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/mrhuangyong/ai-proxy/agents-mdgit clone --depth 1 https://github.com/mrhuangyong/ai-proxyWrote 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/mrhuangyong/ai-proxy/agents-md)<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="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 | $0.00812 | $0.00812 |
| Opus 5 | $0.00406 | $0.00406 |
| Sonnet 5 | $0.00162 | $0.00162 |
| Haiku 4.5 | $0.00081 | $0.00081 |
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 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 — 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 |
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 · 73 lines · 812 tokens per session scan A 3066d108dae9
ai-proxy AGENTS.md is an instructions file published in the GitHub repository mrhuangyong/ai-proxy (11 stars, last pushed 4d ago), licensed Apache-2.0. It adds 812 tokens to every session, about $0.0041 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
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.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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.
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).