agent-browser
por matrixy
Clawdbot ToolsResumo
Headless browser automation CLI optimized for AI agents.
Descrição
O que esta skill faz
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.
Quando usá-la
- 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
Exemplo de fluxo de trabalho
User asks: search Google for 'AI agents' and return the first result link
- 1
Run agent-browser open https://www.google.com
- 2
Run agent-browser snapshot -i --json to get interactive element refs
- 3
Identify search box ref from snapshot, run agent-browser fill @e1 "AI agents" then agent-browser press Enter
- 4
Run agent-browser wait --load networkidle, then agent-browser snapshot -i --json again
- 5
Run agent-browser get attr @e4 "href" --json to extract the first result URL
Returns the href value of the first search result as JSON
Requisitos
- agent-browser CLI installed globally via npm install -g agent-browser
Instalação
clawhub install matrixy/agent-browser-clawdbotExecute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.