Gpt Team Registration logo

Gpt Team Registration

Community
ikunycj
gpt-team-registration

Register ChatGPT Team/Business sub-accounts with the configured email suffix and codex SAML SSO. Use when the user asks to register another Team child account, retry a gpt-team registration, or create an account like ikun0000001/testikun0001 under the Team SSO flow. This skill must use the Codex in-app Browser, never external Chrome or the CLI browser automation script.

Overview

Publisherikunycj
Repositorygpt-team-register
Skill namegpt-team-registration
Stars
67
Forks
8
Bundled files
1
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by ikunycj on GitHub. Read the source before you install it.

Installation

Install the Gpt Team Registration AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/ikunycj/gpt-team-register/tree/master/skills/gpt-team-register
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ikunycj/gpt-team-register.git /tmp/gpt-team-register
mkdir -p .claude/skills
cp -r /tmp/gpt-team-register/skills/gpt-team-register .claude/skills/gpt-team-registration
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gpt Team Registration in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Gpt Team Registration on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Gpt Team Registration is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

GPT Team Registration

Use this skill to register ChatGPT Team/Business sub-accounts from:

text
/Users/yangchunjiang/PersonalCode/closeai/gpt-team-register

Mandatory Browser Rule

Always use the Codex in-app Browser for the registration flow.

Do not use:

  • external Chrome
  • Playwright launched from the shell
  • ./register-team-account
  • .browser-profile

The only shell/Node use allowed during registration is read-only verification or saving the session cache after the in-app browser has successfully logged in.

Configuration

Before deriving an email, read:

text
/Users/yangchunjiang/PersonalCode/closeai/gpt-team-register/skills/gpt-team-register/config.json

Current configurable value:

  • email_suffix: suffix appended to the account id. Default: +@hegiw77632.cloud-ip.cc

Derive the email as:

text
<account-id><email_suffix>

For example, with the default config:

text
testikun0001 -> testikun0001+@hegiw77632.cloud-ip.cc

If the user explicitly provides an email, use the explicit email and mention it before submitting. The SSO User ID is always the account id unless the user explicitly provides another User ID.

In-App Browser Flow

  1. Use the Browser skill and connect to the Codex in-app Browser.

  2. Show the browser when Cloudflare, browser verification, or manual user action may be needed.

  3. Open https://chatgpt.com/auth/login.

  4. If another ChatGPT account is logged in, log out first, then return to the email login form.

  5. Enter the derived email.

  6. Click 继续.

  7. On https://auth.openai.com/sso, choose codex.

  8. On the SAML SSO page, fill:

    • Email: derived email
    • User ID: account id
  9. Submit Sign In immediately.

  10. Complete onboarding:

  • choose 工程 unless the user requested another role
  • dismiss optional prompts with 稍后再说 or 跳过
  1. Verify ChatGPT is usable:
  • URL is https://chatgpt.com/
  • Business workspace is visible
  • chat box is visible

Typing Fallback

The in-app Browser may fail with:

text
Browser Use virtual clipboard is not installed

When that happens, click the field and input characters with tab.cua.keypress one character at a time:

  • @: SHIFT + 2
  • +: SHIFT + =
  • .: .
  • -: -
  • letters and digits: the character itself

Use this fallback for both the ChatGPT email field and the SAML form fields.

Safety Boundaries

  • Do not bypass Cloudflare, CAPTCHA, browser safety interstitials, or paywalls.
  • If Cloudflare or browser verification appears, ask the user to complete it in the visible in-app Browser, then continue.
  • If the in-app Browser policy blocks a URL such as external.auth.openai.com, stop and ask the user to manually continue until the next reachable page, usually the SAML form or ChatGPT home.
  • Do not use external Chrome as a fallback.
  • Session cache files contain secrets. Do not print token values, stage token files, or paste token JSON.

Saving The Session Cache

After successful login, open this URL in the same in-app Browser tab:

text
https://chatgpt.com/api/auth/session

Confirm the JSON has accessToken and sessionToken. Do not print either token.

Save the session cache with the local saver:

js
const authSession = await tab.playwright.evaluate(() => JSON.parse(document.body?.innerText || "{}"));
const mod = await import("/Users/yangchunjiang/PersonalCode/closeai/gpt-team-register/scripts/fetch-json-save.mjs");
await mod.saveChatgptSessionCacheFromAuthSession(authSession, {
  email: "<derived-email>",
});

Then return to https://chatgpt.com/.

Verify the saved file without revealing tokens:

bash
cd /Users/yangchunjiang/PersonalCode/closeai/gpt-team-register
node -e "const fs=require('fs'); const p='chatgpt_sessions/<safe-email>.json'; const d=JSON.parse(fs.readFileSync(p,'utf8')); console.log(JSON.stringify({email:d.email, hasAccessToken:!!d.access_token, hasSessionToken:!!d.session_token, hasRawSession:!!d.raw_session}, null, 2))"

SAML Expiry Retry

The SAML request URL can expire quickly. If Sign In returns:

text
invalid SAML request

then:

  1. Return to https://chatgpt.com/auth/login.
  2. Re-enter the same derived email.
  3. Choose codex again to generate a fresh SAML request.
  4. Fill the same email and User ID.
  5. Submit immediately.

Do not reuse an old SAMLRequest or RelayState URL.

Completion Report

Report:

  • account id and email used
  • whether registration/login reached ChatGPT
  • whether onboarding choices were applied
  • whether session cache was saved and structurally verified
  • any remaining user action required

Keep working until the account is registered/logged in, usable, and the session cache is saved, unless the user explicitly says not to save it.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Gpt Team Registration AI skill do?

Register ChatGPT Team/Business sub-accounts with the configured email suffix and codex SAML SSO. Use when the user asks to register another Team child account, retry a gpt-team registration, or create an account like ikun0000001/testikun0001 under the Team SSO flow. This skill must use the Codex in-app Browser, never external Chrome or the CLI browser automation script.

Why use Gpt Team Registration on TypingMind?

Because you install it once and use it with any model. Gpt Team Registration is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Gpt Team Registration in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ikunycj/gpt-team-register/tree/master/skills/gpt-team-register. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Gpt Team Registration?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Gpt Team Registration?

As many as you like. As long as a model supports skills, you can use Gpt Team Registration with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Gpt Team Registration AI skill free?

Yes. It is published on GitHub by ikunycj under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