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.
npx agentmods add instructions/xiaoliu10/claude-code-router-next/claude-mdgit clone --depth 1 https://github.com/xiaoliu10/claude-code-router-nextWrote 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.
[](https://agentmods.dev/instructions/xiaoliu10/claude-code-router-next/claude-md)<a href="https://agentmods.dev/instructions/xiaoliu10/claude-code-router-next/claude-md"><img src="https://agentmods.dev/badge/instructions/xiaoliu10/claude-code-router-next/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02728 | $0.02728 |
| Opus 5 | $0.01364 | $0.01364 |
| Sonnet 5 | $0.00546 | $0.00546 |
| Haiku 4.5 | $0.00273 | $0.00273 |
Grade A, and why
claude-code-router-next 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 220 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
Claude Code Router is a tool that routes Claude Code requests to different LLM providers. It uses a Monorepo architecture with four main packages:
- cli (
@wengine-ai/claude-code-router-cli): Command-line tool providing theccrcommand - server (
@wengine-ai/claude-code-router-server): Core server handling API routing and transformations - shared (
@wengine-ai/claude-code-router-shared): Shared constants, utilities, and preset management - ui (
@wengine-ai/claude-code-router-ui): Web management interface (React + Vite)
Core Architecture
1. Routing System (packages/server/src/utils/router.ts)
The routing logic determines which model a request should be sent to:
- Default routing: Uses
Router.defaultconfiguration - Project-level routing: Checks
~/.claude/projects/<project-id>/claude-code-router.json - Custom routing: Loads custom JavaScript router function via
CUSTOM_ROUTER_PATH - Built-in scenario routing:
background: Background tasks (typically lightweight models)think: Thinking-intensive tasks (Plan Mode)longContext: Long context (exceedslongContextThresholdtokens)webSearch: Web search tasksimage: Image-related tasks
Token calculation uses tiktoken (cl100k_base) to estimate request size.
2. Transformer System
The project uses the @wengine-ai/llms package (external dependency) to handle request/response transformations. Transformers adapt to different provider API differences:
- Built-in transformers:
anthropic,deepseek,gemini,openrouter,groq,maxtoken,tooluse,reasoning,enhancetool, etc. - Custom transformers: Load external plugins via
transformersarray inconfig.json
Transformer configuration supports:
- Global application (provider level)
- Model-specific application
- Option passing (e.g.,
max_tokensparameter formaxtoken)
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.
- 5d ago First seen · 220 lines · 2,728 tokens per session scan A edbfcc07d2b6
claude-code-router-next CLAUDE.md is an instructions file published in the GitHub repository xiaoliu10/claude-code-router-next (11 stars, last pushed 11d ago), licensed MIT. It adds 2,728 tokens to every session, about $0.0136 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.
Other instructions, from other repositories
ClawRouter CLAUDE.md
Claude Code instructions for BlockRunAI/ClawRouter, covering clawrouter, commands, project structure, key dependencies and conventions.
AI-MarkDone copilot-instructions.md
Instructions for zhaoliangbin42/AI-MarkDone, covering ai copy enhance - ai coding agent instructions, project overview, architecture patterns, adapter pattern for multi-platform support and shadow dom isolation.
freellmpool AGENTS.md
AGENTS.md instructions for 0xzr/freellmpool, covering agent instructions, how to work in this project, starting work, for complex features (multi-file, spec-driven) and available skills.
pcl copilot-instructions.md
Copilot instructions for personamanagmentlayer/pcl, covering project overview, pcl bootstrap system, core architecture principles, 1. compiler pipeline and 2. type system.
AI-MarkDone AGENTS.md
Instructions for zhaoliangbin42/AI-MarkDone, covering ai-markdone engineering guide, project facts, read order, common commands and non-negotiables.
bob-plugin-ollama-translator AGENTS.md
Instructions for CaicoLeung/bob-plugin-ollama-translator, covering repository guidelines, project overview, architecture & data flow, key directories and development commands.