---

name: gsd-browser description: > Native Rust browser automation CLI for AI agents. Use when the user needs to interact with websites — navigating pages, filling forms, clicking buttons, taking screenshots, sharing a live browser view, narrating browser actions, extracting structured data, running assertions, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "show me the browser", "share the screen", "pause the browser", "step through this", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", "visual regression test", "check for prompt injection", or any task requiring programmatic web interaction. allowed-tools: Bash(gsd-browser:*), Bash(gsd-browser *)

Browser Automation with gsd-browser

Critical Rules

1. The daemon auto-starts on browser commands. daemon health only reports state; it does not start a session. Use daemon start only when you want to pre-warm or verify daemon lifecycle explicitly.
2. Always re-snapshot after page changes. Refs are versioned (@v1:e1). After navigation, form submission, or dynamic content loading, old refs are stale. Run gsd-browser snapshot to get fresh refs.
3. Use --json when parsing output. Use text mode when reading output yourself. Use --json when you need to extract values programmatically (e.g., checking assertion results, parsing snapshot refs).
4. Positional args have no flag prefix. Commands like click, type, hover take positional args — do NOT add --selector. See exact syntax in command reference below.
5. Use batch for atomic multi-step flows. Batch reduces round trips and keeps pass/fail checks in one call. Use separate commands when you need intermediate output (e.g., snapshot to discover refs).
6. Use view when the user wants to watch or direct the browser. The live viewer is an authenticated local workbench with Control, Annotate, Record, and Sensitive modes. Keep CLI commands on the same named session.

Core Workflow

Every browser automation follows this pattern:

1. Navigate: gsd-browser navigate <url>
2. Snapshot: gsd-browser snapshot (get versioned refs like @v1:e1, @v1:e2)
3. Interact: Use refs to click, fill, hover
4. Re-snapshot: After navigation or DOM changes, get fresh refs

gsd-browser navigate https://example.com/form
gsd-browser snapshot
# Output: @v1:e1 [input type="email"], @v1:e2 [input type="password"], @v1:e3 [button] "Submit"

gsd-browser fill-ref @v1:e1 "user@example.com"
gsd-browser fill-ref @v1:e2 "password123"
gsd-browser click-ref @v1:e3
gsd-browser wait-for --condition network_idle
gsd-browser snapshot  # REQUIRED — old refs are now stale

Command Chaining

Commands can be chained with && in a single shell invocation. Browser state also persists across separate invocations through the background daemon when you stay on the same session.

# Chain navigate + wait + snapshot
gsd-browser navigate https://example.com && gsd-browser wait-for --condition network_idle && gsd-browser snapshot

# Chain multiple interactions
gsd-browser fill-ref @v1:e1 "user@example.com" && gsd-browser fill-ref @v1:e2 "password123" && gsd-browser click-ref @v1:e3

When to chain: Use && when you don't need intermediate output. Run commands separately when you need to parse output first (e.g., snapshot to discover refs, then interact).

---

Command Reference

Argument syntax: <arg> = required positional, [arg] = optional positional, --flag = named option. Do NOT add -- prefix to positional args.

Navigation

gsd-browser navigate <url>                        # Navigate to a URL
gsd-browser back                                   # Go back in browser history
gsd-browser forward                                # Go forward in browser history
gsd-browser reload                                 # Reload the current page

Interaction

All selectors are positional — do NOT use --selector.

# Click
gsd-browser click <selector>                       # Click by CSS selector
gsd-browser click --x 100 --y 200                  # Click by coordinates (no selector)

# Type — positional: <selector> <text>
gsd-browser type <selector> <text>                 # Atomic fill (replaces content)
gsd-browser type <selector> <text> --slowly        # Character-by-character
gsd-browser type <selector> <text> --clear-first   # Clear field before typing
gsd-browser type <selector> <text> --submit        # Press Enter after typing

# Other interaction — all positional selectors
gsd-browser press <key>                            # Press key: Enter, Escape, Tab, Meta+A
gsd-browser hover <selector>                       # Hover over element
gsd-browser scroll --direction down                # Scroll down 300px (default)
gsd-browser scroll --direction up --amount 500     # Scroll up 500px
gsd-browser select-option <selector> <option>      # Select dropdown by label or value
gsd-browser set-checked <selector> --checked       # Check checkbox/radio (omit --checked to uncheck)
gsd-browser drag <source-selector> <target-selector>  # Drag-and-drop
gsd-browser upload-file <selector> <file>...       # Set files on <input type="file">
gsd-browser set-viewport --preset mobile           # Preset: mobile, tablet, desktop, wide
gsd-browser set-viewport --width 1920 --height 1080  # Custom dimensions

Snapshot & Refs

Refs are versioned (@v1:e1, @v2:e3). The version increments each snapshot. Old refs become stale after page changes — always re-snapshot.

