// Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Fetches an arXiv paper — metadata (title, authors, abstract) via WebFetch on the abs page, plus the full PDF via curl on arxiv.org/pdf and structured extraction by pdfvision. Use when the URL is in the form arxiv.org/abs/{paper_id}.
Reads GitHub via the gh CLI — repo metadata / README / file tree, issues with comments and timeline, pull requests (diff, files, inline comments, GraphQL review threads with isResolved / isOutdated), discussions (GraphQL), code (file contents and code search), and releases (with tarball / zipball fallback). Routes by URL shape into references/{topic}.md so only the relevant command sheet is loaded. Use when the URL is on github.com.
Fetches MDN Web Docs as raw Markdown by mapping the developer.mozilla.org URL to its source file in mdn/content (en-US) or mdn/translated-content (other locales) on GitHub and curl-ing the raw blob. Cleaner and more compact than rendering the SPA page; falls back to WebFetch on the original URL when the path mapping 404s. Use when the URL is on developer.mozilla.org.
Extracts text (with original line breaks), metadata, per-page character / image density, and optional rendered PNGs from a PDF using pdfvision. Falls back to --render on pages whose density Overview shows low text coverage so multimodal models can read raster slides. Use when the URL ends in .pdf, the user supplies a local PDF path, or another readable-* skill produced a PDF that still needs structured extraction.
Fetches a SpeakerDeck slide deck by extracting the public PDF URL from the slide page (WebFetch), downloading it via curl, and running pdfvision — typically with --render on image-heavy pages so the slides can be read visually. Use when the URL is in the form speakerdeck.com/{user}/{slug}.
Reads web platform specifications via WebFetch — uses the multipage HTML variant for the WHATWG HTML spec, anchor-targeted section reads for W3C TR documents and TC39 / ECMAScript. Returns the relevant section rather than the whole spec, since these documents are too large for a single fetch. Use when the URL is on *.spec.whatwg.org, w3.org/TR/, or tc39.es.
| name | agent-browser |
| description | Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages. |
| metadata | {"internal":true} |
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
agent-browser open <url>agent-browser snapshot -i (returns elements with refs like @e1, @e2)agent-browser open <url> # Navigate to URL
agent-browser back # Go back
agent-browser forward # Go forward
agent-browser reload # Reload page
agent-browser close # Close browser
agent-browser snapshot # Full accessibility tree
agent-browser snapshot -i # Interactive elements only (recommended)
agent-browser snapshot -c # Compact output
agent-browser snapshot -d 3 # Limit depth to 3
agent-browser click @e1 # Click
agent-browser dblclick @e1 # Double-click
agent-browser fill @e2 "text" # Clear and type
agent-browser type @e2 "text" # Type without clearing
agent-browser press Enter # Press key
agent-browser press Control+a # Key combination
agent-browser hover @e1 # Hover
agent-browser check @e1 # Check checkbox
agent-browser uncheck @e1 # Uncheck checkbox
agent-browser select @e1 "value" # Select dropdown
agent-browser scroll down 500 # Scroll page
agent-browser scrollintoview @e1 # Scroll element into view
agent-browser get text @e1 # Get element text
agent-browser get value @e1 # Get input value
agent-browser get title # Get page title
agent-browser get url # Get current URL
agent-browser screenshot # Screenshot to stdout
agent-browser screenshot path.png # Save to file
agent-browser screenshot --full # Full page
agent-browser wait @e1 # Wait for element
agent-browser wait 2000 # Wait milliseconds
agent-browser wait --text "Success" # Wait for text
agent-browser wait --load networkidle # Wait for network idle
agent-browser find role button click --name "Submit"
agent-browser find text "Sign In" click
agent-browser find label "Email" fill "user@test.com"
agent-browser open https://example.com/form
agent-browser snapshot -i
# Output shows: textbox "Email" [ref=e1], textbox "Password" [ref=e2], button "Submit" [ref=e3]
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
# Login once
agent-browser open https://app.example.com/login
agent-browser snapshot -i
agent-browser fill @e1 "username"
agent-browser fill @e2 "password"
agent-browser click @e3
agent-browser wait --url "**/dashboard"
agent-browser state save auth.json
# Later sessions: load saved state
agent-browser state load auth.json
agent-browser open https://app.example.com/dashboard
agent-browser --session test1 open site-a.com
agent-browser --session test2 open site-b.com
agent-browser session list
Add --json for machine-readable output:
agent-browser snapshot -i --json
agent-browser get text @e1 --json
agent-browser open example.com --headed # Show browser window
agent-browser console # View console messages
agent-browser errors # View page errors