crawl_site
Crawls a website using headless Playwright to discover all reachable routes, saving evidence for rebuilding the application from a reverse-engineered spec.
Instructions
Playwright headless crawl of reachable routes. Emits periodic progress notifications.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Base URL to crawl | |
| maxPages | No | ||
| repoPath | Yes | Repo path whose .dossier/ this crawl evidence should be saved under |