# agent-browser: Local Dev Insights

> Companion notes for browser tasks. Command details below reflect v0.13.0-era
> usage and may differ in the installed release. Check current help and verify
> the target operation; this file is not a current browser or login test receipt.

---

## Command Compatibility Matrix

**Not all `get` subcommands accept @refs.** This is the #1 source of confusion.

| Command | @refs | CSS selectors | Notes |
|---------|-------|---------------|-------|
| `get text @e1` | YES | YES | Works with both |
| `get html` | NO | YES | Fails silently with refs |
| `get box` | NO | YES | Returns `{x, y, width, height}` JSON |
| `get styles` | NO | YES | Returns compact summary (font, color, bg, border-radius) |
| `get value` | NO | YES | For form inputs |
| `get attr` | NO | YES | Any HTML attribute |
| `get count` | N/A | YES | Returns element count |
| `get url` | N/A | N/A | No selector needed |
| `get title` | N/A | N/A | No selector needed |
| `click` | YES | YES | Works with both |
| `fill` | YES | YES | Works with both |
| `highlight` | NO | YES | Skill shows `highlight @e1` but this fails |

**Rule of thumb:** Interaction commands (click, fill, type, check, select) work with @refs.
Inspection commands (get html/box/styles, highlight) need CSS selectors.

## CSS Selectors: Strict Mode

Playwright strict mode means CSS selectors must match **exactly one element**. If multiple match, you get an error listing all matches (which is actually helpful for debugging).

**Strategies for unique selectors:**
- Use IDs: `#fork-button`
- Use unique attributes: `[data-testid="submit"]`
- Combine: `.header > a:first-child`
- Use `nth`: `.item:nth-child(3)`

## Ref Lifecycle: The Golden Rule

Refs are invalidated by **any page state change**. This includes:
- Navigation (click links, `open`, `back`, `forward`)
- Scoped snapshots (`snapshot -s`)  <-- easy to forget this one
- Form submissions
- Dynamic content (modals, dropdowns, AJAX loads)
- Even `snapshot` itself replaces all previous refs

**Pattern:** Always snapshot immediately before interacting. Never cache refs across multiple actions that change the page.

## Snapshot Mode Comparison

| Flag | What it returns | When to use |
|------|----------------|-------------|
| `-i` | Interactive elements only | **Default choice** - best token efficiency |
| `-i -C` | Interactive + cursor-interactive | When divs with onclick aren't showing up |
| `-c` | Compact (removes empty nodes) | Unreliable - can return "Empty page" on some sites |
| `-d N` | Depth-limited | When `-i` returns too much |
| `-s "#sel"` | Scoped to selector | Laser focus on one component |
| `--json` | JSON format | Programmatic parsing |

Use an interactive or scoped snapshot when a full DOM listing would obscure the elements needed for the task.

## Annotated Screenshots

`screenshot --annotate` is powerful but **can hang on complex pages** (known issue #509). If it hangs:
1. Kill with Ctrl-C or timeout
2. Fall back to regular `screenshot` + separate `snapshot -i`
3. Works best on simpler pages

The annotated screenshot also **caches refs**, so you can interact with elements immediately after without a separate snapshot.

## Network Monitoring

```bash
# See all requests (captured since page was opened)
agent-browser network requests

# Filter to just API calls (huge noise reduction)
agent-browser network requests --filter "/api/"

# Mock an API response
agent-browser network route "https://api.example.com/data" --body '{"mocked": true}'

# Block a request (e.g., analytics)
agent-browser network route "https://www.google-analytics.com/*" --abort
```

Requests are captured from session start. The `--filter` flag is essential on real sites - without it you get dozens of CSS/image/analytics requests.

## JavaScript Eval Patterns

```bash
# Quick one-liner (single quotes, no nesting)
agent-browser eval 'document.title'

# Complex JS (ALWAYS use --stdin for anything with quotes/arrows/template literals)
agent-browser eval --stdin <<'EVALEOF'
JSON.stringify(
  Array.from(document.querySelectorAll("a"))
    .map(a => ({ text: a.textContent.trim(), href: a.href }))
    .filter(a => a.text.length > 0)
    .slice(0, 10)
)
EVALEOF

# Fetch API from browser context (uses page cookies/auth)
agent-browser eval --stdin <<'EVALEOF'
(async () => {
  const res = await fetch('/api/data');
  return JSON.stringify(await res.json());
})()
EVALEOF
```

## Session Management

- **Always close when done:** `agent-browser close` prevents leaked daemon processes
- **Headed mode for debugging:** `agent-browser --headed open <url>`
- **Persistent headed config:** Add `{"headed": true}` to `~/.agent-browser/config.json`
- **Named sessions for parallel work:** `agent-browser --session name open <url>`

## Authentication and retained browser state

Choose the installed tool's supported state or profile mechanism for the target
application. A saved state file or persistent profile does not prove a later
session is authenticated: check the intended account and a meaningful authorized
page or operation after reopening. Server expiry and application policy can
invalidate retained state.

Use an explicitly owned profile for the task. Obtain any required login through
the user's authorized flow; do not assume a profile, account, application URL or
provider workaround from this guide. Browser/provider compatibility must be
checked for the actual version and flow. No tested login or saved profile is
shipped with these notes.

Treat profile directories and saved state as credential-bearing data. Keep them
in the authorized private location, restrict access, and omit cookies, tokens,
passwords and encryption keys from source, ordinary logs and shared evidence.
If encryption is configured, verify the actual tool configuration and key custody;
do not infer encryption from a filename or assume a shell already exports a key.
Retain or remove only state the task owns and whose disposition is authorized.

## Updating the Official Skill

To sync SKILL.md with upstream while preserving local insights:

```bash
# Download latest official SKILL.md
curl -sL https://raw.githubusercontent.com/vercel-labs/agent-browser/main/skills/agent-browser/SKILL.md \
  -o ~/.claude/skills/agent-browser/SKILL.md

# Re-append the local insights reference (3 lines at end of SKILL.md)
cat >> ~/.claude/skills/agent-browser/SKILL.md << 'EOF'

## Local Dev Insights
**IMPORTANT:** Read `LOCAL-INSIGHTS.md` in this skill directory for gotchas, corrections, and tested workflows discovered through hands-on use that this upstream skill doesn't cover.
EOF
```

---
skill: agent-browser
openrig-relationship: vendored-supplemented
---

# OpenRig and this skill

## Origin

- **Upstream**: Vercel agent-browser CLI (https://github.com/vercel/agent-browser)
- **Vendoring pattern**: `add-supplementary-files`
- **Last upstream check**: 2026-05-13 (initial relationship declaration)

## How OpenRig uses this skill

OpenRig ships `agent-browser` so any agent dispatched by an OpenRig topology can drive a real browser (snapshots, form fills, screenshots, scraping, web-app testing) without operators having to separately install a browser-automation skill. It's referenced from any agent profile whose role includes web work.

## OpenRig-specific modifications

This is the canonical example of the **add-supplementary-files** pattern (see `writing-skills-for-openrig` SKILL.md §"Vendored skills"). The upstream skill is kept structurally intact; OpenRig adds a companion file that captures local-use insights without polluting the upstream content.

| Surface | What changed | Why |
|---|---|---|
| `SKILL.md` body | A short "## Local Dev Insights" section was added near the end with an `**IMPORTANT:** Read LOCAL-INSIGHTS.md` pointer. | Without the pointer, agents loading the skill wouldn't know the companion file exists. The pointer is the only structural modification needed for the supplementary pattern to be discoverable. |
| `LOCAL-INSIGHTS.md` (new sibling, ~189 lines) | Field-tested gotchas, command-compatibility matrices, corrections discovered through hands-on use that the upstream skill doesn't cover. | E.g., not all `get` subcommands accept `@refs` — `get text @e1` works but `get html @e1` fails silently. The compatibility matrix saves agents from the most common confusion class. |

Nothing else in `SKILL.md` diverges from upstream content as of the last upstream check.

