Browser Extract Pull structured data out of a web page. Replaces the older skill with three new guarantees: 1. The session is a recorded RVF container (composes ). 2. Successful extractions persist as for reuse. 3. Every string passes AIDefence before AgentDB store and before flowing back to the model. When to use Extracting text, table data, or attribute values from rendered web pages. Building a reusable template for a recurring scrape pattern. Re-running a known template against a new URL on the same host. Steps 1. Open a recorded session via (do not call directly). 2. Wait for content wit…