Browser

This is web automation that actually understands AI token constraints. The big win here is the element ref system: instead of dumping entire DOM trees into context, you get @e1, @e2 style references from accessibility snapshots, cutting context by 93%. You open a page, run snapshot with the -i flag for interactive elements only, then click @e2 or fill @e3 directly. It's built on agent-browser and exposes everything through MCP tools with the browser/ prefix. The session system lets you run parallel browser instances, which is neat for swarm patterns. If you're tired of context bloat from traditional Playwright or Puppeteer wrappers, this is the more surgical approach.

skills.sh installs: 674
GitHub stars: 81.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add ruvnet/ruflo --skill browser --agent claude-code

Installs into .claude/skills of the current project.

Files

Browser Automation Skill

Web browser automation using agent-browser with AI-optimized snapshots. Reduces context by 93% using element refs (@e1, @e2) instead of full DOM.

Core Workflow

# 1. Navigate to page
agent-browser open <url>

# 2. Get accessibility tree with element refs
agent-browser snapshot -i    # -i = interactive elements only

# 3. Interact using refs from snapshot
agent-browser click @e2
agent-browser fill @e3 "text"

# 4. Re-snapshot after page changes
agent-browser snapshot -i

Quick Reference

Navigation

Command	Description
`open <url>`	Navigate to URL
`back`	Go back
`forward`	Go forward
`reload`	Reload page
`close`	Close browser

Snapshots (AI-Optimized)

Command	Description
`snapshot`	Full accessibility tree
`snapshot -i`	Interactive elements only (buttons, links, inputs)
`snapshot -c`	Compact (remove empty elements)
`snapshot -d 3`	Limit depth to 3 levels
`screenshot [path]`	Capture screenshot (base64 if no path)