## Companion files

- `LOCAL-INSIGHTS.md` — load-bearing supplementary content. The SKILL.md body explicitly points readers here for hands-on gotchas the upstream skill doesn't cover.

## When to re-sync upstream

Watch for new `agent-browser` CLI releases (Vercel). When the command surface changes meaningfully:

1. Re-sync `SKILL.md` body from upstream, preserving the "Local Dev Insights" pointer section.
2. Update `LOCAL-INSIGHTS.md` compatibility matrix to reflect new behavior (some `get` subcommands may gain `@ref` support, breaking the current matrix).
3. Bump `last_upstream_check` in `SKILL.md` frontmatter.
4. Note any structural shape changes in `divergence_notes`.

---
name: agent-browser
description: Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, 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", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
allowed-tools: Bash(npx agent-browser:*), Bash(agent-browser:*)
metadata:
  openrig:
    vendored_from: "Vercel agent-browser (https://github.com/vercel/agent-browser)"
    vendoring_pattern: add-supplementary-files
    last_upstream_check: "2026-05-13 (initial vendoring declaration)"
    divergence_notes: |
      Upstream SKILL.md content tracks upstream; a small "Local Dev Insights"
      pointer section was added near the end of the body to surface the sibling
      LOCAL-INSIGHTS.md companion file. See OPENRIG.md for the full OpenRig
      relationship to this skill.
---

# Browser Automation with agent-browser

## Core Workflow

Every browser automation follows this pattern:

1. **Navigate**: `agent-browser open <url>`
2. **Snapshot**: `agent-browser snapshot -i` (get element refs like `@e1`, `@e2`)
3. **Interact**: Use refs to click, fill, select
4. **Re-snapshot**: After navigation or DOM changes, get fresh refs

```bash
agent-browser open https://example.com/form
agent-browser snapshot -i
# Output: @e1 [input type="email"], @e2 [input type="password"], @e3 [button] "Submit"

agent-browser fill @e1 "user@example.com"
agent-browser fill @e2 "password123"
agent-browser click @e3
agent-browser wait --load networkidle
agent-browser snapshot -i  # Check result
```

## Command Chaining

Commands can be chained with `&&` in a single shell invocation. The browser persists between commands via a background daemon, so chaining is safe and more efficient than separate calls.

```bash
# Chain open + wait + snapshot in one call
agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser snapshot -i

# Chain multiple interactions
agent-browser fill @e1 "user@example.com" && agent-browser fill @e2 "password123" && agent-browser click @e3

# Navigate and capture
agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser screenshot page.png
```

**When to chain:** Use `&&` when you don't need to read the output of an intermediate command before proceeding (e.g., open + wait + screenshot). Run commands separately when you need to parse the output first (e.g., snapshot to discover refs, then interact using those refs).

## Essential Commands

```bash
# Navigation
agent-browser open <url>              # Navigate (aliases: goto, navigate)
agent-browser close                   # Close browser

# Snapshot
agent-browser snapshot -i             # Interactive elements with refs (recommended)
agent-browser snapshot -i -C          # Include cursor-interactive elements (divs with onclick, cursor:pointer)
agent-browser snapshot -s "#selector" # Scope to CSS selector

# Interaction (use @refs from snapshot)
agent-browser click @e1               # Click element
agent-browser click @e1 --new-tab     # Click and open in new tab
agent-browser fill @e2 "text"         # Clear and type text
agent-browser type @e2 "text"         # Type without clearing
agent-browser select @e1 "option"     # Select dropdown option
agent-browser check @e1               # Check checkbox
agent-browser press Enter             # Press key
agent-browser scroll down 500         # Scroll page

# Get information
agent-browser get text @e1            # Get element text
agent-browser get url                 # Get current URL
agent-browser get title               # Get page title

# Wait
agent-browser wait @e1                # Wait for element
agent-browser wait --load networkidle # Wait for network idle
agent-browser wait --url "**/page"    # Wait for URL pattern
agent-browser wait 2000               # Wait milliseconds

# Capture
agent-browser screenshot              # Screenshot to temp dir
agent-browser screenshot --full       # Full page screenshot
agent-browser screenshot --annotate   # Annotated screenshot with numbered element labels
agent-browser pdf output.pdf          # Save as PDF

# Diff (compare page states)
agent-browser diff snapshot                          # Compare current vs last snapshot
agent-browser diff snapshot --baseline before.txt    # Compare current vs saved file
agent-browser diff screenshot --baseline before.png  # Visual pixel diff
agent-browser diff url <url1> <url2>                 # Compare two pages
agent-browser diff url <url1> <url2> --wait-until networkidle  # Custom wait strategy
agent-browser diff url <url1> <url2> --selector "#main"  # Scope to element
```

