These are instructions for you (an AI coding agent) to help the user deploy a static UI with vibepage — in the same chat when possible.

## Product

- Name: vibepage
- Site: https://vibepage.cloud/
- Purpose: Publish a static / vibe-coded UI to a public HTTPS subdomain in seconds
- Works with: Claude Code, Cursor, OpenAI Codex, and other CLI-capable agents

## Quick setup

1. Read the full agent playbook (keep it as your source of truth):
   https://vibepage.cloud/for-agents.md

2. Install the vibepage CLI (prefer npx when you do not want a global binary):

   npx vibepage

   or:

   curl -fsSL https://vibepage.cloud/install.sh | bash

3. Authenticate (non-interactive — preferred):

   Ask the user for their API token from https://vibepage.cloud/ (register or dashboard).
   Then run:

   vibepage token <API_TOKEN>

   Or set VIBEPAGE_TOKEN in the environment and skip vibepage token.

4. From the project directory, deploy the static UI (index.html, or dist/ / build/):

   vibepage deploy

5. Read the CLI output for "Live at: https://….app.vibepage.cloud/" and give that URL to the user.

## Limits

- Static UI hosting only (frontend / built static output).
- Do not ask the user to create an AWS account or set up SSH.
- Do not invent extra CLI commands — only: token, deploy, tunnel, status.
- Do not put the API token into public git commits or screenshots.

## Optional live demo tunnel

If the user is running a local server (for example on port 3000):

   vibepage tunnel

Traffic to the same public subdomain routes to localhost until the tunnel stops, then falls back to the last static deploy.

## More context

- Agent playbook: https://vibepage.cloud/for-agents.md
- Short index: https://vibepage.cloud/llms.txt
- Full product text: https://vibepage.cloud/llms-full.txt
- CLI docs: https://vibepage.cloud/documentation.html