| name | codex-chatgpt-control |
| description | Use when Codex agents need to operate visible ChatGPT web sessions through the codex-chatgpt-control SDK, including prompts, threads, files, downloads, reports, browser bridge blockers, and local source smokes. |
codex-chatgpt-control
Use this skill when a user asks Codex to operate ChatGPT web through a visible browser session, or when a task involves the codex-chatgpt-control SDK.
This skill is for visible, user-directed ChatGPT workflows only. It is not an OpenAI API wrapper, does not call hidden ChatGPT endpoints, and must not bypass login, captcha, product permissions, file permissions, or user confirmation.
Required Posture
- Prefer the SDK facade from
createChatGPT({ agent }).
- Use ChatGPT web through a compatible Codex/browser bridge. Do not use private ChatGPT network calls.
- Treat
globalThis.agent as host-provided. If it is missing, report a bridge blocker rather than inventing browser state.
- Stop on login, captcha, rate-limit, selector-drift, upload/download permission, or ambiguous confirmation blockers.
- Ask for explicit user confirmation before public, destructive, third-party, paid, account-level, or externally visible actions.
- Redact run reports by default. Raw prompt/response content is opt-in only.
- Attach only files the user approved.
Runtime Requirements
Deterministic local checks need:
- Node.js 20 or newer
- npm
- a source checkout of
codex-chatgpt-control
Real browser-control runs also need:
- Chrome with a signed-in visible ChatGPT web session
- a compatible Codex/browser bridge exposing
globalThis.agent
- permission to use or open a visible ChatGPT tab
Ordinary shells should not have globalThis.agent. A browser_bridge_unavailable blocker from an ordinary shell is an expected safe result for browser-required calls.
File Upload Permissions
File attachment workflows need two separate permission gates:
- Chrome extension gate: open
chrome://extensions, choose the Codex/browser bridge extension, open Details, and enable Allow access to file URLs.
- Codex app gate: in Codex settings, allow Google Chrome uploads under Computer Use > Google Chrome > Permissions > Uploads. Use the narrowest setting that fits the workflow; unattended smoke tests may need the always-allow setting.
If either gate is missing, stop with a permission blocker and tell the user which gate to check.
Host-Local Attachment Paths
Attachment paths must be absolute on the machine running the Node backend. Use the path form for that host operating system. On Linux/WSL backends, use paths such as /home/you/file.pdf or /mnt/c/work/file.pdf. On Windows backends, use fully qualified paths such as C:\Users\you\file.pdf. If a Windows-looking path is rejected on macOS/Linux, do not retry with the same string. Convert it to the backend host's real path, for example /home/you/file.pdf for a Linux/WSL backend.
Use chatgpt.files.preflight({ paths }) before long file workflows when local path validity is uncertain. It does not open ChatGPT or upload files; it validates host-local file metadata and returns structured blockers/warnings.
Source Setup
From a source checkout:
cd packages/node
npm ci
npm test
npm run build
npm run bundle
npm run bundle:backend
Then use the built bundle from a bridge-enabled host runtime:
import { createChatGPT } from "/absolute/path/to/codex-chatgpt-control/packages/node/dist/codex-chatgpt-control.bundle.mjs";
const chatgpt = createChatGPT({ agent: globalThis.agent });
Prefer normal package imports in projects that depend on the published npm package:
import { createChatGPT } from "codex-chatgpt-control";
Basic Runner Flow
const reviewer = chatgpt.agent({
name: "reviewer",
instructions: "Review carefully and return Markdown."
});
const result = await chatgpt.runner.run(reviewer, {
input: "Review this design.",
thread: { type: "new" },
response: { format: "markdown" }
});
if (!result.ok) {
console.log(JSON.stringify(result.interruptions ?? result, null, 2));
} else {
console.log(result.output_text);
}
Instructions are visible prompt text by default. Use instructionsMode intentionally:
visible_prefix: include instructions in the submitted user message.visible_setup_message: submit instructions as a separate visible setup turn.metadata_only: keep instructions local; they are not sent to ChatGPT.
