agent browser

    0

    A browser automation CLI for AI agents to navigate, interact, and extract data from the web using stable @refs.

    $1.49

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    agent browser

    Example session with this skill installed

    Open https://news.ycombinator.com, take a snapshot of the top stories, and then take a screenshot.

    • Read your context and instructions
    • Compiled the agent browser

    I have navigated to Hacker News, captured the interactive element references for the top stories, and saved a screenshot of the current page layout.

    Browser Automation Result

    ActionResultDetails
    NavigateSuccessLoaded https://news.ycombinator.com
    SnapshotCaptured30 story links identified (@e1-@e30)
    ScreenshotSaved/tmp/agent-browser/screenshot_1715684201.png

    Identified Elements (Sample)

    • @e1: [link] "Why I'm sued by a patent troll"
    • @e2: [link] "Show HN: A new way to build agents"
    • @e3: [link] "The history of Lisp"
    • @e4: [button] "More"

    Next steps

    1. Use agent-browser click @e1 to navigate to the first story.
    2. Run agent-browser get text @e1 to extract the specific headline text.
    3. Use agent-browser batch to click a story and capture its content in one call.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Building browser-based agents often fails due to complex DOM structures, flaky selectors, and authentication hurdles. This skill provides a CLI-driven browser automation layer designed specifically for LLM agents to interact with the web using Chrome/Chromium via CDP.

    What it does

    • Smart Element Discovery provides an accessibility tree snapshot with short @refs for easy element targeting.
    • Session Management maintains state across browser restarts using sessions, persistent profiles, or auth vaults.
    • Visual Verification captures screenshots, annotated views with element labels, and visual diffs to verify actions.
    • Network Control inspects, filters, or blocks XHR/Fetch requests and records HAR files for debugging.
    • Multi-Platform Support executes automations on local Chrome, iOS Simulators, or cloud providers like AgentCore and Browserbase.
    • Efficiency Tooling supports command chaining and batching to minimize tool calls and context window usage.

    How it works

    1. Target Discovery: Run agent-browser open followed by snapshot -i to see interactive elements and their assigned refs.
    2. Interaction: Execute commands like click @e1 or fill @e2 using the discovered refs to manipulate the page.
    3. Observation: Use screenshot or get text to extract data and verify the page state after interaction.
    4. Automation: Batch multiple commands together using the batch command to perform complex sequences in a single call.

    Frameworks & tools

    Built for Chrome/Chromium via Chrome DevTools Protocol (CDP). Supports Node.js, Homebrew, and Cargo installations. Compatible with iOS Simulators (Appium/Xcode) and cloud browser providers including AgentCore, Browserbase, and Lightpanda.

    Why this beats prompting it yourself

    Writing raw Puppeteer or Playwright code inside a prompt is brittle and consumes excessive tokens. This skill abstracts the browser into a high-level CLI that uses stable @refs, handling frame inlining and session persistence automatically so the agent stays focused on the logic rather than the implementation details.

    Use cases

    • Automate complex form submissions across multiple pages with persistent login state.
    • Scrape dynamic web content by discovering elements semantically and extracting clean text or JSON.
    • Perform visual regression testing by comparing snapshots or screenshots against a baseline.
    • Build cross-platform agents that run identical automation scripts on both desktop and mobile layouts.

    Known limitations

    Lightpanda engine does not support extensions, profiles, or state files. iOS automation requires a macOS host with Xcode and Appium installed. Default timeouts may need adjustment for high-latency sites.

    Lightpanda engine lacks extension/profile support. iOS requires macOS/Xcode/Appium. Networkidle wait strategy may hang on sites with persistent tracking or websockets.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 8 days ago

    Requires

    Httpbin
    agent-browser
    Node.js
    macOS

    Permissions

    Terminal / Shell
    Browser
    Network Access
    Read Files
    Write Files

    Allowed Hosts

    proxy.example.com
    httpbin.org
    Listed8 days ago

    What's inside

    Frequently Asked Questions

    Unlike raw Playwright scripts, this skill uses a "Smart Element Discovery" system that assigns short, stable @refs to interactive elements, significantly reducing token consumption and preventing failures caused by changing DOM structures.

    Yes, the skill supports persistent profiles and auth vaults, allowing your agent to maintain login states and sessions across multiple browser restarts without re-authenticating every time.

    The skill is compatible with local Chrome/Chromium via CDP, iOS Simulators (via Appium), and cloud-based providers like Browserbase, AgentCore, and Lightpanda.

    The package includes the full CLI-driven automation layer, visual verification tools for screenshots/diffs, and comprehensive documentation for integrating the @ref system into your agent's workflow.

    To minimize latency and context window usage, you can use the 'batch' command to chain multiple actions—like filling a form and clicking submit—into a single tool call.

    iOS automation requires a macOS host with Xcode and Appium installed, while the Lightpanda engine has specific restrictions such as no support for extensions or state files.

    New in Agents & Orchestration