Assign each URL to an isolated Session with controlled concurrency, then summarize status codes, page titles, duration, and failures for batch collection and site checks.
Mandatory prerequisite: First fetch and fully execute the official Lexmount Setup Prompt returned by https://browser.lexmount.com/api/agent-setup/browser-cli, completing installation, authentication, and environment validation. Continue only after every check passes. If the URL is unreachable or validation fails, stop immediately and report it; never skip the setup or pretend it succeeded.
Task: Use browser-cli only to inspect https://docs.python.org/3/, https://nodejs.org/docs/latest/api/, and https://go.dev/doc/ concurrently, combine the results into structured JSON, and make the report directly openable from the final Codex response.
Flow: Create no more than three temporary Sessions concurrently, with one dedicated Session per URL. For each page, collect the requested URL, final URL, status code, document title, first visible H1, elapsed time, and sanitized error, then combine the results in input order and verify the JSON report.
Execution: Do not replace independent Sessions with multiple tabs in one Session. A failure on one page must not cancel the other tasks. If a page has no visible H1, record null.
Acceptance: Success requires a non-empty, parseable JSON report, an explicit result for every page, and successful cleanup for every Session. The generated JSON must be available as a clickable file in the final Codex response. If any page or cleanup operation fails, report "partial success."
Cleanup: Each task may close only the Session it created and must attempt to close it on success, failure, timeout, or cancellation. Never close a pre-existing Session.
Return only the overall status, success and failure counts, cleanup result, and error summary, then provide the generated JSON report as the final item so it can be opened directly in Codex. Do not expose API keys, Project IDs, Session IDs, or connection URLs.