Common Workflows
Ask in a new or selected thread:
await chatgpt.ask({
prompt: "Reply with the word hi.",
wait: true,
read: { format: "markdown" }
});
Continue an existing thread:
await chatgpt.askInThread({
thread: { type: "url", url: "https://chatgpt.com/c/<conversation-id>" },
existingTab: true,
prompt: "Continue from the latest answer.",
wait: true,
read: { format: "markdown" }
});
When the user says the ChatGPT thread is already open, pass existingTab: true or an exact existing-tab policy such as existingTab: { url: "https://chatgpt.com/c/<conversation-id>" }. A thread: { type: "url" } selector by itself means "navigate to this URL"; it does not express "claim the user-open tab".
Attach approved files:
const preflight = await chatgpt.files.preflight({
paths: ["/absolute/host/path/to/approved-file.pdf"]
});
await chatgpt.askWithFiles({
thread: { type: "new" },
files: ["/absolute/host/path/to/approved-file.pdf"],
prompt: "Summarize this file.",
wait: true,
read: { format: "markdown" },
report: { enabled: true, includeContent: false }
});
Plan append-only Project Sources changes before mutating a ChatGPT Project:
const plan = await chatgpt.projects.sources.planAdd({
projectUrl: "https://chatgpt.com/g/g-p-example/project",
files: ["/absolute/host/path/to/approved-source.md"]
});
const added = await chatgpt.projects.sources.add({
projectUrl: "https://chatgpt.com/g/g-p-example/project",
files: ["/absolute/host/path/to/approved-source.md"],
confirmMutation: true
});
planAdd does not open ChatGPT or read file contents. add operates only through the visible Project Sources UI and returns needs_confirmation unless confirmMutation: true is supplied after user approval.
Run a diagnostic before long workflows:
const diagnostic = await chatgpt.doctor({
check: ["bridge", "login", "upload", "download", "clipboard", "file_preflight"],
files: ["/absolute/host/path/to/approved-file.pdf"]
});
Use opt-in scenario checks before targeted workflows:
await chatgpt.doctor({
check: ["existing_tab"],
existingTab: {
target: { type: "conversationId", conversationId: "<conversation-id>" },
ifMissing: "block"
}
});
await chatgpt.doctor({
check: ["localization", "reports"],
report: { destDir: "/absolute/host/reports" }
});
localization verifies locale-registry readiness without changing the account language; it is not yet proof that every localized selector path is wired.
Response Capture
Use Markdown by default for human-readable answers and saved artifacts:
const latest = await chatgpt.messages.waitAndRead({
role: "assistant",
format: "markdown"
});
Use format: "normalized_text" only for compact assertions, polling checks, or simple exact-string smoke tests.
For long Pro, Thinking, Deep Research, or file-backed answers, poll with chatgpt.messages.wait({ responseContent: "metadata", ... }) so repeated partial polls return status metadata instead of re-emitting the growing answer body. Call readLatest({ format: "markdown" }) once the wait confirms completion.
Python Client
The Python package is a protocol client over the Node backend. Build the backend first:
cd packages/node
npm run bundle:backend
Then run Python from packages/python:
python -m pip install -e .[dev]
python scripts/live_smoke.py --mode ordinary-shell
Point Python at an explicit backend command:
from codex_chatgpt_control import Agent, BackendClient, Runner, StdioBackendTransport
backend = BackendClient(StdioBackendTransport(
command=["node", "../node/dist/codex-chatgpt-control-backend.mjs"]
))
runner = Runner(backend)
Blocker Handling
When a run fails, report the structured blocker. Do not retry blindly.
Common blockers:
browser_bridge_unavailable: no bridge-enabled host runtime is available.login_required: the visible ChatGPT session is not signed in.captcha: user action is required.permission: upload/download/clipboard permission is missing.selector_drift: ChatGPT UI changed and selectors need review.rate_limit: wait or ask the user how to proceed.
Validation
For source changes, run:
cd packages/node
npm test
npm run build
npm run bundle
npm run bundle:backend
npm run contract:validate
npm run parity:fixtures
For Python parity changes, also run:
cd packages/python
python -m unittest discover -s tests
python -m compileall -q src examples
python scripts/live_smoke.py --mode ordinary-shell
