What is gateway CLAUDE.md?

Repository instructions for Claude Code, an AI coding assistant, explaining how to develop the Portkey AI Gateway, software that sends requests to different large language model services through one system.

Starting the gateway, building it, testing its main code and plugins, checking formatting, and deploying it to Cloudflare Workers or Node.js.

It gives the assistant the project’s commands for development, testing, formatting, building, and deployment instead of leaving those choices unclear.

How Portkey-AI/gateway configures Claude Code

About the project

Portkey AI Gateway is an open-source service that gives applications one interface for routing requests to language, vision, audio, and image models. Teams use it to connect AI applications to many model providers while handling retries, fallbacks, load balancing, and guardrails.

Portkey-AI/gateway · 13,329 stars · on GitHub · portkey.ai

Reuse

Borrowing it

Nothing to install: this file belongs to Portkey-AI/gateway. 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/Portkey-AI/gateway/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Portkey-AI/gateway

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/portkey-ai/gateway/claude-md/github.svg)](https://agentmods.dev/instructions/portkey-ai/gateway/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/portkey-ai/gateway/claude-md"><img src="https://agentmods.dev/badge/instructions/portkey-ai/gateway/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/portkey-ai/gateway/claude-md"><img src="https://agentmods.dev/badge/instructions/portkey-ai/gateway/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 844 This file is loaded in full into every session.

When invoked 844 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.

Model	Per session	Once invoked
Fable 5.1	$0.00844	$0.00844
Opus 5.5	$0.00338	$0.00338
Sonnet 5.5	$0.00169	$0.00169
Haiku 4.5	$0.00084	$0.00084

Measured 2mo ago against content hash 9e4cf61d38e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gateway 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 · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 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.

Project Overview

This is the Portkey AI Gateway - a fast, reliable AI gateway that routes requests to 250+ LLMs with sub-1ms latency. It's built with Hono framework for TypeScript/JavaScript and can be deployed to multiple environments including Cloudflare Workers, Node.js servers, and Docker containers.

Development Commands

Core Development

npm run dev - Start development server using Wrangler (Cloudflare Workers)
npm run dev:node - Start development server using Node.js
npm run build - Build the project for production
npm run build-plugins - Build the plugin system

Testing

npm run test:gateway - Run tests for the main gateway code (src/)
npm run test:plugins - Run tests for plugins
jest src/ - Run specific gateway tests
jest plugins/ - Run specific plugin tests

Code Quality

npm run format - Format code with Prettier
npm run format:check - Check code formatting
npm run pretty - Alternative format command

Deployment

npm run deploy - Deploy to Cloudflare Workers
npm run start:node - Start production Node.js server

Architecture

Core Components

Main Application (src/index.ts)

Hono-based HTTP server with middleware pipeline
Handles multiple AI provider integrations
Routes: /v1/chat/completions, /v1/completions, /v1/embeddings, etc.

Provider System (src/providers/)

Modular provider implementations (OpenAI, Anthropic, Azure, etc.)
Each provider has standardized interface: api.ts, chatComplete.ts, embed.ts
Provider configs define supported features and transformations

Middleware Pipeline

requestValidator - Validates incoming requests
hooks - Pre/post request hooks
memoryCache - Response caching
logger - Request/response logging
adminAuth - Node-only local UI session auth for /public/* login endpoints and /log/stream
portkey - Core Portkey-specific middleware for routing, guardrails, etc.

Read the full file on GitHub · 95 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.

2mo ago First seen · 95 lines · 844 tokens per session scan A 9e4cf61d38e7

Subscribe to this mod's changes

gateway CLAUDE.md is an instructions file published in the GitHub repository Portkey-AI/gateway (13,329 stars, last pushed 5mo ago), licensed MIT. It adds 844 tokens to every session, about $0.0034 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.

Backend and APIs LangChain ai-gateway gateway generative-ai llmops llms

gateway CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gateway CLAUDE.mdPortkey-AI/gateway	Instructions file	13k	5mo ago	MIT	A	844	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

gateway: Instructions file for Claude Code