What is auto-openai-account AGENTS.md?

Project-specific instructions for contributing to a Go backend with an embedded React, TypeScript, Vite, and Tailwind web interface. It explains which requirements, architecture, design, and API files to read first.

Use it when modifying the server, web interface, SQLite storage, API routes, background job runner, or project documentation.

It gives coding agents the project context they need before making larger changes. This reduces the risk of putting code in the wrong part of the application or breaking its service boundaries.

How 79E/auto-openai-account configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to 79E/auto-openai-account. 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/79E/auto-openai-account/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/79E/auto-openai-account

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/79e/auto-openai-account/agents-md/github.svg)](https://agentmods.dev/instructions/79e/auto-openai-account/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/79e/auto-openai-account/agents-md"><img src="https://agentmods.dev/badge/instructions/79e/auto-openai-account/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/79e/auto-openai-account/agents-md"><img src="https://agentmods.dev/badge/instructions/79e/auto-openai-account/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 995 This file is loaded in full into every session.

When invoked 995 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	$0.00995	$0.00995
Opus 5.5	$0.00398	$0.00398
Sonnet 5.5	$0.00199	$0.00199
Haiku 4.5	$0.00100	$0.00100

Measured 2mo ago against content hash 8c085087ab25, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

auto-openai-account 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 · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project Summary

auto-openai-account is a Go backend with an embedded React UI for local account automation workflows.

Production should run as one Go service that serves:

/api/* JSON API and SSE events
/ React app
/assets/* React static assets

The backend stays in Go. The frontend stays in React, TypeScript, Vite, and Tailwind CSS. SQLite is the first storage backend.

Read First

Before making non-trivial changes, read these files:

docs/requirements.md for product scope and first-version requirements
docs/architecture.md for module layout and boundaries
docs/design.md for UI and interaction direction
docs/api.md for current API contracts

Project Layout

apps/server/main.go: Go server entrypoint
apps/web: React + Vite frontend
internal/api: HTTP routing, request parsing, response formatting, SSE endpoint handlers
internal/domain: shared business types, JSON fields, status constants, default settings
internal/storage: SQLite schema, migrations, persistence queries, data mapping
internal/runner: job creation, concurrency, cancellation, runtime logs, SSE fanout
internal/legacy: account automation implementation kept behind current app boundaries
internal/proxypool: proxy connectivity tests
internal/webui: embedded frontend filesystem and static UI handler
docs: product, architecture, API, and design notes

Development Commands

Backend:

go test ./...
go run ./apps/server

Frontend:

cd apps/web
npm run dev
npm run build

The default server listen address is :8080. It can be overridden with AUTO_OPENAI_ACCOUNT_LISTEN.

Verification Rules

Run the smallest useful verification for the files changed.

Backend changes: go test ./...
Frontend changes: cd apps/web && npm run build
API contract changes: update docs/api.md and verify frontend types in apps/web/src/types.ts
UI behavior changes: verify the affected page builds and follows docs/design.md

Read the full file on GitHub · 119 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 · 119 lines · 995 tokens per session scan A 8c085087ab25

Subscribe to this mod's changes

auto-openai-account AGENTS.md is an instructions file published in the GitHub repository 79E/auto-openai-account (52 stars, last pushed 5mo ago), licensed MIT. It adds 995 tokens to every session, about $0.0040 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.

auto-openai-account AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
auto-openai-account AGENTS.md79E/auto-openai-account	Instructions file	52	5mo ago	MIT	A	995	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

auto-openai-account: Instructions file for Codex