Skip to content
TakoAPI
Back to skills

agent-browser

by matrixy

Clawdbot Tools
26.2kDownloads reported by clawskills.sh
66Stars
18Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Headless browser automation CLI optimized for AI agents.

Description

What This Skill Does

Headless browser automation CLI built for AI agent workflows. Takes accessibility tree snapshots of web pages and exposes interactive elements as stable refs (like @e2, @e3) for deterministic targeting. Supports isolated sessions, saved auth state, and network interception.

Ref-based element selection from accessibility tree snapshots avoids the fragility of CSS selectors and XPath that break when layouts change.

When to Use It

  • Automating multi-step web form submissions without brittle selectors
  • Running simultaneous admin and user browser sessions for testing
  • Scraping dynamic single-page apps that require JavaScript execution
  • Reusing saved login state to skip authentication on repeat runs
  • Mocking API responses during automated browser workflows

Example Workflow

INPUT

User asks: search Google for 'AI agents' and return the first result link

AGENT
  1. 1

    Run agent-browser open https://www.google.com

  2. 2

    Run agent-browser snapshot -i --json to get interactive element refs

  3. 3

    Identify search box ref from snapshot, run agent-browser fill @e1 "AI agents" then agent-browser press Enter

  4. 4

    Run agent-browser wait --load networkidle, then agent-browser snapshot -i --json again

  5. 5

    Run agent-browser get attr @e4 "href" --json to extract the first result URL

OUTPUT

Returns the href value of the first search result as JSON

Requirements

  • agent-browser CLI installed globally via npm install -g agent-browser

Installation

clawhub install matrixy/agent-browser-clawdbot

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links