skilld
All skills
browserbase avatar

/browser

@6afe866 official
by browserbasebrowserbase/skills3.7k stars
240

Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications. Supports remote Browserbase sessions with Browserbase Identity, Verified browsers, automatic CAPTCHA solving, and residential proxies — ideal for protected websites and JavaScript-heavy pages.

Ask your Agent

Use this Skill: https://skilld.dev/gh/browserbase/skills/browser

This session only. Nothing lands on disk.

REFERENCE.md

≈3.9k tokens on demand. Your agent reads this file only when SKILL.md points to it.

Browser Automation CLI Reference

Technical reference for the browse CLI tool.

Table of Contents

Architecture

The browse CLI is a daemon-based command-line tool:

  • Daemon process: A background process manages the browser instance. Auto-starts on the first command (e.g., browse open), persists across commands, and stops with browse stop.
  • Local mode: browse open <url> --local launches a clean isolated local browser. It is the default when BROWSERBASE_API_KEY is unset. Use browse open <url> --auto-connect to attach to an existing debuggable Chrome, or browse open <url> --cdp <port|url> to attach to a specific CDP target.
  • Remote mode (Browserbase): Connects to a Browserbase cloud browser session when BROWSERBASE_API_KEY is set.
  • Accessibility-first: Use browse snapshot to get the page's accessibility tree with element refs, then interact using those refs.

Command Reference

Navigation

open <url>

Navigate to a URL. Auto-starts the daemon if not running.

browse open https://example.com
browse open https://example.com --wait networkidle   # wait for all network requests to finish (useful for SPAs)
browse open https://example.com --wait domcontentloaded

The --wait flag controls when navigation is considered complete. Values: load (default), domcontentloaded, networkidle. Use networkidle for JavaScript-heavy pages that fetch data after initial load.

Context persistence (remote mode only)

Create a Browserbase session with browse cloud sessions create --context-id <id>, then attach to its CDP endpoint with browse open <url> --cdp <connectUrl>. Add --persist to the cloud session if state changes should save back to the context.

SESSION_JSON="$(browse cloud sessions create --context-id ctx_abc123 --persist --keep-alive)"
SESSION_ID="$(echo "$SESSION_JSON" | jq -r .id)"
CONNECT_URL="$(echo "$SESSION_JSON" | jq -r .connectUrl)"

browse open https://example.com --cdp "$CONNECT_URL"
# ...interact with the page...
browse stop
browse cloud sessions update "$SESSION_ID" --status REQUEST_RELEASE
  • --context-id <id> — Browserbase context ID to load when creating the cloud session.
  • --persist — Save cookies/storage changes back to the context when the Browserbase session is released. Requires --context-id.
  • --keep-alive — Keep the Browserbase session alive while the local browse daemon attaches and detaches.
  • After browse open ... --cdp "$CONNECT_URL", follow-up commands in that session do not repeat --cdp; the daemon remembers the attached target.
reload

Reload the current page.

browse reload
back / forward

Navigate browser history.

browse back
browse forward

Page State

snapshot

Get the accessibility tree with interactive element refs. This is the primary way to understand page structure.

browse snapshot
browse snapshot --compact                # tree only, no ref maps

Returns a text representation of the page with refs like @0-5 that can be passed to click. Use --compact for shorter output when you only need the tree.

screenshot [path]

Take a visual screenshot. Slower than snapshot and uses vision tokens.

browse screenshot                        # print base64 JSON
browse screenshot --path ./capture.png   # custom path
browse screenshot --full-page            # capture entire scrollable page
get <property> [selector]

Get page properties. Available properties: url, title, text, html, markdown, value, box, visible, checked.

browse get url                           # current URL
browse get title                         # page title
browse get text "body"                   # all visible text (selector required)
browse get text ".product-info"          # text within a CSS selector
browse get html "#main"                  # inner HTML of an element
browse get markdown                      # full page body as markdown
browse get markdown ".article"           # specific element as markdown
browse get value "#email-input"          # value of a form field
browse get box "#header"                 # bounding box (centroid coordinates)
browse get visible ".modal"              # check if element is visible
browse get checked "#agree"              # check if checkbox/radio is checked

Note: get text and get html require a selector argument — use "body" for full page content. get markdown defaults to body when no selector is given.