## Common Patterns

### Form Submission

```bash
agent-browser open https://example.com/signup
agent-browser snapshot -i
agent-browser fill @e1 "Jane Doe"
agent-browser fill @e2 "jane@example.com"
agent-browser select @e3 "California"
agent-browser check @e4
agent-browser click @e5
agent-browser wait --load networkidle
```

### Authentication with State Persistence

```bash
# Login once and save state
agent-browser open https://app.example.com/login
agent-browser snapshot -i
agent-browser fill @e1 "$USERNAME"
agent-browser fill @e2 "$PASSWORD"
agent-browser click @e3
agent-browser wait --url "**/dashboard"
agent-browser state save auth.json

# Reuse in future sessions
agent-browser state load auth.json
agent-browser open https://app.example.com/dashboard
```

### Session Persistence

```bash
# Auto-save/restore cookies and localStorage across browser restarts
agent-browser --session-name myapp open https://app.example.com/login
# ... login flow ...
agent-browser close  # State auto-saved to ~/.agent-browser/sessions/

# Next time, state is auto-loaded
agent-browser --session-name myapp open https://app.example.com/dashboard

# Encrypt state at rest
export AGENT_BROWSER_ENCRYPTION_KEY=$(openssl rand -hex 32)
agent-browser --session-name secure open https://app.example.com

# Manage saved states
agent-browser state list
agent-browser state show myapp-default.json
agent-browser state clear myapp
agent-browser state clean --older-than 7
```

### Data Extraction

```bash
agent-browser open https://example.com/products
agent-browser snapshot -i
agent-browser get text @e5           # Get specific element text
agent-browser get text body > page.txt  # Get all page text

# JSON output for parsing
agent-browser snapshot -i --json
agent-browser get text @e1 --json
```

### Parallel Sessions

```bash
agent-browser --session site1 open https://site-a.com
agent-browser --session site2 open https://site-b.com

agent-browser --session site1 snapshot -i
agent-browser --session site2 snapshot -i

agent-browser session list
```

### Connect to Existing Chrome

```bash
# Auto-discover running Chrome with remote debugging enabled
agent-browser --auto-connect open https://example.com
agent-browser --auto-connect snapshot

# Or with explicit CDP port
agent-browser --cdp 9222 snapshot
```

### Visual Browser (Debugging)

```bash
agent-browser --headed open https://example.com
agent-browser highlight @e1          # Highlight element
agent-browser record start demo.webm # Record session
agent-browser profiler start         # Start Chrome DevTools profiling
agent-browser profiler stop trace.json # Stop and save profile (path optional)
```

### Local Files (PDFs, HTML)

```bash
# Open local files with file:// URLs
agent-browser --allow-file-access open file:///path/to/document.pdf
agent-browser --allow-file-access open file:///path/to/page.html
agent-browser screenshot output.png
```

### iOS Simulator (Mobile Safari)

```bash
# List available iOS simulators
agent-browser device list

# Launch Safari on a specific device
agent-browser -p ios --device "iPhone 16 Pro" open https://example.com

# Same workflow as desktop - snapshot, interact, re-snapshot
agent-browser -p ios snapshot -i
agent-browser -p ios tap @e1          # Tap (alias for click)
agent-browser -p ios fill @e2 "text"
agent-browser -p ios swipe up         # Mobile-specific gesture

# Take screenshot
agent-browser -p ios screenshot mobile.png

# Close session (shuts down simulator)
agent-browser -p ios close
```

**Requirements:** macOS with Xcode, Appium (`npm install -g appium && appium driver install xcuitest`)

**Real devices:** Works with physical iOS devices if pre-configured. Use `--device "<UDID>"` where UDID is from `xcrun xctrace list devices`.

