Stats
Actions
Tags
From chrome-driver
Interact with the current browser page WITHOUT navigating away. Essential for multi-step workflows on SPAs.
How this command is triggered — by the user, by Claude, or both
Slash command
/chrome-driver:interactThe summary Claude sees in its command listing — used to decide when to auto-load this command
# Interact Interact with the current browser page WITHOUT navigating away. Essential for multi-step workflows on SPAs. **Key difference from navigate**: This command works on the already-open tab without reloading the page, preserving state between actions. Parse the user's request and run: Options: - `--click=SELECTOR` - Click element matching CSS selector - `--type=SELECTOR=TEXT` - Type text into input field - `--eval=JAVASCRIPT` - Execute JavaScript and print result - `--wait-for=SELECTOR` - Wait for element to appear - `--select=SELECTOR=VALUE` - Select dropdown option - `--focus=...
Interact with the current browser page WITHOUT navigating away. Essential for multi-step workflows on SPAs.
Key difference from navigate: This command works on the already-open tab without reloading the page, preserving state between actions.
Parse the user's request and run:
${CLAUDE_PLUGIN_ROOT}/bin/interact [OPTIONS]
Options:
--click=SELECTOR - Click element matching CSS selector--type=SELECTOR=TEXT - Type text into input field--eval=JAVASCRIPT - Execute JavaScript and print result--wait-for=SELECTOR - Wait for element to appear--select=SELECTOR=VALUE - Select dropdown option--focus=SELECTOR - Focus an element--text=SELECTOR - Get text content of element--timeout=SECONDS - Timeout (default: 30)--no-headless - Run with visible browser window--user-data=PATH - Use persistent Chrome profile (required for session continuity)Examples:
# Execute JavaScript on current page
${CLAUDE_PLUGIN_ROOT}/bin/interact --eval="document.title" --user-data=~/.chrome-session
# Click a button without navigating
${CLAUDE_PLUGIN_ROOT}/bin/interact --click="#submit-btn" --user-data=~/.chrome-session
# Chain actions: type then click
${CLAUDE_PLUGIN_ROOT}/bin/interact --type="#search=query" --click="#search-btn" --user-data=~/.chrome-session
# Get text from an element
${CLAUDE_PLUGIN_ROOT}/bin/interact --text="h1.title" --user-data=~/.chrome-session
npx claudepluginhub joshuarweaver/cascade-web-research --plugin the-focus-ai-chrome-driver/browseLaunches headless browser via Playwright to navigate URL, click elements, fill forms, take screenshots. Outputs screenshot path, page title, and URL for visual verification and e2e testing.
/agent-browserAutomates browser for web interaction and testing: navigate to URLs, take screenshots, fill forms, click elements, or run tests using Playwright CLI.
/browseNavigates to a URL, performs optional browser automation tasks like form filling, UI checks, or data scraping, and returns page snapshots or results.
/puppeteerConfigures session to use Puppeteer MCP for browser automation and testing instead of Playwright, auto-adding --puppeteer flag to test commands and enabling screenshots.
/exploreExplores web pages or navigation goals using browser automation. Analyzes with accessibility snapshots and reports elements, navigation options, content found.