MCPInstall

codex-auto-register

Automate ChatGPT/Codex account registration and OAuth token generation using DuckMail temporary email service

Installs
250
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/reason-machines/codex-skills --skill codex-auto-register
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads codex-auto-register automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Codex Auto Register

Skill by ara.so — Codex Skills collection.

Overview

codex_auto_register is a Python tool for automated ChatGPT/Codex account registration and OAuth token generation using the DuckMail temporary email API. It supports two workflows:

  1. Root script (chatgpt_register.py): Register ChatGPT accounts with optional OAuth
  2. Codex protocol script (codex/protocol_keygen.py): Full Codex OAuth flow with CLIProxyAPI v6 compatible token output

Installation

Dependencies

For root registration script:

pip install curl_cffi

For Codex protocol script:

pip install requests urllib3

Configuration Setup

  1. Copy example configs to active configs:
cp config.example.json config.json
cp codex/config.example.json codex/config.json
  1. Edit config.json and codex/config.json with your credentials (see Configuration section)

Root Script: ChatGPT Registration

Configuration (config.json)

{
  "total_accounts": 5,
  "duckmail_api_base": "https://duckmail.example.com",
  "duckmail_bearer": "${DUCKMAIL_TOKEN}",
  "proxy": "http://username:password@proxy.example.com:8080",
  "output_file": "registered_accounts.txt",
  "enable_oauth": true,
  "oauth_required": false,
  "upload_api_url": "https://cpa.example.com/api/accounts",
  "upload_api_token": "${CPA_API_TOKEN}"
}

Key Fields:

  • total_accounts: Number of accounts to register
  • duckmail_api_base: DuckMail API endpoint
  • duckmail_bearer: DuckMail authentication token (use env var)
  • proxy: HTTP/HTTPS proxy (required for registration)
  • enable_oauth: Whether to perform OAuth flow
  • oauth_required: Fail if OAuth fails
  • upload_api_url/upload_api_token: Optional CPA upload

Usage

python chatgpt_register.py

The script will:

  1. Create temporary email via DuckMail
  2. Register ChatGPT account
  3. Optionally perform OAuth
  4. Save results to registered_accounts.txt
  5. Optionally upload to CPA

Output Format

registered_accounts.txt contains:

email@example.com:password123:access_token:refresh_token
email2@example.com:password456:access_token2:refresh_token2

Codex Protocol Script

Configuration (codex/config.json)

{
  "total_accounts": 10,
  "duckmail_api_base": "https://duckmail.example.com",
  "duckmail_bearer": "${DUCKMAIL_TOKEN}",
  "proxy": "http://user:pass@proxy.example.com:8080",
  "output_dir": "codex_tokens",
  "accounts_file": "accounts.txt",
  "csv_file": "registered_accounts.csv",
  "upload_api_url": "https://cpa.example.com/api/codex",
  "upload_api_token": "${CPA_API_TOKEN}",
  "save_access_token": true,
  "save_refresh_token": true,
  "ak_file": "ak.txt",
  "rk_file": "rk.txt"
}

Usage

python codex/protocol_keygen.py

The script performs:

  1. DuckMail temporary email creation
  2. ChatGPT account registration
  3. Codex OAuth login flow
  4. Token extraction and storage
  5. CLIProxyAPI v6 compatible file generation

Output Files

Token JSON files (CLIProxyAPI v6 format):

codex_tokens/
├── fk-xxxxxx.json
├── fk-yyyyyy.json
└── ...

Each JSON contains:

{
  "access_token": "ey...",
  "refresh_token": "ey...",
  "expires_at": 1234567890
}

Account files:

  • accounts.txt: email:password:access_token:refresh_token
  • ak.txt: Access tokens (one per line)
  • rk.txt: Refresh tokens (one per line)
  • registered_accounts.csv: CSV format with all fields

Common Patterns

Environment Variables for Secrets

Never hardcode credentials. Use environment variables:

export DUCKMAIL_TOKEN="your_duckmail_token"
export CPA_API_TOKEN="your_cpa_token"

Reference in config:

{
  "duckmail_bearer": "${DUCKMAIL_TOKEN}",
  "upload_api_token": "${CPA_API_TOKEN}"
}

Proxy Configuration

Both scripts require proxies to bypass rate limits:

{
  "proxy": "http://username:password@proxy-host:port"
}

For SOCKS5:

{
  "proxy": "socks5://username:password@proxy-host:port"
}

Batch Registration

Register multiple accounts in sequence:

# In your automation script
import subprocess
import json

config = {
    "total_accounts": 50,
    "duckmail_api_base": "...",
    # ... other config
}

with open("codex/config.json", "w") as f:
    json.dump(config, f)

subprocess.run(["python", "codex/protocol_keygen.py"])

Token File Naming Convention

Codex tokens follow CLIProxyAPI v6 naming:

  • Format: fk-{unique_id}.json
  • Compatible with CLIProxyAPI token directory structure
  • Can be directly placed in CPA token folders

DuckMail API Integration

The project uses DuckMail for temporary email:

Create email:

POST {duckmail_api_base}/api/email/create
Authorization: Bearer {duckmail_bearer}

Check inbox:

GET {duckmail_api_base}/api/email/{email_id}/messages
Authorization: Bearer {duckmail_bearer}

See duckmaildoc.md for full API reference.

