yxhpy

ChatGPT Pro Browser — Development skill for Claude Code

Development community

Use your logged-in ChatGPT (incl.

How to install ChatGPT Pro Browser

This entry records only its repository, not the path inside it, so there is no exact command to give. Open yxhpy/chatgpt-pro-browser and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What ChatGPT Pro Browser does

Use your logged-in ChatGPT (incl. Pro) from the terminal by driving the real Chrome browser. ZCode/Codex skill + Python harness.

Alternatives in Development

Mem0 Chrome Extension — OpenMemory Chrome Extension: Long-term memory for ChatGPT, Claude, Perplexity, Grok etc 671 ★
Zoetrope — Watch a Claude Code session as a live flow graph, in your terminal or your browser 584 ★
Open Claude In Chrome — Claude in Chrome, reverse-engineered and open-source 199 ★

README

chatgpt-pro-browser

Use your **already-logged-in ChatGPT (incl. Pro)** from the terminal by driving the real Chrome browser — call it, upload files, and generate executable plans.

[![tests](https://img.shields.io/badge/tests-20%2F20%20pass-brightgreen)](TEST_REPORT.md) [![platform](https://img.shields.io/badge/platform-macOS-lightgrey)](#prerequisites) [![python](https://img.shields.io/badge/python-3.10%2B-blue)](requirements.txt)

This is a ZCode/Codex **plugin** (two skills) plus a reusable Python **harness** that lets you call ChatGPT (especially **GPT-5 Pro / GPT-5.5 Pro**) from scripts, automation, or other agents — by operating the actual chatgpt.com web UI with your own logged-in session.

It is **not** a reverse-engineered API. Raw HTTP/cookie access to ChatGPT is blocked by Cloudflare (`cf-mitigated: challenge`, confirmed 403). This project decrypts Chrome's login cookies and injects them into a Playwright-controlled **real** Chrome, then drives the UI like a human would.

Two skills

Skill	What it does
chatgpt-pro-browser	Call ChatGPT Pro from code: send prompts, upload files, multi-turn. The reusable `lib/harness.py`.
chatgpt-pro-planner	Generate executable engineering plans (dev / test / refactor / bugfix) via Pro's reasoning, in the superpowers markdown format that Codex, Claude Code, and `executing-plans` / `subagent-driven-development` consume directly.

What works (verified, 20/20 tests passing)

Capability	Status
Login reuse (Pro/Plus/Free)	✅
Single prompt → text reply	✅
File uploads: PNG, JPG, PDF, CSV, TXT, JSON, PY, MD, DOCX, XLSX	✅
Multi-file uploads (3-5 files, mixed types)	✅
Cross-file reasoning	✅
Big inputs (132 KB file, 14 KB pasted prompt)	✅
Long outputs (2000+ words)	✅
Deep reasoning (GPT-5 Pro)	✅
Multi-turn conversation state	✅
Resume after disconnect (server keeps generating)	✅
Multi-line/large prompts