Tip: Prefer get markdown over get text or get html when you need readable page content for analysis — it preserves links, headings, and structure without HTML noise.

refs

Show the cached ref map from the last browse snapshot. Useful for looking up element refs without re-running a full snapshot.

browse refs

Interaction

click <ref>

Click an element by its ref from browse snapshot output.

browse click @0-5                        # click element with ref 0-5
click_xy <x> <y>

Click at exact viewport coordinates.

browse click_xy 500 300
hover <x> <y>

Hover at viewport coordinates.

browse hover 500 300
type <text>

Type text into the currently focused element.

browse type "Hello, world!"
browse type "slow typing" --delay 100    # 100ms between keystrokes
browse type "human-like" --mistakes      # simulate human typing with typos
fill <selector> <value>

Fill an input element matching a CSS selector. Add --press-enter when Enter is needed.

browse fill "#search" "browser automation"
browse fill "input[name=email]" "user@example.com"
browse fill "#search" "query" --press-enter   # fill and press Enter
select <selector> <values...>

Select option(s) from a dropdown.

browse select "#country" "United States"
browse select "#tags" "javascript" "typescript"    # multi-select
upload <selector> <files...>

Upload file(s) to an <input type="file"> element. Works with both local and remote Browserbase sessions (remote uses base64 injection). Supports ref-based selectors from snapshot.

browse upload "#fileUpload" ./document.pdf          # single file
browse upload @0-5 ./photo.png                      # using ref from snapshot
browse upload "#files" ./a.png ./b.png              # multiple files
press <key>

Press a keyboard key or key combination.

browse press Enter
browse press Tab
browse press Escape
browse press Cmd+A                       # select all (Mac)
browse press Ctrl+C                      # copy (Linux/Windows)
mouse scroll <x> <y> <deltaX> <deltaY>

Scroll at a given position by a given amount.

browse mouse scroll 500 300 0 -300       # scroll up at (500, 300)
browse mouse scroll 500 300 0 500        # scroll down
mouse drag <fromX> <fromY> <toX> <toY>

Drag from one viewport coordinate to another.

browse mouse drag 80 80 310 100                # drag with default 10 steps
browse mouse drag 80 80 310 100 --steps 20     # more intermediate steps
browse mouse drag 80 80 310 100 --delay 50     # 50ms between steps
browse mouse drag 80 80 310 100 --button right # use right mouse button
browse mouse drag 80 80 310 100 --return-xpath # return source/target XPaths
highlight <selector>

Highlight an element on the page for visual debugging.

browse highlight "#submit-btn"           # highlight for 2 seconds (default)
browse highlight ".nav" -d 5000          # highlight for 5 seconds
is <check> <selector>

Check element state. Available checks: visible, checked.

browse is visible ".modal"               # returns { visible: true/false }
browse is checked "#agree"               # returns { checked: true/false }
wait <type> [arg]

Wait for a condition.

browse wait load                         # wait for page load
browse wait "selector" ".results"        # wait for element to appear
browse wait timeout 3000                 # wait 3 seconds

Session Management

start

Start the browser daemon manually. Usually not needed — the daemon auto-starts on first command.

browse start
stop

Stop the browser daemon and close the browser.

browse stop
browse stop --force                      # force kill if daemon is unresponsive
status

Check whether the daemon is running, its connection details, and current environment.

browse status
Starting sessions with a mode flag

Choose the browser target on the command that starts the session:

browse open https://example.com --local
browse open https://example.com --local --headed
browse open https://example.com --auto-connect
browse open https://example.com --cdp 9222
browse open https://example.com --cdp ws://localhost:9222/devtools/browser/...
browse open https://example.com --remote
  • browse status shows the resolved mode and active target once the daemon is running.
  • browse stop closes the current daemon session; the next browse open chooses mode from its flags or environment.
tab new [url]

Create a new tab, optionally navigating to a URL.

browse tab new                           # open blank tab
browse tab new https://example.com       # open tab with URL
tab list

List all open tabs.

browse tab list
tab switch <index-or-target-id>

Switch to a tab by its index or target ID (from browse tab list).

browse tab switch 1
tab close [index-or-target-id]

Close a tab. Closes current tab if no index given. The CLI refuses to close the last remaining tab.

browse tab close          # close current tab
browse tab close 2        # close tab at index 2

JavaScript Evaluation

eval <expression>

Evaluate JavaScript in the page context.

browse eval "document.title"
browse eval "document.querySelectorAll('a').length"

Viewport

viewport <width> <height>

Set the browser viewport size.

browse viewport 1920 1080

Network Capture

Capture network requests to the filesystem for inspection.

network on

Enable network request capture. Creates a temp directory where requests and responses are saved as JSON files.

browse network on
network off

Disable network capture.

browse network off
network path

Show the capture directory path.

browse network path
network clear

Clear all captured requests.

browse network clear

CDP Event Tailing

cdp <url|port>

Attach to any Chrome DevTools Protocol target and stream events as NDJSON (one JSON object per line). This command bypasses the daemon entirely — it opens a direct WebSocket connection and runs until interrupted.

