codex-chatgpt-control AGENTS.md

codex-chatgpt-control AGENTS.md is an instructions file for Codex, OpenCode from adamallcock/codex-chatgpt-control. It costs 548 tokens per session, scanned A, original, MIT.

Repository instructions for a public, unofficial toolkit that controls visible ChatGPT browser sessions through Node and Python packages. They describe the package boundaries, safety rules, and limits around live browser tests and data extraction.

In plain words
What is it for?
Use them when changing browser control, backend commands, live-smoke tests, safety redaction, protocol contracts, fixtures, documentation, or the Node and Python clients.
Why use it?
They help contributors preserve the public-session boundary and avoid treating the project as a private API, scraping system, or background automation service. They also reduce inconsistencies between the two language packages.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/adamallcock/codex-chatgpt-control/agents-md
Clone the repo
git clone --depth 1 https://github.com/adamallcock/codex-chatgpt-control

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 codex-chatgpt-control AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/adamallcock/codex-chatgpt-control/agents-md.svg)](https://agentmods.dev/instructions/adamallcock/codex-chatgpt-control/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/adamallcock/codex-chatgpt-control/agents-md"><img src="https://agentmods.dev/badge/instructions/adamallcock/codex-chatgpt-control/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 548 This file is loaded in full into every session.
When invoked 548 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00548 $0.00548
Opus 5 $0.00274 $0.00274
Sonnet 5 $0.00110 $0.00110
Haiku 4.5 $0.00055 $0.00055

Measured 6d ago against content hash 972ca3d4390e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

codex-chatgpt-control 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 6d 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 · 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.

codex-chatgpt-control Agent Instructions

Public Repo Boundary

  • This is a public alpha SDK for user-directed workflows in visible ChatGPT web sessions. Keep all guidance safe for public contributors.
  • Do not add private OpenAI account details, cookies, tokens, internal browser bridge state, unpublished package credentials, or private run transcripts to the repo.
  • This project is unofficial. Do not phrase docs, package metadata, or examples as if the project is endorsed by OpenAI.

Architecture

  • The Node package is the runtime authority for browser control, backend commands, live-smoke orchestration, safety redaction, and contract fixtures.
  • The Python package is a parity client over the same backend protocol. It should not diverge into a separate browser automation implementation.
  • Shared behavior changes must update contracts, fixtures, docs, examples, and both language surfaces when applicable.

Safety Model

  • Keep the visible-session boundary: this is not a scraping framework, private ChatGPT API wrapper, background automation service, or bulk extraction tool.
  • Live browser tests can touch a real user session. Run them only when the user asks for live validation or when the task clearly requires it.
  • Redact prompts, responses, filenames, account identifiers, and local paths in reports unless the user explicitly wants a local private artifact.

Local Commands

From the repository root:

npm run node:test
npm run node:build
npm run node:bundle
npm run node:contracts
npm run python:test
npm run python:compile
npm run release:check-version
npm run release:check-names
npm run release:check-node-pack

For Node package work:

cd packages/node
npm test
npm run build
npm run bundle
npm run bundle:backend
npm run contract:validate
npm run docs:drift
npm run parity:fixtures
npm run parity:suite
npm run test:backend-conformance

For Python package work:

cd packages/python
python -m pip install -e ".[dev]"
python -m unittest discover -s tests
python -m compileall -q src examples

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. 6d ago First seen · 80 lines · 548 tokens per session scan A 972ca3d4390e

Subscribe to this mod's changes

codex-chatgpt-control AGENTS.md is an instructions file published in the GitHub repository adamallcock/codex-chatgpt-control (390 stars, last pushed 15d ago), licensed MIT. It adds 548 tokens to every session, about $0.0027 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.