agent-browserlisted

# agent-browser core > **moi note:** vendored from the `agent-browser` npm package (v0.27.0, > `agent-browser skills get core --full` serves the copy matching your > installed CLI). In Claude Code cloud sessions the CLI is preinstalled and > `AGENT_BROWSER_EXECUTABLE_PATH` points at the system Chromium — never run > `agent-browser install` (its Chrome download fails behind the egress relay). > Starting the moi server itself: `docs/browser-testing-cloud.md`. Fast browser automation CLI for AI agents. Chrome/Chromium via CDP, no Playwright or Puppeteer dependency. Accessibility-tree snapshots with compact `@eN` refs let agents interact with pages in ~200-400 tokens instead of parsing raw HTML. Most normal web tasks (navigate, read, click, fill, extract, screenshot) are covered here. Load a specialized skill when the task falls outside browser web pages — see [When to load another skill](#when-to-load-another-skill). ## The core loop ```bash agent-browser open <url> # 1. Open a page agent-browser snapshot -i # 2. See what's on it (interactive elements only) agent-browser click @e3 # 3. Act on refs from the snapshot agent-browser snapshot -i # 4. Re-snapshot after any page change ``` Refs (`@e1`, `@e2`, ...) are assigned fresh on every snapshot. They become **stale the moment the page changes** — after clicks that navigate, form submits, dynamic re-renders, dialog opens. Always re-snapshot before your next ref interaction. ## Quickstart ```bash