skills/web-browser/SKILL.md
Allows to interact with web pages by performing actions such as clicking buttons, filling out forms, and navigating links. It works by remote controlling Google Chrome or Chromium browsers using the Chrome DevTools Protocol (CDP). When Claude needs to browse the web, it can use this skill to do so.
npx skillsauth add mitsuhiko/agent-commands web-browserInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Minimal CDP tools for collaborative site exploration.
./scripts/start.js # Isolated reusable profile (default)
./scripts/start.js --profile # Copy your profile into isolated cache
./scripts/start.js --reset-profile # Clear selected cached profile before launch
Starts Chrome with remote debugging (default port :9222).
Profile behavior:
~/.cache/agent-web/browser/fresh-profile--profile mode uses: ~/.cache/agent-web/browser/profile-copy:9222 is already used by an unknown instance, start will fail instead of reusing itIf Chrome is installed in a non-standard location, set:
BROWSER_BIN=/path/to/chrome ./scripts/start.js
Optional debug endpoint override:
BROWSER_DEBUG_PORT=9333 ./scripts/start.js
./scripts/nav.js https://example.com
./scripts/nav.js https://example.com --new
Navigate current tab or open new tab.
./scripts/emulate.js --list
./scripts/emulate.js iphone-14
./scripts/emulate.js pixel-7 --landscape
./scripts/emulate.js --reset
Set an active device emulation preference (viewport, DPR, touch, UA) for browser skill commands. Use --reset to clear.
Commands like nav.js, eval.js, pick.js, dismiss-cookies.js, and screenshot.js automatically apply the active preference.
./scripts/eval.js 'document.title'
./scripts/eval.js 'document.querySelectorAll("a").length'
./scripts/eval.js 'document.querySelector("button")?.click(); "clicked"'
./scripts/eval.js 'await Promise.resolve(document.title)'
./scripts/eval.js 'JSON.stringify(Array.from(document.querySelectorAll("a")).map(a => ({ text: a.textContent.trim(), href: a.href })).filter(link => !link.href.startsWith("https://")))'
Execute JavaScript in the active tab. Input can be an expression or statement list; the console-style completion value is printed and promises/top-level await are awaited. Be careful with string escaping, best to use single quotes.
./scripts/screenshot.js
./scripts/screenshot.js --full-page
./scripts/screenshot.js --device iphone-14
./scripts/screenshot.js --device pixel-7 --full-page
Takes a screenshot and returns a temp file path.
--full-page: captures full document height--device <preset>: temporary mobile emulation for that screenshot only./scripts/pick.js "Click the submit button"
Interactive element picker. Click to select, Cmd/Ctrl+Click for multi-select, Enter to finish.
./scripts/dismiss-cookies.js # Accept cookies
./scripts/dismiss-cookies.js --reject # Reject cookies (where possible)
Automatically dismisses EU cookie consent dialogs.
Run after navigating to a page:
./scripts/nav.js https://example.com && ./scripts/dismiss-cookies.js
./scripts/start.js
./scripts/nav.js https://example.com
./scripts/emulate.js iphone-14
./scripts/nav.js https://example.com # reload with mobile UA
./scripts/dismiss-cookies.js
./scripts/screenshot.js --full-page
Automatically started by start.js and writes JSONL logs to:
~/.cache/agent-web/logs/YYYY-MM-DD/<targetId>.jsonl
Manually start:
./scripts/watch.js
Tail latest log:
./scripts/logs-tail.js # dump current log and exit
./scripts/logs-tail.js --follow # keep following
Summarize network responses:
./scripts/net-summary.js
development
Trigger native web search. Use when you need quick internet research with concise summaries and full source URLs.
development
Use `uv` instead of pip/python/venv. Run scripts with `uv run script.py`, add deps with `uv add`, use inline script metadata for standalone scripts.
documentation
Read this skill before updating changelogs
tools
Remote control tmux sessions for interactive CLIs (python, gdb, etc.) by sending keystrokes and scraping pane output.