# Take snapshot
gsd-browser snapshot                               # Snapshot interactive elements, assign refs
gsd-browser snapshot --selector "form"             # Scope to a CSS selector
gsd-browser snapshot --mode <mode>                 # Semantic mode (see below)
gsd-browser snapshot --limit 80                    # Increase element limit (default: 40)

# Use refs — all positional
gsd-browser get-ref <ref>                          # Get metadata for a ref
gsd-browser click-ref <ref>                        # Click element by ref
gsd-browser hover-ref <ref>                        # Hover element by ref
gsd-browser fill-ref <ref> <text>                  # Type into element by ref

Snapshot modes (--mode):

| Mode | What it captures | |------|-----------------| | interactive | Buttons, inputs, links, selects (default) | | form | Form fields with labels and current values | | dialog | Elements inside open dialogs/modals | | navigation | Links and nav elements | | errors | Error messages, validation warnings | | headings | Heading elements (h1-h6) for page structure | | visible_only | All visible elements regardless of interactivity |

Inspection

gsd-browser accessibility-tree                     # Full accessibility tree (roles, names, states)
gsd-browser find --text "Sign In"                  # Find elements by text (case-insensitive)
gsd-browser find --role button                     # Find by ARIA role
gsd-browser find --selector ".my-class"            # Find by CSS selector
gsd-browser find --role link --limit 50            # Increase limit (default: 20)
gsd-browser page-source                            # Get raw HTML of page
gsd-browser page-source --selector "main"          # Scoped HTML source
gsd-browser eval '<js-expression>'                 # Evaluate JavaScript in page context

Assertions

Run explicit pass/fail checks against the current page state. Prefer this over inferring success from output.

gsd-browser assert --checks '[
  {"kind": "url_contains", "text": "/dashboard"},
  {"kind": "text_visible", "text": "Welcome"},
  {"kind": "selector_visible", "selector": "#user-menu"},
  {"kind": "value_equals", "selector": "input[name=email]", "value": "user@test.com"},
  {"kind": "no_console_errors"},
  {"kind": "no_failed_requests"}
]'

Assertion kinds (17): url_contains, text_visible, text_hidden, selector_visible, selector_hidden, value_equals, checked, no_console_errors, no_failed_requests, request_url_seen, response_status, console_message_matches, network_count, console_count, element_count, no_console_errors_since, no_failed_requests_since.

Batch Execution

Execute multiple steps in one call to reduce round trips. Stops on first failure by default.

gsd-browser batch --steps '[
  {"action": "navigate", "url": "https://example.com"},
  {"action": "wait_for", "condition": "network_idle"},
  {"action": "click", "selector": "#login-btn"},
  {"action": "type", "selector": "input[name=email]", "text": "user@test.com"},
  {"action": "type", "selector": "input[name=password]", "text": "secret", "submit": true},
  {"action": "assert", "checks": [{"kind": "url_contains", "text": "/dashboard"}]}
]'

# With --summary-only to reduce output
gsd-browser batch --steps '[...]' --summary-only

Batch actions: navigate, click, type, key_press, wait_for, assert, click_ref, fill_ref.

Wait Conditions

gsd-browser wait-for --condition selector_visible --value "#content"
gsd-browser wait-for --condition selector_hidden --value ".spinner"
gsd-browser wait-for --condition url_contains --value "/dashboard"
gsd-browser wait-for --condition network_idle
gsd-browser wait-for --condition delay --value 2000
gsd-browser wait-for --condition text_visible --value "Success"
gsd-browser wait-for --condition text_hidden --value "Loading"
gsd-browser wait-for --condition request_completed --value "/api/data"
gsd-browser wait-for --condition console_message --value "ready"
gsd-browser wait-for --condition element_count --value ".item" --threshold ">=5"
gsd-browser wait-for --condition region_stable --value "#content"

# Custom timeout (default: 10000ms)
gsd-browser wait-for --condition selector_visible --value "#slow" --timeout 30000

Forms (Smart Fill)

Analyze forms and fill them by field label, name, placeholder, or aria-label — no selectors needed.

# Analyze form structure
gsd-browser analyze-form
gsd-browser analyze-form --selector "#signup-form"

# Fill by field identifiers (resolved: label -> name -> placeholder -> aria-label)
gsd-browser fill-form --values '{"Email": "a@b.com", "Password": "secret", "Country": "US"}'
gsd-browser fill-form --values '{"Email": "a@b.com"}' --submit  # Fill and click submit
gsd-browser fill-form --values '{"Email": "a@b.com"}' --selector "#login-form"

Intent-Based Interaction

Find and act on elements by semantic intent — no selectors or refs needed. Intents are predefined categories, not free-form text.

# Find top candidates for an intent (returns scored matches with selectors)
gsd-browser find-best --intent submit_form
gsd-browser find-best --intent accept_cookies
gsd-browser find-best --intent primary_cta --scope "#modal"

# Act: find best match and click/focus it in one call
gsd-browser act --intent submit_form
gsd-browser act --intent accept_cookies
gsd-browser act --intent fill_email

Intents (15):

| Intent | Action | Description | |--------|--------|-------------| | submit_form | click | Submit buttons, form actions | | close_dialog | click | Modal/dialog close buttons | | primary_cta | click | Primary call-to-action elements | | search_field | focus | Search inputs and searchboxes | | next_step | click | Next/continue/proceed buttons | | dismiss | click | Dismiss overlays, banners, toasts | | auth_action | click | Login/signup/register buttons | | back_navigation | click | Back/previous navigation links | | fill_email | focus | Email input fields | | fill_password | focus | Password input fields | | fill_username | focus | Username/login input fields | | accept_cookies | click | Cookie consent accept buttons | | main_content | click | Main c