetch CLAUDE.mdphuctm97/modelfetchInstructions file14510mo agoMITA3,340Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode