agentmods.dev

claude-relay-service: Instructions file for Claude Code

CLAUDE.md

claude-relay-service CLAUDE.md is an instructions file for Claude Code from Wei-Shaw/claude-relay-service. It costs 2,425 tokens per session, scanned A, original, MIT.

Project instructions for a service that routes requests between clients and several AI providers, written partly in Chinese and English.

In plain words
What is it for?
They guide work on routes, services, account management, API conversion, authentication, encryption, logging, and request cleanup.
Why use it?
They give an agent the project structure and rules for keeping business logic, security, data access, and API translation in the right places.

Instructions file for Claude Code

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

This is Wei-Shaw/claude-relay-service's own configuration. It tells Claude Code how to work on claude-relay-service 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 claude-relay-service configures →

not rated 13krepo +8 today A scan 2,425 tokens original MIT
View source ↗ Wei-Shaw/claude-relay-service pincc.ai
About the project

Claude Relay Service is a self-hosted relay that lets users connect Claude Code and other listed AI clients to managed Claude accounts through their own server. It is intended for people who need self-managed access, multiple-account rotation, shared subscription costs, usage tracking, and monitoring.

Wei-Shaw/claude-relay-service · 12,601 stars · on GitHub · pincc.ai

Reuse

Borrowing it

Nothing to install: this file belongs to Wei-Shaw/claude-relay-service. 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/Wei-Shaw/claude-relay-service/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Wei-Shaw/claude-relay-service

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 claude-relay-service CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/wei-shaw/claude-relay-service/claude-md"><img src="https://agentmods.dev/badge/instructions/wei-shaw/claude-relay-service/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,425 This file is loaded in full into every session.
When invoked 2,425 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 $0.02425 $0.02425
Opus 5 $0.01213 $0.01213
Sonnet 5 $0.00485 $0.00485
Haiku 4.5 $0.00243 $0.00243

Measured 10d ago against content hash b74156fde4e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

claude-relay-service 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 10d 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 · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 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.

项目概述

Claude Relay Service — 多平台 AI API 中转服务，作为客户端与上游 AI API 之间的中间件。 支持 Claude (官方/Console)、Gemini、OpenAI Responses、AWS Bedrock、Azure OpenAI、Droid、CCR 等账户类型。 核心能力：多账户管理、API Key 认证、统一调度、代理配置、限流、成本统计。

架构原则

Clean Architecture 分层映射

层级 目录 职责
框架层 src/routes/, src/middleware/ HTTP 路由、请求验证、响应格式化
接口适配层 src/handlers/, src/services/openaiToClaude.js 请求/响应格式转换
用例层 src/services/*Scheduler.js, *RelayService.js 调度逻辑、转发编排
实体层 src/services/*AccountService.js, src/models/ 账户管理、数据模型
基础设施层 src/utils/, config/ 日志、缓存、加密、代理

开发原则

  • 依赖方向: 外层 → 内层，内层不知道外层存在
  • 新增路由: 只做参数提取和响应格式化，业务逻辑放 service
  • 新增服务: 先确定属于哪一层，遵循该层职责边界
  • 格式转换: 不同 API 格式的转换放 handlers 或专用转换服务
  • 数据访问: 通过 src/models/redis.js 统一访问

安全约束

  • 敏感数据（OAuth token、refreshToken、credentials）必须 AES 加密存储（参考 claudeAccountService.js）
  • API Key 使用 SHA-256 哈希存储，禁止明文
  • 每个请求必须经过完整认证链（API Key → 权限 → 客户端限制 → 模型黑名单）
  • 客户端断开时必须通过 AbortController 清理资源和并发计数
  • 日志中禁止输出完整 token，使用 tokenMask.js 脱敏

项目结构

src/
├── routes/              # HTTP 路由
│   ├── api.js           # Claude API 主路由
│   ├── admin/           # 管理后台路由（24个子文件）
│   ├── geminiRoutes.js, standardGeminiRoutes.js
│   ├── openaiRoutes.js, openaiClaudeRoutes.js, openaiGeminiRoutes.js
│   ├── azureOpenaiRoutes.js, droidRoutes.js
│   ├── userRoutes.js, webhook.js, unified.js, apiStats.js, web.js
├── middleware/           # auth.js(认证/权限/限流), browserFallback.js
├── handlers/             # geminiHandlers.js
├── services/             # 业务服务
│   ├── relay/                 # 各平台转发服务（9个）
│   ├── account/               # 各平台账户管理（11个）
│   ├── scheduler/             # 统一调度器（4个）
│   ├── apiKeyService.js       # API Key 管理
│   ├── pricingService.js      # 定价和成本
│   └── ...                    # 其余 ~30 个业务服务
├── models/redis.js       # Redis 数据模型
├── utils/                # 35+ 工具文件（logger, proxy, oauth, cache, stream...）
config/config.js          # 主配置
scripts/                  # 运维脚本
cli/                      # CLI 工具
web/admin-spa/            # Vue SPA 管理界面
data/init.json            # 管理员凭据

Read the full file on GitHub · 189 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. 10d ago First seen · 189 lines · 2,425 tokens per session scan A b74156fde4e7

Subscribe to this mod's changes

claude-relay-service CLAUDE.md is an instructions file published in the GitHub repository Wei-Shaw/claude-relay-service (12,601 stars, last pushed today), licensed MIT. It adds 2,425 tokens to every session, about $0.0121 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.

Claude Codeclaudeclaude-apiclaude-proxycodex-cligemini-cli
Related

Other instructions, from other repositories

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens