菜单
Core agent-browser usage guide — read before running any agent-browser command. Use when the user asks to interact with, test, or automate a website — clicking, filling forms, extracting data, taking screenshots, logging in.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Build, launch, and drive the mindwalk web UI end-to-end for verification.
Set up or troubleshoot Yassimba's curated agent skills, Pi packages, Herdr, and Herdr plugins through the ai-setup CLI. Use when the user asks to install this collection, configure Herdr, add one of its capabilities, update the setup, or diagnose installation problems.
Backlog management: use when the user mentions a backlog, asks what's next, wants work recorded before implementation, or wants queued ideas or specs prioritized, transitioned, completed, or removed; also use when another skill needs to record lifecycle changes.
Use when the user wants to brainstorm or explore an idea — a feature, product direction, or "what if" — before deciding whether it deserves a plan. Ideation only — ends in an idea brief, not a design.
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (this repo's documented coding standards) and Spec (what the originating issue/PRD asked for). Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
Use when creating a git commit — the user asks to commit, or a unit of work is complete and ready to commit.
| name | browser-usage |
| description | Core agent-browser usage guide — read before running any agent-browser command. Use when the user asks to interact with, test, or automate a website — clicking, filling forms, extracting data, taking screenshots, logging in. |
Fast browser automation CLI for AI agents. Chrome/Chromium via CDP, no
Playwright or Puppeteer dependency. Accessibility-tree snapshots with compact
@eN refs let agents interact with pages in ~200-400 tokens instead of
parsing raw HTML.
Most normal web tasks (navigate, read, click, fill, extract, screenshot) are covered here.
agent-browser open <url> # 1. Open a page
agent-browser snapshot -i # 2. See what's on it (interactive elements only)
agent-browser click @e3 # 3. Act on refs from the snapshot
agent-browser snapshot -i # 4. Re-snapshot after any page change
Refs (@e1, @e2, ...) are assigned fresh on every snapshot. They become
stale the moment the page changes — after clicks that navigate, form
submits, dynamic re-renders, dialog opens. Always re-snapshot before your
next ref interaction.
# Install once
npm i -g agent-browser && agent-browser install
# Take a screenshot of a page
agent-browser open https://example.com
agent-browser screenshot home.png
agent-browser close
# Search, click a result, and capture it
agent-browser open https://duckduckgo.com
agent-browser snapshot -i # find the search box ref
agent-browser fill @e1 "agent-browser cli"
agent-browser press Enter
agent-browser wait --load networkidle
agent-browser snapshot -i # refs now reflect results
agent-browser click @e5 # click a result
agent-browser screenshot result.png
The browser stays running across commands so these feel like a single
session. Use agent-browser close (or close --all) when you're done.
agent-browser snapshot # full tree (verbose)
agent-browser snapshot -i # interactive elements only (preferred)
agent-browser snapshot -i -u # include href urls on links
agent-browser snapshot -i -c # compact (no empty structural nodes)
agent-browser snapshot -i -d 3 # cap depth at 3 levels
agent-browser snapshot -s "#main" # scope to a CSS selector
agent-browser snapshot -i --json # machine-readable output
Snapshot output looks like:
Page: Example - Log in
URL: https://example.com/login
@e1 [heading] "Log in"
@e2 [form]
@e3 [input type="email"] placeholder="Email"
@e4 [input type="password"] placeholder="Password"
@e5 [button type="submit"] "Continue"
@e6 [link] "Forgot password?"
For unstructured reading (no refs needed):
agent-browser get text @e1 # visible text of an element
agent-browser get html @e1 # innerHTML
agent-browser get attr @e1 href # any attribute
agent-browser get value @e1 # input value
agent-browser get title # page title
agent-browser get url # current URL
agent-browser get count ".item" # count matching elements
agent-browser click @e1 # click
agent-browser click @e1 --new-tab # open link in new tab instead of navigating
agent-browser dblclick @e1 # double-click
agent-browser hover @e1 # hover
agent-browser focus @e1 # focus (useful before keyboard input)
agent-browser fill @e2 "hello" # clear then type
agent-browser type @e2 " world" # type without clearing
agent-browser press Enter # press a key at current focus
agent-browser press Control+a # key combination
agent-browser check @e3 # check checkbox
agent-browser uncheck @e3 # uncheck
agent-browser select @e4 "option-value" # select dropdown option
agent-browser select @e4 "a" "b" # select multiple
agent-browser upload @e5 file1.pdf # upload file(s)
agent-browser scroll down 500 # scroll page (up/down/left/right)
agent-browser scrollintoview @e1 # scroll element into view
agent-browser drag @e1 @e2 # drag and drop
Use semantic locators:
agent-browser find role button click --name "Submit"
agent-browser find text "Sign In" click
agent-browser find text "Sign In" click --exact # exact match only
agent-browser find label "Email" fill "user@test.com"
agent-browser find placeholder "Search" type "query"
agent-browser find testid "submit-btn" click
agent-browser find first ".card" click
agent-browser find nth 2 ".card" hover
Or a raw CSS selector:
agent-browser click "#submit"
agent-browser fill "input[name=email]" "user@test.com"
agent-browser click "button.primary"
Rule of thumb: snapshot + @eN refs are fastest and most reliable for
AI agents. find role/text/label is next best and doesn't require a prior
snapshot. Raw CSS is a fallback when the others fail.
