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.
npx agentmods add instructions/adamallcock/codex-chatgpt-control/agents-mdgit clone --depth 1 https://github.com/adamallcock/codex-chatgpt-controlWrote 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.
[](https://agentmods.dev/instructions/adamallcock/codex-chatgpt-control/agents-md)<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>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 | $0.00548 | $0.00548 |
| Opus 5 | $0.00274 | $0.00274 |
| Sonnet 5 | $0.00110 | $0.00110 |
| Haiku 4.5 | $0.00055 | $0.00055 |
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.
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
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.
- 6d ago First seen · 80 lines · 548 tokens per session scan A 972ca3d4390e
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.
Other instructions, from other repositories
Browser4 CLAUDE.md
Claude Code instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
cc-websearch CLAUDE.md
Claude Code instructions for Djarvur/cc-websearch, covering project, constraints, technology stack, what not to add and conventions.
fix-quera AGENTS.md
Instructions for AlirezaKeshavarz83/fix-quera, covering agent guidance, project shape, visual style, quera page data findings and compatibility findings.
sniff AGENTS.md
AGENTS.md instructions for Aboudjem/sniff, covering agents.md: sniff, what this repo is, how an agent should use sniff, handling the playwright setup gate and finding output schema.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
sendblue-browser-use AGENTS.md
Instructions for sendblue-api/sendblue-browser-use, covering agents.md — sendblue-browser-use, what this repo is, setup, common commands and health (no auth).