What is ai-proxy AGENTS.md?

Development instructions for a Tauri 2 desktop application that combines a Vue frontend with a Rust backend. The application acts as a local proxy that presents several AI provider APIs through one interface.

Use them when developing or reviewing this repository, especially when changing Vue views, Rust server handlers, API-format conversion, provider routing, encrypted API-key storage, interception, or related tests.

They give contributors a map of the project and its conventions, reducing confusion about where frontend, server, conversion, provider, and key-storage changes belong. They also describe the expected build, test, and coding practices.

How mrhuangyong/ai-proxy configures Codex and OpenCode

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/AGENTS.md

Clone the repo

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

Made for: Codex, OpenCode.

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

Your own site

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

Per session 812 This file is loaded in full into every session.

When invoked 812 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	$0.00812	$0.00812
Opus 5.5	$0.00325	$0.00325
Sonnet 5.5	$0.00162	$0.00162
Haiku 4.5	$0.00081	$0.00081

Measured 2mo ago against content hash 3066d108dae9, 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 AGENTS.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.

AGENTS.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

A Tauri 2 desktop app (Rust backend + Vue 3 frontend) that acts as a local AI/LLM proxy, unifying multiple provider APIs.

src/                        # Vue 3 frontend (Vite + TypeScript)
  views/                    # Page components (Dashboard, Providers, Models, Rules, Logs, Statistics, Settings, Apps)
  api/index.ts              # Frontend API client
  types/index.ts            # Shared TypeScript types
  stores/                   # Pinia stores
  router.ts                 # Vue Router config

src-tauri/                  # Rust backend (Axum server embedded in Tauri)
  src/
    lib.rs                  # App entry, tray, proxy lifecycle
    server/                 # HTTP server: handlers, router, API endpoints, middleware
    converter/              # Format conversion via IR layer
      parsers/              # Parse Completions / Responses / Anthropic / Gemini → IR
      generators/           # Generate from IR → each provider format
    provider/               # Provider management & model routing
    key/                    # API Key encrypted storage & rotation (AES-256-GCM)
    interceptor/            # Rule engine for request/response interception
    usage/                  # Token usage tracking & cost estimation
    logging/                # Request logging store
    db/                     # SQLite via SQLx, connection pool, migrations
    apps/                   # App management (Codex CLI, Claude Desktop, etc.)
  migrations/               # Numbered SQLite migration scripts (001_init.sql …)
  tests/                    # Rust integration tests (e.g. ir_conversion.rs)

Build, Test, and Development Commands

Command	Description
`pnpm install`	Install frontend dependencies
`pnpm tauri dev`	Start dev mode (Vite + Rust hot-reload, opens desktop window)
`pnpm tauri build`	Production build for the current platform
`pnpm build`	Frontend-only type-check (`vue-tsc`) then Vite build
`cd src-tauri && cargo test`	Run all Rust tests

Read the full file on GitHub · 73 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 · 73 lines · 812 tokens per session scan A 3066d108dae9

Subscribe to this mod's changes

ai-proxy AGENTS.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 812 tokens to every session, about $0.0032 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.

ai-proxy AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ai-proxy AGENTS.mdmrhuangyong/ai-proxy	Instructions file	12	1mo ago	Apache-2.0	A	812	Codex, OpenCode
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 Codex