Agents fail more often from bad waits than from bad selectors. Pick the right wait for the situation:
agent-browser wait @e1 # until an element appears
agent-browser wait 2000 # dumb wait, milliseconds (last resort)
agent-browser wait --text "Success" # until the text appears on the page
agent-browser wait --url "**/dashboard" # until URL matches pattern (glob)
agent-browser wait --load networkidle # until network idle (post-navigation)
agent-browser wait --load domcontentloaded # until DOMContentLoaded
agent-browser wait --fn "window.myApp.ready === true" # until JS condition
After any page-changing action, pick one:
wait @ref or wait --text "...".wait --url "**/new-page".wait --load networkidle.Avoid bare wait 2000 except when debugging — it makes scripts slow and
flaky. Timeouts default to 25 seconds.
agent-browser open https://app.example.com/login
agent-browser snapshot -i
# Pick the email/password refs out of the snapshot, then:
agent-browser fill @e3 "user@example.com"
agent-browser fill @e4 "hunter2"
agent-browser click @e5
agent-browser wait --url "**/dashboard"
agent-browser snapshot -i
Credentials in shell history are a leak. For anything sensitive, use the auth vault (see references/authentication.md):
agent-browser auth save my-app --url https://app.example.com/login \
--username user@example.com --password-stdin
# (type password, Ctrl+D)
agent-browser auth login my-app # fills + clicks, waits for form
# Log in once, save cookies + localStorage
agent-browser state save ./auth.json
# Later runs start already-logged-in
agent-browser --state ./auth.json open https://app.example.com
Or use --session-name for auto-save/restore:
AGENT_BROWSER_SESSION_NAME=my-app agent-browser open https://app.example.com
# State is auto-saved and restored on subsequent runs with the same name.
# Structured snapshot (best for AI reasoning over page content)
agent-browser snapshot -i --json > page.json
# Targeted extraction with refs
agent-browser snapshot -i
agent-browser get text @e5
agent-browser get attr @e10 href
# Arbitrary shape via JavaScript
cat <<'EOF' | agent-browser eval --stdin
const rows = document.querySelectorAll("table tbody tr");
Array.from(rows).map(r => ({
name: r.cells[0].innerText,
price: r.cells[1].innerText,
}));
EOF
Prefer eval --stdin (heredoc) or eval -b <base64> for any JS with
quotes or special characters. Inline agent-browser eval "..." works
only for simple expressions.
agent-browser screenshot # temp path, printed on stdout
agent-browser screenshot page.png # specific path
agent-browser screenshot --full full.png # full scroll height
agent-browser screenshot --annotate map.png # numbered labels + legend keyed to snapshot refs
--annotate is designed for multimodal models: each label [N] maps to ref @eN.
agent-browser tab # list open tabs (with stable tabId)
agent-browser tab new https://docs... # open a new tab (and switch to it)
agent-browser tab 2 # switch to tab 2
agent-browser tab close 2 # close tab 2
Stable tabIds mean tab 2 points at the same tab across commands even
when other tabs open or close. After switching, refs from a prior snapshot
on a different tab no longer apply — re-snapshot.
