aai-gateway: Instructions file for Claude Code

CLAUDE.md

aai-gateway CLAUDE.md is an instructions file for Claude Code from gybob/aai-gateway. It costs 1,102 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for Claude Code, an AI coding assistant, covering how to build, test, lint, format, and understand a project.

In plain words
What is it for?
Use them when developing the AAI Gateway, a single service that connects AI agents to multiple tools and services.
Why use it?
They give the assistant the project’s rules and structure so it can work with the codebase consistently and use the right commands.

Instructions file for Claude Code

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

This is gybob/aai-gateway's own configuration. It tells Claude Code how to work on aai-gateway 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 aai-gateway configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gybob/aai-gateway. 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/gybob/aai-gateway/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/gybob/aai-gateway

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 aai-gateway CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gybob/aai-gateway/claude-md.svg)](https://agentmods.dev/instructions/gybob/aai-gateway/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/gybob/aai-gateway/claude-md"><img src="https://agentmods.dev/badge/instructions/gybob/aai-gateway/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,102 This file is loaded in full into every session.
When invoked 1,102 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 $0.01102 $0.01102
Opus 5 $0.00551 $0.00551
Sonnet 5 $0.00220 $0.00220
Haiku 4.5 $0.00110 $0.00110

Measured 8d ago against content hash e428501fbe5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

aai-gateway 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 8d 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 · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 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.

「 以第一性原理!从原始需求和问题本质出发,不从惯例和模板出发。

  1. 不要假设自己清楚自己想要什么。动机或目标不清晰时,停下来讨论。
  2. 目标清晰但路径不是最短的,直接告诉我并建议更好的方案。
  3. 遇到问题追根因,不打补丁。每个决策都要能回答“为什么”。
  4. 输出说重点,砍掉一切不改变决策的信息。 」

Build & Development Commands

npm run build          # tsc + vite build + chmod CLI
npm run dev            # vite-node src/index.ts (dev mode)
npx tsc --noEmit       # type check only
npm run lint           # eslint src --ext .ts
npm run lint:fix       # eslint with auto-fix
npm run format         # prettier
npm test               # vitest run
npm run test:watch     # vitest watch mode
npm run test:coverage  # vitest with coverage

Architecture

AAI Gateway is a unified MCP gateway that manages Agent Apps (MCP servers, Skills, ACP agents). It runs as a single MCP server (stdio) and routes tool calls to downstream apps, enabling multiple AI agents to share tools with 99% context token savings via two-phase disclosure (one-line summaries → full schemas on demand).

Core Flow

AI Agent (Claude Code / Codex / OpenCode)
    ↓ MCP protocol (stdio)
  Server (src/mcp/server.ts)
    ↓
  Gateway (src/core/gateway.ts)  ← orchestrator
    ↓
  ExecutionCoordinator (src/core/execution-coordinator.ts)
    ├─ MCP Executor  → downstream MCP servers (stdio/SSE/HTTP)
    ├─ Skill Executor → reads SKILL.md files
    └─ ACP Executor  → spawns agent subprocesses (JSON-RPC)

Key Modules

  • Gateway (src/core/gateway.ts): Main orchestrator. Handles aai:exec, import flows, enable/disable, search. Protocol-agnostic — delegates execution to ExecutionCoordinator.
  • ExecutionCoordinator (src/core/execution-coordinator.ts): Routes to the correct executor by protocol. Manages inactivity timeouts.
  • AppRegistry (src/core/app-registry.ts): In-memory Map<appId, RuntimeAppRecord> of all known apps.
  • Executors (src/executors/): Each implements the Executor interface (interface.ts). acp.ts is the most complex — manages subprocess lifecycle, session/turn state machine, permission requests, and streaming.
  • Storage (src/storage/): File-based registries (FileRegistry<T>) persisting MCP configs, skills, and managed apps to ~/.local/share/aai-gateway/.
  • Discovery (src/discovery/): Auto-discovers preset agents (Claude Code, Codex, OpenCode) via command/file checks.
  • Tool Definitions (src/core/tool-definitions.ts): Defines gateway-level MCP tools (aai:exec, mcp:import, skill:import, search:discover, etc.).

Read the full file on GitHub · 80 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. 8d ago First seen · 80 lines · 1,102 tokens per session scan A e428501fbe5f

Subscribe to this mod's changes

aai-gateway CLAUDE.md is an instructions file published in the GitHub repository gybob/aai-gateway (99 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,102 tokens to every session, about $0.0055 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.

Related

Other instructions, from other repositories

vibetags com-example-config-AsyncTestConfig.instructions.md

Instructions for PIsberg/vibetags, covering copilot instructions for asynctestconfig and immutable type.

PIsberg/vibetags · 82 tokens

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