libretto
Browser automation CLI for building, maintaining, and running browser automation workflows by inspecting live pages and…
Read-only Libretto workflow for diagnosing live browser state without clicks, typing, navigation, or mutation requests.
Claude Code
$ npx -y skills add cashew-labs/libretto --skill libretto-readonly --agent claude-code
Codex
$ npx skills add cashew-labs/libretto --skill libretto-readonly -a codex -y
Cursor
$ npx skills add cashew-labs/libretto --skill libretto-readonly -a cursor -y
Gemini CLI
$ npx skills add cashew-labs/libretto --skill libretto-readonly -a gemini-cli -y
GitHub Copilot
$ npx skills add cashew-labs/libretto --skill libretto-readonly -a github-copilot -y
OpenCode
$ npx skills add cashew-labs/libretto --skill libretto-readonly -a opencode -y
Windsurf
$ npx skills add cashew-labs/libretto --skill libretto-readonly -a windsurf -y
name: libretto-readonly description: "Read-only Libretto workflow for diagnosing live browser state without clicks, typing, navigation, or mutation requests." license: MIT metadata: author: saffron-health version: "0.6.45"
libretto connect http://127.0.0.1:9222 --read-only --session failed-job-debug
libretto pages --session failed-job-debug
Standard JS globals `console`, `URL`, `Buffer`, `setTimeout`, and `setInterval` are also available.
libretto readonly-exec "return page.url()" --session failed-job-debug
libretto readonly-exec "return await page.getByRole('heading').first().textContent()" --session failed-job-debug
libretto readonly-exec "return await page.frames()[1]?.getByRole('heading').textContent()" --session failed-job-debug
# HTTP GET inspection
echo "const r = await get('https://api.example.com/status'); return await r.json()" \
| libretto readonly-exec - --session failed-job-debug
# Scroll down to inspect below-the-fold content
libretto readonly-exec "await scrollBy(0, 500)" --session failed-job-debuglibretto close --session failed-job-debug
Libretto is a toolkit for building robust web integrations. It gives your coding agent a live browser and a token-efficient CLI to: Inspect live pages with minimal context overhead Capture network traffic to reverse-engineer site APIs Record user actions and
Browser automation CLI for building, maintaining, and running browser automation workflows by inspecting live pages and…
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web…
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…