Each --session <name> is an isolated browser with its own cookies, tabs,
and refs. Useful for testing multi-user flows or parallel scraping:
agent-browser --session a open https://app.example.com
agent-browser --session b open https://app.example.com
agent-browser --session a fill @e1 "alice@test.com"
agent-browser --session b fill @e1 "bob@test.com"
AGENT_BROWSER_SESSION=myapp sets the default session for the current
shell.
agent-browser network route "**/api/users" --body '{"users":[]}' # stub a response
agent-browser network route "**/analytics" --abort # block entirely
agent-browser network requests # inspect what fired
agent-browser network har start # record all traffic
# ... perform actions ...
agent-browser network har stop /tmp/trace.har
agent-browser record start demo.webm
agent-browser open https://example.com
agent-browser snapshot -i
agent-browser click @e3
agent-browser record stop
See references/video-recording.md for codec options, GIF export, and more.
Iframes are auto-inlined in the snapshot — their refs work transparently:
agent-browser snapshot -i
# @e3 [Iframe] "payment-frame"
# @e4 [input] "Card number"
# @e5 [button] "Pay"
agent-browser fill @e4 "4111111111111111"
agent-browser click @e5
To scope a snapshot to an iframe (for focus or deep nesting):
agent-browser frame @e3 # switch context to the iframe
agent-browser snapshot -i
agent-browser frame main # back to main frame
alert and beforeunload are auto-accepted so agents never block. For
confirm and prompt:
agent-browser dialog status # is there a pending dialog?
agent-browser dialog accept # accept
agent-browser dialog accept "text" # accept with prompt input
agent-browser dialog dismiss # cancel
If a command fails unexpectedly (Unknown command, Failed to connect,
stale daemons, version mismatches after upgrade, missing Chrome, etc.)
run doctor before anything else:
agent-browser doctor # full diagnosis (env, Chrome, daemons, config, providers, network, launch test)
agent-browser doctor --offline --quick # fast, local-only
agent-browser doctor --fix # also run destructive repairs (reinstall Chrome, purge old state, ...)
agent-browser doctor --json # structured output for programmatic consumption
doctor auto-cleans stale socket/pid/version sidecar files on every run.
Destructive actions require --fix. Exit code is 0 if all checks pass
(warnings OK), 1 if any fail.
"Ref not found" / "Element not found: @eN"
Page changed since the snapshot. Run agent-browser snapshot -i again,
then use the new refs.
Element exists in the DOM but not in the snapshot It's probably off-screen or not yet rendered. Try:
agent-browser scroll down 1000
agent-browser snapshot -i
# or
agent-browser wait --text "..."
agent-browser snapshot -i
Click does nothing / overlay swallows the click Some modals and cookie banners block other clicks. Snapshot, find the dismiss/close button, click it, then re-snapshot.
Fill / type doesn't work Some custom input components intercept key events. Try:
agent-browser focus @e1
agent-browser keyboard inserttext "text" # bypasses key events
# or
agent-browser keyboard type "text" # raw keystrokes, no selector
Page needs JS you can't get right in one shot
Use eval --stdin with a heredoc instead of inline:
cat <<'EOF' | agent-browser eval --stdin
// Complex script with quotes, backticks, whatever
document.querySelectorAll('[data-id]').length
EOF
Cross-origin iframe not accessible
Cross-origin iframes that block accessibility tree access are silently
skipped. Use frame "#iframe" to switch into them explicitly if the
parent opts in, otherwise the iframe's contents aren't available via
snapshot — fall back to eval in the iframe's origin or use the
--headers flag to satisfy CORS.
Authentication expires mid-workflow
Use --session-name <name> or state save/state load so your session
survives browser restarts. See references/session-management.md
and references/authentication.md.
--session <name> # isolated browser session
--json # JSON output (for machine parsing)
--headed # show the window (default is headless)
--auto-connect # connect to an already-running Chrome
--cdp <port> # connect to a specific CDP port
--profile <name|path> # use a Chrome profile (login state survives)
--headers <json> # HTTP headers scoped to the URL's origin
--proxy <url> # proxy server
--state <path> # load saved auth state from JSON
--session-name <name> # auto-save/restore session state by name
agent-browser skills get electronagent-browser skills get slackagent-browser skills get dogfoodagent-browser skills get vercel-sandboxagent-browser skills get agentcoreEverything covered here plus the complete command/flag/env listing:
agent-browser skills get core --full
That pulls in:
references/commands.md — every command, flag, aliasreferences/snapshot-refs.md — deep dive on the snapshot + ref modelreferences/authentication.md — auth vault, credential handlingreferences/session-management.md — persistence, multi-session workflowsreferences/profiling.md — Chrome DevTools tracing and profilingreferences/video-recording.md — video capture optionsreferences/proxy-support.md — proxy configurationtemplates/* — starter shell scripts for auth, capture, form automation