browse cdp 9222                          # bare port — auto-discovers via /json/version
browse cdp ws://127.0.0.1:9222/devtools/browser/...  # full WebSocket URL
browse cdp wss://connect.browserbase.com/debug/...    # remote Browserbase debug URL

Options:

Flag Description
--domain <domains...> CDP domains to enable (repeatable). Default: Network, Console, Runtime, Log, Page
--pretty Human-readable output instead of JSON. Auto-enabled for TTY

Default domains: Network, Console, Runtime, Log, Page. To capture only specific domains:

browse cdp 9222 --domain Network                     # network events only
browse cdp 9222 --domain Network --domain Console    # network + console

Piping and filtering:

browse cdp 9222 > events.jsonl                       # save to file
browse cdp 9222 | jq '.method'                       # extract method names
browse cdp 9222 | jq 'select(.method == "Network.requestWillBeSent") | .params.request.url'

Pretty output shows compact one-line summaries:

[Target.attachedToTarget] [page] https://example.com
[Network.requestWillBeSent] GET https://example.com/api/data
[Network.responseReceived] 200 https://example.com/api/data
[Runtime.consoleAPICalled] [log] Hello world
[Page.frameNavigated] https://example.com/about

With Browserbase sessions: Use bb sessions debug <session-id> to get the wsUrl, then pass it to browse cdp:

# Get the debug WebSocket URL
bb sessions debug <session-id>
# Copy the wsUrl field and pass it to browse cdp
browse cdp wss://connect.browserbase.com/debug/<session-id>/devtools/browser/...

Configuration

Common Flags

--session <name>

Run commands against a named session, enabling multiple concurrent browsers.

browse open https://a.com --session work
browse open https://b.com --session personal

Context flags such as --context-id and --persist live on browse cloud sessions create; attach to the resulting connectUrl with browse open ... --cdp <connectUrl>.

Environment Variables

Variable Required Description
BROWSE_SESSION No Default session name (alternative to --session)
BROWSERBASE_API_KEY For remote mode API key from https://browserbase.com/settings; makes Browserbase the default desired mode when no override is set
BROWSERBASE_PROJECT_ID No Passed through to Browserbase when set

Without an override, setting BROWSERBASE_API_KEY makes Browserbase the default desired mode. Otherwise the default desired mode is local. Use --local, --remote, --auto-connect, or --cdp <port|url> on browse open when you need an explicit target.

Setting credentials

export BROWSERBASE_API_KEY="bb_live_..."

Get these values from https://browserbase.com/settings.

Error Messages

"No active page"

  • The daemon is running but has no page open.
  • Fix: Run browse open <url>. If the issue persists, run browse stop and retry. For zombie daemons: pkill -f "browse.*daemon".

"Chrome not found" / "Could not find local Chrome installation"

  • Chrome/Chromium is not installed or not in a standard location.
  • Fix: Install Chrome, use browse open <url> --auto-connect if you already have a debuggable Chrome running, or switch to remote with browse open <url> --remote (no local browser needed).

"Daemon not running"

  • No daemon process is active. Most commands auto-start the daemon, but snapshot, click, etc. require an active session.
  • Fix: Run browse open <url> to start a session.

Element ref not found (e.g., "@0-5")

  • The ref from a previous snapshot is no longer valid (page changed).
  • Fix: Run browse snapshot again to get fresh refs.

Timeout errors

  • The page took too long to load or an element didn't appear.
  • Fix: Try browse wait load before interacting, or increase wait time.

Source: SKILL.md on GitHub

Third-party checks

2 warnings16d5 checks · Risk SAFE
  • Gen Agent Trust Hub16d

    This skill provides a standard wrapper for the 'browse' command-line interface tool allowing automated web browser operations locally or via the Browserbase cloud infrastructure. No malicious actions or risks were found; all dependencies and commands align perfectly with legitimate vendor usage.

  • Socket16d

    No alerts

  • Snyk16d

    Risk: MEDIUM · 1 issue

  • Runlayer7mo

    1/4 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Provenance

Signed by skilld at 6afe866. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Activeupdated 3 months ago

Capability

What it can do
Runs commands
All 1 allowed tools
Bash
Other metadata
compatibility
Requires the browse CLI (`npm install -g browse`). Remote Browserbase sessions need `BROWSERBASE_API_KEY`. Local mode uses Chrome/Chromium on your machine.
metadata
{
  "openclaw": {
    "requires": {
      "bins": [
        "browse"
      ]
    },
    "install": [
      {
        "kind": "node",
        "package": "browse",
        "bins": [
          "browse"
        ]
      }
    ],
    "homepage": "https://github.com/browserbase/skills"
  }
}

README badge

README badge for browserbase/skills/browser