Browser Use

Browser Automation with playwright-cli

Authentication → attach to the user's live Chrome. Any time a task needs a signed-in session (logging in, or reaching anything behind a login or bot challenge), use attach --extension=chrome to drive the user's real Chrome with its existing logins, instead of launching a fresh browser with open. Playwright-launched Chromium and WebKit get flagged by Google/OAuth as an insecure browser and the sign-in is blocked. See references/extension-attach.md.

House patterns (use these by default)

# One NAMED session per task (-s=dash, -s=mail, -s=print …); pass the same -s to every
# follow-up command. Parallel tasks never collide, and the default session stays clean.
playwright-cli -s=dash open https://dash.example.com

# Signed-in work: attach to the user's real Chrome. Token skips the "Share this tab" dialog.
PLAYWRIGHT_MCP_EXTENSION_TOKEN=<token> playwright-cli -s=mail attach --extension=chrome
# Stale attach session? close-then-reattach is the reliable reset:
playwright-cli -s=mail close 2>/dev/null; PLAYWRIGHT_MCP_EXTENSION_TOKEN=<token> playwright-cli -s=mail attach --extension=chrome

# Big pages: write the snapshot to a file and grep it, instead of dumping it into context
playwright-cli -s=dash snapshot --filename=.playwright-cli/cur.yml >/dev/null 2>&1
grep -n -iE 'button|save|error' .playwright-cli/cur.yml

# Pixel-accurate rendering (resumes, print layouts): resize to exact CSS px
# (816x1056 = US Letter at 96dpi), then capture
playwright-cli -s=print resize 816 1056
playwright-cli -s=print screenshot --full-page --filename=page.png
playwright-cli -s=print pdf --filename=page.pdf

# --raw for shell pipelines (values only, no status/snapshot chrome)
playwright-cli --raw eval "JSON.stringify([...document.querySelectorAll('a')].map(a => a.href))" | jq .

Commands

Core

# `open` defaults to HEADLESS. Pass --headed when the human needs to see
# the window (e.g. they're driving the browser themselves, or you're
# debugging by eyeball). Headless is fine for scripted automation.
playwright-cli open
playwright-cli open --headed
# open and navigate right away
playwright-cli open https://example.com/
playwright-cli goto https://playwright.dev
playwright-cli type "search query"
playwright-cli click e3
playwright-cli dblclick e7
# --submit presses Enter after filling the element
playwright-cli fill e5 "user@example.com"  --submit
playwright-cli drag e2 e8
# drop files or data onto an element (from outside the page)
playwright-cli drop e4 --path=./image.png
playwright-cli drop e4 --data="text/plain=hello world"
playwright-cli hover e4
playwright-cli select e9 "option-value"
playwright-cli upload ./document.pdf
playwright-cli check e12
playwright-cli uncheck e12
playwright-cli snapshot
playwright-cli eval "document.title"
playwright-cli eval "el => el.textContent" e5
# get element id, class, or any attribute not visible in the snapshot
playwright-cli eval "el => el.id" e5
playwright-cli eval "el => el.getAttribute('data-testid')" e5
playwright-cli dialog-accept
playwright-cli dialog-accept "confirmation text"
playwright-cli dialog-dismiss
playwright-cli resize 1920 1080
playwright-cli close

Navigation

playwright-cli go-back
playwright-cli go-forward
playwright-cli reload

Keyboard

playwright-cli press Enter
playwright-cli press ArrowDown
playwright-cli keydown Shift
playwright-cli keyup Shift

Mouse

playwright-cli mousemove 150 300
playwright-cli mousedown
playwright-cli mousedown right
playwright-cli mouseup
playwright-cli mouseup right
playwright-cli mousewheel 0 100

Save as

playwright-cli screenshot
playwright-cli screenshot e5
playwright-cli screenshot --filename=page.png
# full scrollable page, not just the viewport
playwright-cli screenshot --full-page
# device pixels (honors devicePixelRatio) instead of css pixels
playwright-cli screenshot --hires
playwright-cli pdf --filename=page.pdf

Tabs

playwright-cli tab-list
playwright-cli tab-new
playwright-cli tab-new https://example.com/page
playwright-cli tab-close
playwright-cli tab-close 2
playwright-cli tab-select 0

Storage

playwright-cli state-save
playwright-cli state-save auth.json
playwright-cli state-load auth.json

# Cookies
playwright-cli cookie-list
playwright-cli cookie-list --domain=example.com
playwright-cli cookie-get session_id
playwright-cli cookie-set session_id abc123
playwright-cli cookie-set session_id abc123 --domain=example.com --httpOnly --secure
playwright-cli cookie-delete session_id
playwright-cli cookie-clear

# LocalStorage
playwright-cli localstorage-list
playwright-cli localstorage-get theme
playwright-cli localstorage-set theme dark
playwright-cli localstorage-delete theme
playwright-cli localstorage-clear

# SessionStorage
playwright-cli sessionstorage-list
playwright-cli sessionstorage-get step
playwright-cli sessionstorage-set step 3
playwright-cli sessionstorage-delete step
playwright-cli sessionstorage-clear

Network

# list all requests since page load, numbered for use with `request`
playwright-cli requests
# full details / just one part of a single request by its number
playwright-cli request 5
playwright-cli request-headers 5
playwright-cli request-body 5
playwright-cli response-headers 5
# textual bodies inline; binary bodies saved to a file, path printed
playwright-cli response-body 5

# Mocking
playwright-cli route "**/*.jpg" --status=404
playwright-cli route "https://api.example.com/**" --body='{"mock": true}'
playwright-cli route-list
playwright-cli unroute "**/*.jpg"
playwright-cli unroute

# Simulate offline / restore connectivity
playwright-cli network-state-set offline
playwright-cli network-state-set online

DevTools

playwright-cli console
playwright-cli console warning
playwright-cli run-code "async page => await page.context().grantPermissions(['geolocation'])"
playwright-cli run-code --filename=script.js
playwright-cli tracing-start
playwright-cli tracing-stop
playwright-cli video-start video.webm
playwright-cli video-chapter "Chapter Title" --description="Details" --duration=2000
playwright-cli video-stop

# annotate each subsequent action (click, type, ...) with a callout naming the action
# and highlighting the target — great for demo/walkthrough videos
playwright-cli video-show-actions --duration=600 --position=top-right
playwright-cli video-hide-actions

# launch the dashboard for UI review / design feedback — user annotates the page,
# you receive the annotated screenshot, snapshot, and notes
playwright-cli show --annotate

# generate a stable Playwright locator for an element from its ref or selector
playwright-cli generate-locator e5 --raw

# persistent highlight overlay for an element (point the user at something on screen)
playwright-cli highlight e5
playwright-cli highlight e5 --style="outline: 3px dashed red"
playwright-cli highlight e5 --hide
playwright-cli highlight --hide   # hide all highlights

Raw output

The global --raw option strips page status, generated code, and snapshot sections from the output, returning only the result value. Use it to pipe command output into other tools. Commands that don't produce output return nothing.

playwright-cli --raw eval "JSON.stringify(performance.timing)" | jq '.loadEventEnd - .navigationStart'
playwright-cli --raw eval "JSON.stringify([...document.querySelectorAll('a')].map(a => a.href))" > links.json
playwright-cli --raw snapshot > before.yml
playwright-cli click e5
playwright-cli --raw snapshot > after.yml
diff before.yml after.yml
TOKEN=$(playwright-cli --raw cookie-get session_id)
playwright-cli --raw localstorage-get theme

For structured output wrapping every reply as JSON, pass --json:

playwright-cli list --json

Open parameters

playwright-cli open --headed   # show the window (default is headless)

# Use specific browser when creating session
playwright-cli open --browser=chrome
playwright-cli open --browser=firefox
playwright-cli open --browser=webkit
playwright-cli open --browser=msedge

# Use persistent profile (by default profile is in-memory)
playwright-cli open --persistent
# Use persistent profile with custom directory
playwright-cli open --profile=/path/to/profile

# Connect to the user's real Chrome via the bridge extension (their logins/cookies).
# Set PLAYWRIGHT_MCP_EXTENSION_TOKEN to skip the "Share this tab" dialog; use a named
# session (-s=name) so you don't disturb the default browser. See references/extension-attach.md
PLAYWRIGHT_MCP_EXTENSION_TOKEN=<token> playwright-cli -s=name attach --extension=chrome
playwright-cli attach --extension

# Attach to a running Chrome/Edge by channel name (needs remote debugging enabled
# via chrome://inspect/#remote-debugging), or to any CDP endpoint
playwright-cli attach --cdp=chrome
playwright-cli attach --cdp=msedge
playwright-cli attach --cdp=http://localhost:9222

# Start with config file
playwright-cli open --config=my-config.json

# Close the browser
playwright-cli close
# Detach from an attached browser (leaves the external browser running;
# only for sessions created via `attach` — `open` sessions use `close`)
playwright-cli -s=name detach
# Delete user data for the default session
playwright-cli delete-data

Snapshots

After each command, playwright-cli provides a snapshot of the current browser state.

