Agent Browser

This is a Playwright-style browser automation CLI designed for AI agents to drive headless Chrome through natural language tasks. It uses a snapshot-then-interact pattern where you grab element references like @e1, @e2 from an interactive snapshot, then click, fill, or extract from them. The auth vault is clever: save credentials once with encryption, then login without exposing passwords to the LLM. Session persistence means you can stay logged in across runs. Commands chain with && for efficiency since a background daemon keeps the browser alive between calls. Honestly most useful for form automation, web scraping, and testing flows where you need programmatic control but don't want to write full Playwright scripts.

skills.sh installs: 273
GitHub stars: 6
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add andreadellacorte/groove --skill agent-browser --agent claude-code

Installs into .claude/skills of the current project.

Files

Browser Automation with agent-browser

Core Workflow

Every browser automation follows this pattern:

Navigate: agent-browser open <url>
Snapshot: agent-browser snapshot -i (get element refs like @e1, @e2)
Interact: Use refs to click, fill, select
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 "user@example.com"
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

SKILL.md on GitHub