agent-browser

name	agent-browser
description	Browser automation CLI for AI agents. Use when the user needs to interact with websites, verify dev server output, test web apps, navigate pages, fill forms, click buttons, take screenshots, extract data, or automate any browser task. Also triggers when a dev server starts so you can verify it visually.
metadata	{"priority":3,"docs":["https://docs.anthropic.com/en/docs/claude-code/sub-agents"],"pathPatterns":["agent-browser.json","playwright.config.*","e2e/**","tests/e2e/**","test/e2e/**","cypress/**","cypress.config.*"],"bashPatterns":["\\bagent-browser\\b","\\bnext\\s+dev\\b","\\bnpm\\s+run\\s+dev\\b","\\bpnpm\\s+dev\\b","\\bbun\\s+run\\s+dev\\b","\\byarn\\s+dev\\b","\\bvite\\b","\\bnuxt\\s+dev\\b","\\bvercel\\s+dev\\b","\\blocalhost:\\d+","\\b127\\.0\\.0\\.1:\\d+","\\bcurl\\s+.*localhost","\\bopen\\s+https?://","\\bplaywright\\b","\\bcypress\\b"]}
retrieval	{"aliases":["browser automation","puppeteer","playwright","web scraping"],"intents":["automate browser","take screenshot","test web app","fill form","click button"],"entities":["Puppeteer","Playwright","screenshot","browser","headless"]}
chainTo	[{"pattern":"localhost:\\d+|127\\.0\\.0\\.1:\\d+","targetSkill":"agent-browser-verify","message":"Dev server URL detected — loading browser verification skill to run a visual gut-check (page loads, console errors, key UI elements)."},{"pattern":"playwright\\.config|cypress\\.config|\\.spec\\.(ts|js)|\\.test\\.(ts|js).*browser","targetSkill":"nextjs","message":"End-to-end test configuration detected — loading Next.js guidance for framework-aware test setup and dev server integration."}]

Browser Automation with agent-browser

The CLI uses Chrome/Chromium via CDP directly. Install via npm i -g agent-browser, brew install agent-browser, or cargo install agent-browser. Run agent-browser install to download Chrome. Run agent-browser upgrade to update to the latest version.

Core Workflow

Every browser automation follows this pattern:

1. Navigate: agent-browser open <url>
2. Snapshot: agent-browser snapshot -i (get element refs like @e1, @e2)
3. Interact: Use refs to click, fill, select
4. Re-snapshot: After navigation or DOM changes, get fresh refs

agent-browser open https://example.com/form
agent-browser snapshot -i
# Output: @e1 [input type="email"], @e2 [input type="password"], @e3 [button] "Submit"

agent-browser fill @e1 "[e-mail]"
agent-browser fill @e2 "password123"
agent-browser click @e3
agent-browser wait --load networkidle
agent-browser snapshot -i  # Check result

Command Chaining

Commands can be chained with && in a single shell invocation. The browser persists between commands via a background daemon, so chaining is safe and more efficient than separate calls.

# Chain open + wait + snapshot in one call
agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser snapshot -i

# Chain multiple interactions
agent-browser fill @e1 "[e-mail]" && agent-browser fill @e2 "password123" && agent-browser click @e3

# Navigate and capture
agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser screenshot page.png

When to chain: Use && when you don't need to read the output of an intermediate command before proceeding (e.g., open + wait + screenshot). Run commands separately when you need to parse the output first (e.g., snapshot to discover refs, then interact using those refs).