What is free-ai-gateway AGENTS.md?

Project instructions for Free-AI Gateway, an enterprise TypeScript monorepo, meaning one repository containing multiple related packages and applications. They describe package boundaries, architecture rules, and commands for building and testing everything.

Use them when developing Free-AI Gateway, deciding which package owns a change, or running builds and end-to-end tests across the repository.

They help an AI agent place changes in the correct package and preserve the separation between the gateway’s core, server, CLI, and other components.

How zaber-dev/free-ai-gateway configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to zaber-dev/free-ai-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/zaber-dev/free-ai-gateway/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/zaber-dev/free-ai-gateway

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/zaber-dev/free-ai-gateway/agents-md/github.svg)](https://agentmods.dev/instructions/zaber-dev/free-ai-gateway/agents-md)

Your own site

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

Per session 955 This file is loaded in full into every session.

When invoked 955 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	$0.00955	$0.00955
Opus 5.5	$0.00382	$0.00382
Sonnet 5.5	$0.00191	$0.00191
Haiku 4.5	$0.00096	$0.00096

Measured 2mo ago against content hash 4ca05046616f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

free-ai-gateway 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 · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🤖 Free-AI Gateway - Agentic Development Guidelines

Target Audience: AI Coding Assistants, Autonomous Agents, and Pair Programmers (Antigravity, Claude Code, Cursor, GitHub Copilot, Codex, Gemini).

🏛️ Monorepo Architecture & Package Boundaries

This repository is organized as an Enterprise TypeScript Monorepo using npm workspaces. Every agent working in this codebase MUST respect the strict architectural separation between layers:

free-ai-gateway/ (Monorepo Root)
├── packages/
│   ├── core/       → @free-ai-gateway/core (Pure, protocol-neutral AI orchestration engine)
│   ├── mcp/        → @free-ai-gateway/mcp (Model Context Protocol server for AI agents)
│   ├── skills/     → @free-ai-gateway/skills (Agentic IDE skills & installer CLI)
│   └── cli/        → @free-ai-gateway/cli (Developer CLI & terminal AI assistant)
├── apps/
│   └── gateway/    → @free-ai-gateway/gateway (Fastify HTTP server with OpenAI-compatible API)
└── tests/
    └── e2e/        → Cross-package end-to-end integration tests

🛑 Strict Architectural Rules for Agents

Core HTTP Boundary:
- @free-ai-gateway/core MUST NEVER import or depend on HTTP server frameworks (e.g. Fastify, Express, Koa).
- Core only contains client transport (HttpClient) for upstream provider communication.
No Background Timers in Core:
- Core must remain synchronous, deterministic, and pure.
- Background workers (like JobScheduler and reverify.ts) belong exclusively to apps/gateway.
Single Public Entrypoint Imports:
- Downstream packages (packages/mcp, packages/skills, apps/gateway) MUST ONLY import from @free-ai-gateway/core public exports (packages/core/src/index.ts).
- Deep imports into internal files (e.g. @free-ai-gateway/core/src/resilience/circuit-breaker) are strictly prohibited.
Protocol-Neutral Representations:
- Core works exclusively with UnifiedRequest and UnifiedResponse.
- Protocol-specific adaptations (e.g., OpenAI chat completion format) happen in apps/gateway/src/adapters/openai.ts.

Read the full file on GitHub · 93 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 · 93 lines · 955 tokens per session scan A 4ca05046616f

Subscribe to this mod's changes

free-ai-gateway AGENTS.md is an instructions file published in the GitHub repository zaber-dev/free-ai-gateway (18 stars, last pushed 1mo ago), licensed MIT. It adds 955 tokens to every session, about $0.0038 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.

Building agents Languages TypeScript agentic-ai ai ai-gateway antigravity cli cursor

free-ai-gateway AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
free-ai-gateway AGENTS.mdzaber-dev/free-ai-gateway	Instructions file	18	1mo ago	MIT	A	955	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

free-ai-gateway: Instructions file for Codex