What is ai-proxy CLAUDE.md?

Development instructions for AI Proxy, a local desktop application that converts requests between OpenAI, Anthropic, and Google Gemini formats. It uses a Rust backend, a Vue frontend, and a local endpoint.

Use them when changing the AI Proxy desktop app, its request-conversion layer, its Vue interface, or its Rust code. They also provide commands for frontend builds and Rust tests.

They explain the project's two-part structure and give commands for running, building, formatting, and testing it, so an AI coding agent can work within its conventions.

How mrhuangyong/ai-proxy configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mrhuangyong/ai-proxy. 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/mrhuangyong/ai-proxy/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/mrhuangyong/ai-proxy

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/mrhuangyong/ai-proxy/claude-md/github.svg)](https://agentmods.dev/instructions/mrhuangyong/ai-proxy/claude-md)

Your own site

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

Per session 1,410 This file is loaded in full into every session.

When invoked 1,410 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	$0.01410	$0.01410
Opus 5.5	$0.00564	$0.00564
Sonnet 5.5	$0.00282	$0.00282
Haiku 4.5	$0.00141	$0.00141

Measured 2mo ago against content hash e9fe0152921f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ai-proxy 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 · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 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

AI Proxy is a local LLM reverse proxy packaged as a Tauri 2 desktop app (Rust backend + Vue 3 frontend). It unifies OpenAI Completions/Responses, Anthropic Messages, and Google Gemini behind a single endpoint at http://127.0.0.1:7860, using an IR (Intermediate Representation) layer for transparent bidirectional format conversion. UI language is Chinese (zh-CN).

Build & Dev Commands

pnpm install                                  # Install frontend deps
pnpm tauri dev                                # Full dev mode (Vite :1420 + Rust hot-reload, proxy :7860)
pnpm tauri build                              # Production build → native installer
pnpm build                                    # Frontend type-check (vue-tsc) + Vite bundle
cd src-tauri && cargo test                    # All Rust tests
cd src-tauri && cargo test --test ir_conversion   # Specific integration test
cd src-tauri && cargo test test_name          # Single test by name
cd src-tauri && cargo fmt                     # Format Rust code

No frontend test framework. No linter/formatter for TS — match existing style.

Architecture

Dual Server Pattern

The Tauri app embeds an Axum HTTP server. The Vue frontend talks to Axum via HTTP (not Tauri IPC), so the proxy is independently accessible by external LLM clients. During frontend-only dev, Vite proxies /api and /health to the Axum backend. A shared reqwest::Client (http.rs → SHARED_HTTP_CLIENT) is used for all upstream requests.

Feature Flags: Desktop vs Server

Two build modes via Cargo features:

desktop (default): Tauri GUI, system tray, auto-update, app management (apps/ module)
server: Headless CLI binary (ai-proxy-server), JWT auth (auth/ module), no Tauri deps

#[cfg(feature = "desktop")] guards Tauri-specific code in lib.rs. The server_main.rs is currently a placeholder.

Read the full file on GitHub · 102 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 · 102 lines · 1,410 tokens per session scan A e9fe0152921f

Subscribe to this mod's changes

ai-proxy CLAUDE.md is an instructions file published in the GitHub repository mrhuangyong/ai-proxy (12 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,410 tokens to every session, about $0.0056 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 Frontend Vue and Svelte

ai-proxy CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ai-proxy CLAUDE.mdmrhuangyong/ai-proxy	Instructions file	12	1mo ago	Apache-2.0	A	1,410	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

ai-proxy: Instructions file for Claude Code