What is llm_router CLAUDE.md?

A project instruction document for an LLM Router Trace Viewer, a tool that sends model requests through a local proxy, saves request traces in SQLite, and displays them in a web interface. It describes a monorepo, meaning one repository containing multiple related packages, plus setup and configuration details.

Use it when developing or debugging the proxy and web packages, configuring the upstream language-model service, installing dependencies, or inspecting stored traces.

It gives a coding agent the project structure, required environment setting, request-routing behavior, and common commands it needs to work safely in the repository.

How tao2years/llm_router configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to tao2years/llm_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/tao2years/llm_router/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/tao2years/llm_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/tao2years/llm_router/claude-md/github.svg)](https://agentmods.dev/instructions/tao2years/llm_router/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/tao2years/llm_router/claude-md"><img src="https://agentmods.dev/badge/instructions/tao2years/llm_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/tao2years/llm_router/claude-md"><img src="https://agentmods.dev/badge/instructions/tao2years/llm_router/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,424 This file is loaded in full into every session.

When invoked 1,424 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	$0.01424	$0.01424
Opus 5.5	$0.00570	$0.00570
Sonnet 5.5	$0.00285	$0.00285
Haiku 4.5	$0.00142	$0.00142

Measured 2mo ago against content hash acbc63dd0ef0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

llm_router 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 · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 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

LLM Router Trace Viewer — a transparent Claude Code wrapper plus debugging proxy. The ccrt CLI launches Claude Code with the original arguments, routes LLM traffic through the local trace proxy, stores traces in SQLite, and visualizes them in a real-time Next.js UI.

Monorepo Structure

Two packages with separate package.json and tsconfig.json:

proxy/ — Express.js proxy server (Node.js, CommonJS, TypeScript → dist/)
web/ — Next.js 15 + React 19 trace viewer (browser/ESM TypeScript)

Configuration

The proxy requires the LLM_UPSTREAM_URL environment variable (base URL of the upstream LLM API, no trailing slash required). Anthropic traffic is sent to {UPSTREAM_URL}/v1/messages; OpenAI-style traffic to {UPSTREAM_URL}/v1/chat/completions. Request headers from the agent (including auth) are forwarded except hop-by-hop fields (host, content-length, connection).

Example:

set LLM_UPSTREAM_URL=https://api.example.com

Commands

Setup

npm run install:all   # Install deps in both proxy/ and web/

Primary wrapper flow

npm run ccrt -- -p "say hello to me"

After npm link, users can run:

ccrt --dangerously-skip-permissions
ccrt -p "say hello to me"

ccrt starts the proxy/API/web services if needed, then passes all arguments through to claude. It sets Claude Code API/proxy environment variables for the child process instead of requiring users to change their persistent Claude config.

Development

npm run dev           # Run both proxy + web concurrently (recommended)
npm run dev:proxy     # Proxy only (ts-node-dev, hot reload)
npm run dev:web       # Web UI only (Next.js, port 3000)
npm run build         # Build proxy + web

Per-package (proxy / web)

cd proxy && npm run dev    # ts-node-dev with hot reload
cd proxy && npm run build && npm start

cd web && npm run dev      # Next.js dev on :3000
cd web && npm run build && npm start

Read the full file on GitHub · 140 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 · 140 lines · 1,424 tokens per session scan A acbc63dd0ef0

Subscribe to this mod's changes

llm_router CLAUDE.md is an instructions file published in the GitHub repository tao2years/llm_router (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 1,424 tokens to every session, about $0.0057 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 2026-08-31.

llm_router CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
llm_router CLAUDE.mdtao2years/llm_router	Instructions file	5	4mo ago	Apache-2.0	A	1,424	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	5,685	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	3,086	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	280k	2d ago	MIT	A	4,325	Codex, OpenCode

llm_router: Instructions file for Claude Code