Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution.
SkillScore87Maintained
Automatic
◆AI Engineer pack
Last verified 8/27/2026
What it changes
Passed 17 of 20 test cases with the skill, and 3 of 20 without it.
Without skill17%
With skill87%
Checks it passed that the model alone missed
Uses agent-browser get attr @e5 href
Uses agent-browser wait --load networkidle
Uses agent-browser trace start to begin recording
and 14 more in the full report
16 fixed4 passed either way3 still failing0 broke
Pass-rate lift
+70 pp
Tokens
+156%
Agent turns
0%
Response time
-56%
Model gemini-3.6-flashMeasured 8/27/2026v1120 of 23 cases passed with skill · 20 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 16 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 16
Prompt
I want to click a button labeled 'Submit Application' on a web form without needing to run a DOM snapshot first. What single command finds and clicks this button by its text label?
What was checked, without and with the skill
Checked
Without skill
With skill
Uses agent-browser find text or agent-browser find role button to locate and click
Missed
Passed
case-08 · gemini-3.6-flash · 8/27/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md341 lines9 files
Browser Automation with agent-browser
Quick start
agent-browser open <url> # Navigate to page
agent-browser snapshot -i # Get interactive elements with refs
agent-browser click @e1 # Click element by ref
agent-browser fill @e2 "text" # Fill input by ref
agent-browser close # Close browser
Core workflow
Navigate: agent-browser open <url>
Snapshot: agent-browser snapshot -i (returns elements with refs like @e1, @e2)
Interact using refs from the snapshot
Re-snapshot after navigation or significant DOM changes
Commands
Navigation
agent-browser open <url> # Navigate to URL (aliases: goto, navigate)
# Supports: https://, http://, file://, about:, data://
# Auto-prepends https:// if no protocol given
agent-browser back # Go back
agent-browser forward # Go forward
agent-browser reload # Reload page
agent-browser close # Close browser (aliases: quit, exit)
agent-browser connect 9222 # Connect to browser via CDP port
Snapshot (page analysis)
agent-browser snapshot # Full accessibility tree
agent-browser snapshot -i # Interactive elements only (recommended)
agent-browser snapshot -c # Compact output