What is claude-router CLAUDE.md?

Repository instructions for a universal Claude Code proxy that sends requests through a Python FastAPI server to local Ollama models and adapts to different projects.

Useful for setting up the router, connecting Claude Code to a project, and developing its request handling, path inference, or Ollama integration.

They explain how to start the proxy and how Claude Code connects to projects with different languages or folder layouts.

How say828/claude-router configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to say828/claude-router. 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/say828/claude-router/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/say828/claude-router

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/say828/claude-router/claude-md/github.svg)](https://agentmods.dev/instructions/say828/claude-router/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/say828/claude-router/claude-md"><img src="https://agentmods.dev/badge/instructions/say828/claude-router/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/say828/claude-router/claude-md"><img src="https://agentmods.dev/badge/instructions/say828/claude-router/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,156 This file is loaded in full into every session.

When invoked 2,156 The same file — it is already loaded in full.

Security scan B 1 finding. 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	$0.02156	$0.02156
Opus 5	$0.01078	$0.01078
Sonnet 5	$0.00431	$0.00431
Haiku 4.5	$0.00216	$0.00216

Measured 9d ago against content hash 59a76bdc3f5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

claude-router CLAUDE.md scanned grade B with 1 finding 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 9d 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

- Enable all tools with `allowedTools: ["*"]`

CLAUDE.md · 256 lines

How it starts

The opening of the file, as written. The whole thing — 256 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.

Overview

This is a universal Claude Router proxy server that connects local Ollama servers with GPT-OSS models to provide Claude Code functionality for ANY project. The Python FastAPI application acts as a proxy between Claude Code and local Ollama instances.

Universal Usage

🌍 Works with any project: Python, JavaScript, React, Go, Rust, etc.
📁 Adaptive to any folder structure: Automatically infers project patterns
🔧 Zero configuration: Just run ./run.sh and connect Claude Code
🎯 Smart path inference: Understands context and creates appropriate file structures

How to Use with Any Project

Start the Claude Router (one-time setup):
```
cd claude-router/
./run.sh
```
Navigate to YOUR project:
```
cd /path/to/your/awesome-project/
```
Open Claude Code in your project:
- Claude Code will automatically use http://localhost:4000 (configured by router)
- The router adapts to your project structure automatically
Start coding naturally:
- "create auth service" → Creates appropriate auth files for your stack
- "read the README" → Finds and reads your project's README
- "add a component" → Creates components in the right location for your framework

Architecture

Core Components

src/main.py: FastAPI proxy server that handles Anthropic Messages API compatibility
- Converts Claude message format to Ollama prompts
- Streams responses from Ollama back to Claude Code
- Handles /v1/messages, /health, and root endpoints
- Supports tool calling with proper Ollama format conversion
src/util.py: Utility functions for message and tool conversion
- convert_claude_tools_to_ollama(): Converts Claude tool format to Ollama function calling format
- convert_messages_to_ollama_format(): Handles message format conversion
- add_tool_instruction(): Adds system instructions for tool usage
- generate_signature(): Creates HMAC signatures for thinking blocks

Read the full file on GitHub · 256 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.

9d ago First seen · 256 lines · 2,156 tokens per session scan B 59a76bdc3f5b

Subscribe to this mod's changes

claude-router CLAUDE.md is an instructions file published in the GitHub repository say828/claude-router (56 stars, last pushed 1y ago), licensed MIT. It adds 2,156 tokens to every session, about $0.0108 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Backend and APIs Building agents

vibe-coding-prompt-template backend.instructions.md

Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.

KhazP/vibe-coding-prompt-template · 139 tokens

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.

vercel/next.js · 7,296 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 · 5,153 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

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

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 · 4,469 tokens

claude-router: Instructions file for Claude Code