## Diffing (Verifying Changes)

Use `diff snapshot` after performing an action to verify it had the intended effect. This compares the current accessibility tree against the last snapshot taken in the session.

```bash
# Typical workflow: snapshot -> action -> diff
agent-browser snapshot -i          # Take baseline snapshot
agent-browser click @e2            # Perform action
agent-browser diff snapshot        # See what changed (auto-compares to last snapshot)
```

For visual regression testing or monitoring:

```bash
# Save a baseline screenshot, then compare later
agent-browser screenshot baseline.png
# ... time passes or changes are made ...
agent-browser diff screenshot --baseline baseline.png

# Compare staging vs production
agent-browser diff url https://staging.example.com https://prod.example.com --screenshot
```

`diff snapshot` output uses `+` for additions and `-` for removals, similar to git diff. `diff screenshot` produces a diff image with changed pixels highlighted in red, plus a mismatch percentage.

## Timeouts and Slow Pages

The default Playwright timeout is 60 seconds for local browsers. For slow websites or large pages, use explicit waits instead of relying on the default timeout:

```bash
# Wait for network activity to settle (best for slow pages)
agent-browser wait --load networkidle

# Wait for a specific element to appear
agent-browser wait "#content"
agent-browser wait @e1

# Wait for a specific URL pattern (useful after redirects)
agent-browser wait --url "**/dashboard"

# Wait for a JavaScript condition
agent-browser wait --fn "document.readyState === 'complete'"

# Wait a fixed duration (milliseconds) as a last resort
agent-browser wait 5000
```

When dealing with consistently slow websites, use `wait --load networkidle` after `open` to ensure the page is fully loaded before taking a snapshot. If a specific element is slow to render, wait for it directly with `wait <selector>` or `wait @ref`.

## Session Management and Cleanup

When running multiple agents or automations concurrently, always use named sessions to avoid conflicts:

```bash
# Each agent gets its own isolated session
agent-browser --session agent1 open site-a.com
agent-browser --session agent2 open site-b.com

# Check active sessions
agent-browser session list
```

Always close your browser session when done to avoid leaked processes:

```bash
agent-browser close                    # Close default session
agent-browser --session agent1 close   # Close specific session
```

If a previous session was not closed properly, the daemon may still be running. Use `agent-browser close` to clean it up before starting new work.

## Ref Lifecycle (Important)

Refs (`@e1`, `@e2`, etc.) are invalidated when the page changes. Always re-snapshot after:

- Clicking links or buttons that navigate
- Form submissions
- Dynamic content loading (dropdowns, modals)

```bash
agent-browser click @e5              # Navigates to new page
agent-browser snapshot -i            # MUST re-snapshot
agent-browser click @e1              # Use new refs
```

## Annotated Screenshots (Vision Mode)

Use `--annotate` to take a screenshot with numbered labels overlaid on interactive elements. Each label `[N]` maps to ref `@eN`. This also caches refs, so you can interact with elements immediately without a separate snapshot.

```bash
agent-browser screenshot --annotate
# Output includes the image path and a legend:
#   [1] @e1 button "Submit"
#   [2] @e2 link "Home"
#   [3] @e3 textbox "Email"
agent-browser click @e2              # Click using ref from annotated screenshot
```

Use annotated screenshots when:
- The page has unlabeled icon buttons or visual-only elements
- You need to verify visual layout or styling
- Canvas or chart elements are present (invisible to text snapshots)
- You need spatial reasoning about element positions