Troubleshooting

Registration Fails

Problem: ChatGPT registration returns errors

Solutions:

  1. Verify proxy is working and not banned
  2. Check DuckMail API is accessible
  3. Ensure duckmail_bearer token is valid
  4. Try different proxy IP range

OAuth Token Not Generated

Problem: enable_oauth: true but no tokens

Solutions:

  1. Set oauth_required: false to continue without OAuth
  2. Verify proxy supports OAuth endpoints
  3. Check account was successfully verified
  4. Inspect network logs for OAuth failures

DuckMail Email Not Received

Problem: Verification email not arriving

Solutions:

  1. Wait 30-60 seconds (DuckMail polling interval)
  2. Check DuckMail API rate limits
  3. Verify email was successfully created
  4. Try different email domain if available

CPA Upload Fails

Problem: upload_api_url returns errors

Solutions:

  1. Verify upload_api_token is correct
  2. Check CPA endpoint is accessible through proxy
  3. Ensure token format matches CPA expectations
  4. Review CPA API documentation for required fields

Token Files Not Compatible

Problem: CLIProxyAPI doesn't recognize tokens

Solutions:

  1. Verify filename format: fk-*.json
  2. Check JSON structure matches expected schema
  3. Ensure expires_at is Unix timestamp
  4. Validate tokens are not expired

Proxy Authentication Errors

Problem: 407 Proxy Authentication Required

Solutions:

  1. Verify proxy username/password are correct
  2. Use URL-encoded credentials in proxy string
  3. Test proxy with curl: curl -x proxy http://api.openai.com
  4. Check proxy supports CONNECT method for HTTPS

File Structure

Generated files (all in .gitignore):

project_root/
├── config.json                    # Root script config
├── registered_accounts.txt        # Root script output
└── codex/
    ├── config.json               # Codex script config
    ├── accounts.txt              # email:password:tokens
    ├── ak.txt                    # Access tokens only
    ├── rk.txt                    # Refresh tokens only
    ├── registered_accounts.csv   # CSV format
    └── codex_tokens/             # CLIProxyAPI compatible
        ├── fk-xxxxx.json
        └── fk-yyyyy.json

Security Notes

  • Never commit config.json files (use .example.json templates)
  • Store tokens securely (files are gitignored by default)
  • Use environment variables for all secrets
  • Rotate DuckMail tokens regularly
  • Keep proxy credentials separate from code
  • Review registered_accounts.txt for sensitive data before sharing logs

Integration with CLIProxyAPI

Place generated token files directly in CPA token directory:

cp codex/codex_tokens/*.json /path/to/CLIProxyAPI/tokens/codex/

CPA will automatically detect and use tokens with fk-*.json naming pattern.

FAQ

What does the codex-auto-register skill do?

Automate ChatGPT/Codex account registration and OAuth token generation using DuckMail temporary email service

How do I install codex-auto-register?

Run npx skills add https://github.com/reason-machines/codex-skills --skill codex-auto-register in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/codex-auto-register/ (personal) or .claude/skills/codex-auto-register/ (project).

Which AI agents can use codex-auto-register?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is codex-auto-register safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains codex-auto-register?

It is published by reason-machines in reason-machines/codex-skills. It has 250 recorded installs.

More from reason-machines/codex-skills

View all →

academic-research-skills-codex

reason-machines/codex-skills

AI-assisted academic research workflows for literature review, paper writing, peer review, and research pipelines

codexplusplus-launcher

reason-machines/codex-skills

Enhanced launcher for Codex App that unlocks plugins, enables session deletion, exports conversations, and syncs provider sessions via CDP injection

Security286 installs

codex-plugin-claude-code

reason-machines/codex-skills

Use OpenAI Codex from inside Claude Code for code reviews, adversarial reviews, and delegating tasks to Codex as a subagent.

AI & Agents277 installs

codex-plusplus-tweak-system

reason-machines/codex-skills

Expert in developing, installing, and managing tweaks for the Codex++ desktop app extension system

274 installs

awesome-codex-skills-curator

reason-machines/codex-skills

Curate, install, and manage Codex skills from the awesome-codex-skills collection for AI coding agents.

274 installs

awesome-codex-subagents

reason-machines/codex-skills

A curated collection of 136+ specialized Codex subagents for development tasks across 10 categories

AI & Agents273 installs

Popular productivity & automation skills

View category →

agent-browser

vercel-labs/agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

OfficialProductivity & Automation1.3M installs

lark-doc

open.feishu.cn

飞书云文档(Docx / Wiki)内容操作:读取、创建、编辑文档,插入或下载图片附件,以及操作思维笔记。用户提供文档 URL/token(包括 doubao.com 的 /docx/、/wiki/)时使用;按 URL 路径/token 而非域名路由;/page/ 是妙搭应用,非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive;随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。

lark-base

open.feishu.cn

飞书多维表格(Base)操作:建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式(BaseApp/AppMode 页面与组件)、Workspace 目录、workflow、角色权限、模板中心(多维表格模板分类/列表/搜索);遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps;文件导入/导出转 lark-drive,认证/授权转 lark-shared。

lark-drive

open.feishu.cn

飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签(secure labels)和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用;doubao.com 云空间 URL/token 也按资源路径和 token 路由,不回退 WebFetch。不负责:文档内容编辑(走 lark-doc)、表格/Base 表内数据操作(走 lark-sheets/lark-base)、知识空间节点/成员管理(走 lark-wiki)、原生 Markdown 文件读写/patch/diff(走 lark-markdown)。

lark-shared

open.feishu.cn

Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.

lark-im

open.feishu.cn

飞书即时通讯:收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片(Interactive Card)、监听卡片按钮回调(card.action.trigger)。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶(添加/移除/查询置顶会话)、管理标签数据、处理卡片回调时使用。