> playwright-cli goto https://example.com
### Page
- Page URL: https://example.com/
- Page Title: Example Domain
### Snapshot
[Snapshot](.playwright-cli/page-2026-02-14T19-22-42-679Z.yml)

You can also take a snapshot on demand using playwright-cli snapshot command. All the options below can be combined as needed.

# default - save to a file with timestamp-based name
playwright-cli snapshot

# save to file, use when snapshot is a part of the workflow result
playwright-cli snapshot --filename=after-click.yaml

# snapshot an element instead of the whole page
playwright-cli snapshot "#main"

# limit snapshot depth for efficiency, take a partial snapshot afterwards
playwright-cli snapshot --depth=4
playwright-cli snapshot e34

# include each element's bounding box as [box=x,y,width,height]
# (viewport-relative css pixels — pairs well with mousemove/mousedown)
playwright-cli snapshot --boxes

Targeting elements

By default, use refs from the snapshot to interact with page elements.

# get snapshot with refs
playwright-cli snapshot

# interact using a ref
playwright-cli click e15

You can also use css selectors or Playwright locators.

# css selector
playwright-cli click "#main > button.submit"

# role locator
playwright-cli click "getByRole('button', { name: 'Submit' })"

# test id
playwright-cli click "getByTestId('submit-button')"

Browser Sessions

# create new browser session named "mysession" with persistent profile
playwright-cli -s=mysession open example.com --persistent
# same with manually specified profile directory (use when requested explicitly)
playwright-cli -s=mysession open example.com --profile=/path/to/profile
playwright-cli -s=mysession click e6
playwright-cli -s=mysession close  # stop a named browser
playwright-cli -s=mysession delete-data  # delete user data for persistent session

playwright-cli list
# Close all browsers
playwright-cli close-all
# Forcefully kill all browser processes
playwright-cli kill-all

Installation

If global playwright-cli command is not available, try a local version via npx playwright-cli:

npx --no-install playwright-cli --version

When local version is available, use npx playwright-cli in all commands. Otherwise, install playwright-cli as a global command:

npm install -g @playwright/cli@latest

This skill is a customized fork — do not install --skills

This skill is the upstream playwright-cli skill plus customizations (extension-attach guidance, house patterns). It lives at ~/.claude/skills/browser-use, not .claude/skills/playwright-cli, so the CLI's version check doesn't flag the differences. Never run playwright-cli install --skills: it would install the stock skill alongside this one as a near-duplicate. After a CLI upgrade, diff against the bundled copy and merge by hand:

diff -r ~/.claude/skills/browser-use "$(npm root -g)/@playwright/cli/node_modules/playwright-core/lib/tools/cli-client/skill"

Example: Debugging with DevTools

playwright-cli open https://example.com
playwright-cli click e4
playwright-cli fill e7 "test"
playwright-cli console
playwright-cli requests
playwright-cli close

playwright-cli open https://example.com
playwright-cli tracing-start
playwright-cli click e4
playwright-cli fill e7 "test"
playwright-cli tracing-stop
playwright-cli close

Example: Interactive session

Ask the user for UI review or design feedback. The user draws boxes on the live page and types comments; you receive the annotated screenshot, the snapshot of the marked region, and the user's notes. Use this whenever the user asks for "UI review", "design feedback", or to "ask the user what they think / want / mean":

playwright-cli open https://example.com
playwright-cli show --annotate

Specific tasks

• Running and Debugging Playwright tests references/playwright-tests.md
• Request mocking references/request-mocking.md
• Running Playwright code references/running-code.md
• Browser session management (incl. attach/detach, CDP) references/session-management.md
• Attaching to the user's real Chrome (extension) references/extension-attach.md
• Spec-driven testing (plan / generate / heal) references/spec-driven-testing.md
• Storage state (cookies, localStorage) references/storage-state.md
• Test generation references/test-generation.md
• Tracing references/tracing.md
• Video recording references/video-recording.md
• Inspecting element attributes references/element-attributes.md