## Semantic Locators (Alternative to Refs)

When refs are unavailable or unreliable, use semantic locators:

```bash
agent-browser find text "Sign In" click
agent-browser find label "Email" fill "user@test.com"
agent-browser find role button click --name "Submit"
agent-browser find placeholder "Search" type "query"
agent-browser find testid "submit-btn" click
```

## JavaScript Evaluation (eval)

Use `eval` to run JavaScript in the browser context. **Shell quoting can corrupt complex expressions** -- use `--stdin` or `-b` to avoid issues.

```bash
# Simple expressions work with regular quoting
agent-browser eval 'document.title'
agent-browser eval 'document.querySelectorAll("img").length'

# Complex JS: use --stdin with heredoc (RECOMMENDED)
agent-browser eval --stdin <<'EVALEOF'
JSON.stringify(
  Array.from(document.querySelectorAll("img"))
    .filter(i => !i.alt)
    .map(i => ({ src: i.src.split("/").pop(), width: i.width }))
)
EVALEOF

# Alternative: base64 encoding (avoids all shell escaping issues)
agent-browser eval -b "$(echo -n 'Array.from(document.querySelectorAll("a")).map(a => a.href)' | base64)"
```

**Why this matters:** When the shell processes your command, inner double quotes, `!` characters (history expansion), backticks, and `$()` can all corrupt the JavaScript before it reaches agent-browser. The `--stdin` and `-b` flags bypass shell interpretation entirely.

**Rules of thumb:**
- Single-line, no nested quotes -> regular `eval 'expression'` with single quotes is fine
- Nested quotes, arrow functions, template literals, or multiline -> use `eval --stdin <<'EVALEOF'`
- Programmatic/generated scripts -> use `eval -b` with base64

## Configuration File

Create `agent-browser.json` in the project root for persistent settings:

```json
{
  "headed": true,
  "proxy": "http://localhost:8080",
  "profile": "./browser-data"
}
```

Priority (lowest to highest): `~/.agent-browser/config.json` < `./agent-browser.json` < env vars < CLI flags. Use `--config <path>` or `AGENT_BROWSER_CONFIG` env var for a custom config file (exits with error if missing/invalid). All CLI options map to camelCase keys (e.g., `--executable-path` -> `"executablePath"`). Boolean flags accept `true`/`false` values (e.g., `--headed false` overrides config). Extensions from user and project configs are merged, not replaced.

## Deep-Dive Documentation

| Reference | When to Use |
|-----------|-------------|
| [references/commands.md](references/commands.md) | Full command reference with all options |
| [references/snapshot-refs.md](references/snapshot-refs.md) | Ref lifecycle, invalidation rules, troubleshooting |
| [references/session-management.md](references/session-management.md) | Parallel sessions, state persistence, concurrent scraping |
| [references/authentication.md](references/authentication.md) | Login flows, OAuth, 2FA handling, state reuse |
| [references/video-recording.md](references/video-recording.md) | Recording workflows for debugging and documentation |
| [references/profiling.md](references/profiling.md) | Chrome DevTools profiling for performance analysis |
| [references/proxy-support.md](references/proxy-support.md) | Proxy configuration, geo-testing, rotating proxies |

## Ready-to-Use Templates

| Template | Description |
|----------|-------------|
| [templates/form-automation.sh](templates/form-automation.sh) | Form filling with validation |
| [templates/authenticated-session.sh](templates/authenticated-session.sh) | Login once, reuse state |
| [templates/capture-workflow.sh](templates/capture-workflow.sh) | Content extraction with screenshots |

```bash
./templates/form-automation.sh https://example.com/form
./templates/authenticated-session.sh https://app.example.com/login
./templates/capture-workflow.sh https://example.com ./output
```

## Local Dev Insights

**IMPORTANT:** Read `LOCAL-INSIGHTS.md` in this skill directory for gotchas, corrections, and tested workflows discovered through hands-on use that this upstream skill doesn't cover.