gateway: Instructions file for Codex

AGENTS.md

gateway AGENTS.md is an instructions file for Codex, OpenCode from ongoingai/gateway. It costs 1,584 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for coding agents working on the OngoingAI Gateway, an intermediary that controls access to AI providers and records usage data.

In plain words
What is it for?
Use them when implementing or reviewing gateway features, especially authentication, provider integrations, streaming, storage, and error handling.
Why use it?
They give an agent the project's boundaries, security expectations, reliability requirements, and engineering conventions before it changes code.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is ongoingai/gateway's own configuration. It tells Codex and OpenCode how to work on 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 gateway configures →

Reuse

Borrowing it

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

agentmods badge for gateway AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ongoingai/gateway/agents-md/github.svg)](https://agentmods.dev/instructions/ongoingai/gateway/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ongoingai/gateway/agents-md"><img src="https://agentmods.dev/badge/instructions/ongoingai/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.

agentmods 80×15 button for gateway AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ongoingai/gateway/agents-md"><img src="https://agentmods.dev/badge/instructions/ongoingai/gateway/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,584 This file is loaded in full into every session.
When invoked 1,584 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 $0.01584 $0.01584
Opus 5.5 $0.00634 $0.00634
Sonnet 5.5 $0.00317 $0.00317
Haiku 4.5 $0.00158 $0.00158

Measured 1mo ago against content hash 59fb855c18c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 1mo 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 · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to AI coding agents when working with code in this repository.

Mission And Scope

OngoingAI Gateway is a transparent, auditable proxy between applications and AI providers. It should enforce access control and capture trustworthy trace/usage data while staying invisible to client workflows.

  • Security first: no credential leakage, strong tenant isolation, least-privilege access, auditable behavior.
  • Reliability first: streaming integrity, predictable failure modes, and stable operation under load.
  • Practical developer experience: fast local setup, clear config, and easy-to-extend provider integrations.
  • Scope boundary: this repo is a headless AI gateway and owns gateway M2M auth/enforcement; UI/user-session concerns are out of scope.

Design intent:

  • Self-hosted default: single binary, SQLite by default.
  • Team/multi-instance mode: Postgres-backed storage and dynamic key management.
  • Upstream provider API keys are pass-through only and must never be persisted.
  • Gateway keys are identity/authorization credentials for the proxy and are distinct from provider credentials.

High-Priority Outcomes

When implementing features or fixes, optimize for these outcomes in order:

  1. Prevent security regressions.
  2. Preserve correctness and tenant boundaries.
  3. Preserve low-latency proxy behavior.
  4. Keep architecture simple and maintainable.
  5. Improve observability and operator experience.

Go Engineering Standards

  • Write idiomatic Go. Keep functions small, cohesive, and explicit.
  • Keep interfaces at boundaries (trace, configstore, providers); avoid speculative abstractions.
  • Pass context.Context as the first parameter for request-bound or storage calls.
  • Wrap errors with actionable context (fmt.Errorf("load gateway key: %w", err)).
  • Use deterministic behavior for critical logic (auth, limits, tenant scoping, redaction policies).
  • Avoid global mutable state. Prefer dependency injection via constructors.
  • Keep hot-path allocations low in middleware/proxy code.
  • Protect concurrency edges: no data races, leaked goroutines, or unbounded queues.
  • Use structured logs and never log secrets, tokens, raw credentials, or unredacted sensitive payloads.
  • Add comments where helpful, especially for non-obvious "why" decisions. Do not add redundant comments.
  • Keep exported symbols documented with concise Go doc comments.

Read the full file on GitHub · 158 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. 1mo ago First seen · 158 lines · 1,584 tokens per session scan A 59fb855c18c8

Subscribe to this mod's changes

gateway AGENTS.md is an instructions file published in the GitHub repository ongoingai/gateway (13 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 1,584 tokens to every session, about $0.0063 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 2026-09-17.

Related

gateway AGENTS.md compared with instructions from other repositories

gateway AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
gateway AGENTS.mdongoingai/gatewayInstructions file138mo agoApache-2.0A1,584Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode