feat(skills): add agent-browser option for browser automation (#1090)
Add configurable browser automation allowing users to choose between Playwright MCP (default) and Vercel's agent-browser CLI. Changes: - Add browser_automation_engine.provider config option - Dynamic skill loading based on provider selection - Comprehensive agent-browser CLI reference (inline in skills.ts) - Propagate browserProvider to delegate_task and buildAgent - Update documentation with provider comparison Co-authored-by: Suyeol Jeon <devxoul@gmail.com> Co-authored-by: YeonGyu Kim <code.yeongyu@gmail.com>
This commit is contained in:
YeonGyu-Kim
@@ -0,0 +1,296 @@
|
||||
---
|
||||
name: agent-browser
|
||||
description: Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
|
||||
---
|
||||
|
||||
# Browser Automation with agent-browser
|
||||
|
||||
## Quick start
|
||||
|
||||
```bash
|
||||
agent-browser open <url> # Navigate to page
|
||||
agent-browser snapshot -i # Get interactive elements with refs
|
||||
agent-browser click @e1 # Click element by ref
|
||||
agent-browser fill @e2 "text" # Fill input by ref
|
||||
agent-browser close # Close browser
|
||||
```
|
||||
|
||||
## Core workflow
|
||||
|
||||
1. Navigate: `agent-browser open <url>`
|
||||
2. Snapshot: `agent-browser snapshot -i` (returns elements with refs like `@e1`, `@e2`)
|
||||
3. Interact using refs from the snapshot
|
||||
4. Re-snapshot after navigation or significant DOM changes
|
||||
|
||||
## Commands
|
||||
|
||||
### Navigation
|
||||
```bash
|
||||
agent-browser open <url> # Navigate to URL
|
||||
agent-browser back # Go back
|
||||
agent-browser forward # Go forward
|
||||
agent-browser reload # Reload page
|
||||
agent-browser close # Close browser
|
||||
```
|
||||
|
||||
### Snapshot (page analysis)
|
||||
```bash
|
||||
agent-browser snapshot # Full accessibility tree
|
||||
agent-browser snapshot -i # Interactive elements only (recommended)
|
||||
agent-browser snapshot -c # Compact output
|
||||
agent-browser snapshot -d 3 # Limit depth to 3
|
||||
agent-browser snapshot -s "#main" # Scope to CSS selector
|
||||
```
|
||||
|
||||
### Interactions (use @refs from snapshot)
|
||||
```bash
|
||||
agent-browser click @e1 # Click
|
||||
agent-browser dblclick @e1 # Double-click
|
||||
agent-browser focus @e1 # Focus element
|
||||
agent-browser fill @e2 "text" # Clear and type
|
||||
agent-browser type @e2 "text" # Type without clearing
|
||||
agent-browser press Enter # Press key
|
||||
agent-browser press Control+a # Key combination
|
||||
agent-browser keydown Shift # Hold key down
|
||||
agent-browser keyup Shift # Release key
|
||||
agent-browser hover @e1 # Hover
|
||||
agent-browser check @e1 # Check checkbox
|
||||
agent-browser uncheck @e1 # Uncheck checkbox
|
||||
agent-browser select @e1 "value" # Select dropdown
|
||||
agent-browser scroll down 500 # Scroll page
|
||||
agent-browser scrollintoview @e1 # Scroll element into view
|
||||
agent-browser drag @e1 @e2 # Drag and drop
|
||||
agent-browser upload @e1 file.pdf # Upload files
|
||||
```
|
||||
|
||||
### Get information
|
||||
```bash
|
||||
agent-browser get text @e1 # Get element text
|
||||
agent-browser get html @e1 # Get innerHTML
|
||||
agent-browser get value @e1 # Get input value
|
||||
agent-browser get attr @e1 href # Get attribute
|
||||
agent-browser get title # Get page title
|
||||
agent-browser get url # Get current URL
|
||||
agent-browser get count ".item" # Count matching elements
|
||||
agent-browser get box @e1 # Get bounding box
|
||||
```
|
||||
|
||||
### Check state
|
||||
```bash
|
||||
agent-browser is visible @e1 # Check if visible
|
||||
agent-browser is enabled @e1 # Check if enabled
|
||||
agent-browser is checked @e1 # Check if checked
|
||||
```
|
||||
|
||||
### Screenshots & PDF
|
||||
```bash
|
||||
agent-browser screenshot # Screenshot to stdout
|
||||
agent-browser screenshot path.png # Save to file
|
||||
agent-browser screenshot --full # Full page
|
||||
agent-browser pdf output.pdf # Save as PDF
|
||||
```
|
||||
|
||||
### Video recording
|
||||
```bash
|
||||
agent-browser record start ./demo.webm # Start recording (uses current URL + state)
|
||||
agent-browser click @e1 # Perform actions
|
||||
agent-browser record stop # Stop and save video
|
||||
agent-browser record restart ./take2.webm # Stop current + start new recording
|
||||
```
|
||||
Recording creates a fresh context but preserves cookies/storage from your session.
|
||||
|
||||
### Wait
|
||||
```bash
|
||||
agent-browser wait @e1 # Wait for element
|
||||
agent-browser wait 2000 # Wait milliseconds
|
||||
agent-browser wait --text "Success" # Wait for text
|
||||
agent-browser wait --url "**/dashboard" # Wait for URL pattern
|
||||
agent-browser wait --load networkidle # Wait for network idle
|
||||
agent-browser wait --fn "window.ready" # Wait for JS condition
|
||||
```
|
||||
|
||||
### Mouse control
|
||||
```bash
|
||||
agent-browser mouse move 100 200 # Move mouse
|
||||
agent-browser mouse down left # Press button
|
||||
agent-browser mouse up left # Release button
|
||||
agent-browser mouse wheel 100 # Scroll wheel
|
||||
```
|
||||
|
||||
### Semantic locators (alternative to refs)
|
||||
```bash
|
||||
agent-browser find role button click --name "Submit"
|
||||
agent-browser find text "Sign In" click
|
||||
agent-browser find label "Email" fill "user@test.com"
|
||||
agent-browser find first ".item" click
|
||||
agent-browser find nth 2 "a" text
|
||||
```
|
||||
|
||||
### Browser settings
|
||||
```bash
|
||||
agent-browser set viewport 1920 1080 # Set viewport size
|
||||
agent-browser set device "iPhone 14" # Emulate device
|
||||
agent-browser set geo 37.7749 -122.4194 # Set geolocation
|
||||
agent-browser set offline on # Toggle offline mode
|
||||
agent-browser set headers '{"X-Key":"v"}' # Extra HTTP headers
|
||||
agent-browser set credentials user pass # HTTP basic auth
|
||||
agent-browser set media dark # Emulate color scheme
|
||||
```
|
||||
|
||||
### Cookies & Storage
|
||||
```bash
|
||||
agent-browser cookies # Get all cookies
|
||||
agent-browser cookies set name value # Set cookie
|
||||
agent-browser cookies clear # Clear cookies
|
||||
agent-browser storage local # Get all localStorage
|
||||
agent-browser storage local key # Get specific key
|
||||
agent-browser storage local set k v # Set value
|
||||
agent-browser storage local clear # Clear all
|
||||
agent-browser storage session # Get all sessionStorage
|
||||
agent-browser storage session key # Get specific key
|
||||
agent-browser storage session set k v # Set value
|
||||
agent-browser storage session clear # Clear all
|
||||
```
|
||||
|
||||
### Network
|
||||
```bash
|
||||
agent-browser network route <url> # Intercept requests
|
||||
agent-browser network route <url> --abort # Block requests
|
||||
agent-browser network route <url> --body '{}' # Mock response
|
||||
agent-browser network unroute [url] # Remove routes
|
||||
agent-browser network requests # View tracked requests
|
||||
agent-browser network requests --filter api # Filter requests
|
||||
```
|
||||
|
||||
### Tabs & Windows
|
||||
```bash
|
||||
agent-browser tab # List tabs
|
||||
agent-browser tab new [url] # New tab
|
||||
agent-browser tab 2 # Switch to tab
|
||||
agent-browser tab close # Close tab
|
||||
agent-browser window new # New window
|
||||
```
|
||||
|
||||
### Frames
|
||||
```bash
|
||||
agent-browser frame "#iframe" # Switch to iframe
|
||||
agent-browser frame main # Back to main frame
|
||||
```
|
||||
|
||||
### Dialogs
|
||||
```bash
|
||||
agent-browser dialog accept [text] # Accept dialog
|
||||
agent-browser dialog dismiss # Dismiss dialog
|
||||
```
|
||||
|
||||
### JavaScript
|
||||
```bash
|
||||
agent-browser eval "document.title" # Run JavaScript
|
||||
```
|
||||
|
||||
## Global Options
|
||||
|
||||
| Option | Description |
|
||||
|--------|-------------|
|
||||
| `--session <name>` | Isolated browser session (`AGENT_BROWSER_SESSION` env) |
|
||||
| `--profile <path>` | Persistent browser profile (`AGENT_BROWSER_PROFILE` env) |
|
||||
| `--headers <json>` | HTTP headers scoped to URL's origin |
|
||||
| `--executable-path <path>` | Custom browser binary (`AGENT_BROWSER_EXECUTABLE_PATH` env) |
|
||||
| `--args <args>` | Browser launch args (`AGENT_BROWSER_ARGS` env) |
|
||||
| `--user-agent <ua>` | Custom User-Agent (`AGENT_BROWSER_USER_AGENT` env) |
|
||||
| `--proxy <url>` | Proxy server (`AGENT_BROWSER_PROXY` env) |
|
||||
| `--proxy-bypass <hosts>` | Hosts to bypass proxy (`AGENT_BROWSER_PROXY_BYPASS` env) |
|
||||
| `-p, --provider <name>` | Cloud browser provider (`AGENT_BROWSER_PROVIDER` env) |
|
||||
| `--json` | Machine-readable JSON output |
|
||||
| `--headed` | Show browser window (not headless) |
|
||||
| `--cdp <port\|wss://url>` | Connect via Chrome DevTools Protocol |
|
||||
| `--debug` | Debug output |
|
||||
|
||||
## Example: Form submission
|
||||
|
||||
```bash
|
||||
agent-browser open https://example.com/form
|
||||
agent-browser snapshot -i
|
||||
# Output shows: textbox "Email" [ref=e1], textbox "Password" [ref=e2], button "Submit" [ref=e3]
|
||||
|
||||
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
|
||||
```
|
||||
|
||||
## Example: Authentication with saved state
|
||||
|
||||
```bash
|
||||
# Login once
|
||||
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
|
||||
|
||||
# Later sessions: load saved state
|
||||
agent-browser state load auth.json
|
||||
agent-browser open https://app.example.com/dashboard
|
||||
```
|
||||
|
||||
### Header-based Auth (Skip login flows)
|
||||
```bash
|
||||
# Headers scoped to api.example.com only
|
||||
agent-browser open api.example.com --headers '{"Authorization": "Bearer <token>"}'
|
||||
# Navigate to another domain - headers NOT sent (safe)
|
||||
agent-browser open other-site.com
|
||||
# Global headers (all domains)
|
||||
agent-browser set headers '{"X-Custom-Header": "value"}'
|
||||
```
|
||||
|
||||
## Sessions & Persistent Profiles
|
||||
|
||||
### Sessions (parallel browsers)
|
||||
```bash
|
||||
agent-browser --session test1 open site-a.com
|
||||
agent-browser --session test2 open site-b.com
|
||||
agent-browser session list
|
||||
```
|
||||
|
||||
### Persistent Profiles
|
||||
Persists cookies, localStorage, IndexedDB, service workers, cache, login sessions across browser restarts.
|
||||
```bash
|
||||
agent-browser --profile ~/.myapp-profile open myapp.com
|
||||
# Or via env var
|
||||
AGENT_BROWSER_PROFILE=~/.myapp-profile agent-browser open myapp.com
|
||||
```
|
||||
- Use different profile paths for different projects
|
||||
- Login once → restart browser → still logged in
|
||||
- Stores: cookies, localStorage, IndexedDB, service workers, browser cache
|
||||
|
||||
## JSON output (for parsing)
|
||||
|
||||
Add `--json` for machine-readable output:
|
||||
```bash
|
||||
agent-browser snapshot -i --json
|
||||
agent-browser get text @e1 --json
|
||||
```
|
||||
|
||||
## Debugging
|
||||
|
||||
```bash
|
||||
agent-browser open example.com --headed # Show browser window
|
||||
agent-browser console # View console messages
|
||||
agent-browser errors # View page errors
|
||||
agent-browser record start ./debug.webm # Record from current page
|
||||
agent-browser record stop # Save recording
|
||||
agent-browser connect 9222 # Local CDP port
|
||||
agent-browser --cdp "wss://browser-service.com/cdp?token=..." snapshot # Remote via WebSocket
|
||||
agent-browser console --clear # Clear console
|
||||
agent-browser errors --clear # Clear errors
|
||||
agent-browser highlight @e1 # Highlight element
|
||||
agent-browser trace start # Start recording trace
|
||||
agent-browser trace stop trace.zip # Stop and save trace
|
||||
```
|
||||
|
||||
---
|
||||
Install: `bun add -g agent-browser && agent-browser install`. Run `agent-browser --help` for all commands. Repo: https://github.com/vercel-labs/agent-browser
|
||||
@@ -1,2 +1,2 @@
|
||||
export * from "./types"
|
||||
export { createBuiltinSkills } from "./skills"
|
||||
export { createBuiltinSkills, type CreateBuiltinSkillsOptions } from "./skills"
|
||||
|
||||
@@ -0,0 +1,89 @@
|
||||
import { describe, test, expect } from "bun:test"
|
||||
import { createBuiltinSkills } from "./skills"
|
||||
|
||||
describe("createBuiltinSkills", () => {
|
||||
test("returns playwright skill by default", () => {
|
||||
// #given - no options (default)
|
||||
|
||||
// #when
|
||||
const skills = createBuiltinSkills()
|
||||
|
||||
// #then
|
||||
const browserSkill = skills.find((s) => s.name === "playwright")
|
||||
expect(browserSkill).toBeDefined()
|
||||
expect(browserSkill!.description).toContain("browser")
|
||||
expect(browserSkill!.mcpConfig).toHaveProperty("playwright")
|
||||
})
|
||||
|
||||
test("returns playwright skill when browserProvider is 'playwright'", () => {
|
||||
// #given
|
||||
const options = { browserProvider: "playwright" as const }
|
||||
|
||||
// #when
|
||||
const skills = createBuiltinSkills(options)
|
||||
|
||||
// #then
|
||||
const playwrightSkill = skills.find((s) => s.name === "playwright")
|
||||
const agentBrowserSkill = skills.find((s) => s.name === "agent-browser")
|
||||
expect(playwrightSkill).toBeDefined()
|
||||
expect(agentBrowserSkill).toBeUndefined()
|
||||
})
|
||||
|
||||
test("returns agent-browser skill when browserProvider is 'agent-browser'", () => {
|
||||
// #given
|
||||
const options = { browserProvider: "agent-browser" as const }
|
||||
|
||||
// #when
|
||||
const skills = createBuiltinSkills(options)
|
||||
|
||||
// #then
|
||||
const agentBrowserSkill = skills.find((s) => s.name === "agent-browser")
|
||||
const playwrightSkill = skills.find((s) => s.name === "playwright")
|
||||
expect(agentBrowserSkill).toBeDefined()
|
||||
expect(agentBrowserSkill!.description).toContain("browser")
|
||||
expect(agentBrowserSkill!.allowedTools).toContain("Bash(agent-browser:*)")
|
||||
expect(agentBrowserSkill!.template).toContain("agent-browser")
|
||||
expect(playwrightSkill).toBeUndefined()
|
||||
})
|
||||
|
||||
test("agent-browser skill template is inlined (not loaded from file)", () => {
|
||||
// #given
|
||||
const options = { browserProvider: "agent-browser" as const }
|
||||
|
||||
// #when
|
||||
const skills = createBuiltinSkills(options)
|
||||
const agentBrowserSkill = skills.find((s) => s.name === "agent-browser")
|
||||
|
||||
// #then - template should contain substantial content (inlined, not fallback)
|
||||
expect(agentBrowserSkill!.template).toContain("## Quick start")
|
||||
expect(agentBrowserSkill!.template).toContain("## Commands")
|
||||
expect(agentBrowserSkill!.template).toContain("agent-browser open")
|
||||
expect(agentBrowserSkill!.template).toContain("agent-browser snapshot")
|
||||
})
|
||||
|
||||
test("always includes frontend-ui-ux and git-master skills", () => {
|
||||
// #given - both provider options
|
||||
|
||||
// #when
|
||||
const defaultSkills = createBuiltinSkills()
|
||||
const agentBrowserSkills = createBuiltinSkills({ browserProvider: "agent-browser" })
|
||||
|
||||
// #then
|
||||
for (const skills of [defaultSkills, agentBrowserSkills]) {
|
||||
expect(skills.find((s) => s.name === "frontend-ui-ux")).toBeDefined()
|
||||
expect(skills.find((s) => s.name === "git-master")).toBeDefined()
|
||||
}
|
||||
})
|
||||
|
||||
test("returns exactly 3 skills regardless of provider", () => {
|
||||
// #given
|
||||
|
||||
// #when
|
||||
const defaultSkills = createBuiltinSkills()
|
||||
const agentBrowserSkills = createBuiltinSkills({ browserProvider: "agent-browser" })
|
||||
|
||||
// #then
|
||||
expect(defaultSkills).toHaveLength(3)
|
||||
expect(agentBrowserSkills).toHaveLength(3)
|
||||
})
|
||||
})
|
||||
@@ -1,4 +1,5 @@
|
||||
import type { BuiltinSkill } from "./types"
|
||||
import type { BrowserAutomationProvider } from "../../config/schema"
|
||||
|
||||
const playwrightSkill: BuiltinSkill = {
|
||||
name: "playwright",
|
||||
@@ -14,6 +15,303 @@ This skill provides browser automation capabilities via the Playwright MCP serve
|
||||
},
|
||||
}
|
||||
|
||||
const agentBrowserSkill: BuiltinSkill = {
|
||||
name: "agent-browser",
|
||||
description: "MUST USE for any browser-related tasks. Browser automation via agent-browser CLI - verification, browsing, information gathering, web scraping, testing, screenshots, and all browser interactions.",
|
||||
template: `# Browser Automation with agent-browser
|
||||
|
||||
## Quick start
|
||||
|
||||
\`\`\`bash
|
||||
agent-browser open <url> # Navigate to page
|
||||
agent-browser snapshot -i # Get interactive elements with refs
|
||||
agent-browser click @e1 # Click element by ref
|
||||
agent-browser fill @e2 "text" # Fill input by ref
|
||||
agent-browser close # Close browser
|
||||
\`\`\`
|
||||
|
||||
## Core workflow
|
||||
|
||||
1. Navigate: \`agent-browser open <url>\`
|
||||
2. Snapshot: \`agent-browser snapshot -i\` (returns elements with refs like \`@e1\`, \`@e2\`)
|
||||
3. Interact using refs from the snapshot
|
||||
4. Re-snapshot after navigation or significant DOM changes
|
||||
|
||||
## Commands
|
||||
|
||||
### Navigation
|
||||
\`\`\`bash
|
||||
agent-browser open <url> # Navigate to URL
|
||||
agent-browser back # Go back
|
||||
agent-browser forward # Go forward
|
||||
agent-browser reload # Reload page
|
||||
agent-browser close # Close browser
|
||||
\`\`\`
|
||||
|
||||
### Snapshot (page analysis)
|
||||
\`\`\`bash
|
||||
agent-browser snapshot # Full accessibility tree
|
||||
agent-browser snapshot -i # Interactive elements only (recommended)
|
||||
agent-browser snapshot -c # Compact output
|
||||
agent-browser snapshot -d 3 # Limit depth to 3
|
||||
agent-browser snapshot -s "#main" # Scope to CSS selector
|
||||
\`\`\`
|
||||
|
||||
### Interactions (use @refs from snapshot)
|
||||
\`\`\`bash
|
||||
agent-browser click @e1 # Click
|
||||
agent-browser dblclick @e1 # Double-click
|
||||
agent-browser focus @e1 # Focus element
|
||||
agent-browser fill @e2 "text" # Clear and type
|
||||
agent-browser type @e2 "text" # Type without clearing
|
||||
agent-browser press Enter # Press key
|
||||
agent-browser press Control+a # Key combination
|
||||
agent-browser keydown Shift # Hold key down
|
||||
agent-browser keyup Shift # Release key
|
||||
agent-browser hover @e1 # Hover
|
||||
agent-browser check @e1 # Check checkbox
|
||||
agent-browser uncheck @e1 # Uncheck checkbox
|
||||
agent-browser select @e1 "value" # Select dropdown
|
||||
agent-browser scroll down 500 # Scroll page
|
||||
agent-browser scrollintoview @e1 # Scroll element into view
|
||||
agent-browser drag @e1 @e2 # Drag and drop
|
||||
agent-browser upload @e1 file.pdf # Upload files
|
||||
\`\`\`
|
||||
|
||||
### Get information
|
||||
\`\`\`bash
|
||||
agent-browser get text @e1 # Get element text
|
||||
agent-browser get html @e1 # Get innerHTML
|
||||
agent-browser get value @e1 # Get input value
|
||||
agent-browser get attr @e1 href # Get attribute
|
||||
agent-browser get title # Get page title
|
||||
agent-browser get url # Get current URL
|
||||
agent-browser get count ".item" # Count matching elements
|
||||
agent-browser get box @e1 # Get bounding box
|
||||
\`\`\`
|
||||
|
||||
### Check state
|
||||
\`\`\`bash
|
||||
agent-browser is visible @e1 # Check if visible
|
||||
agent-browser is enabled @e1 # Check if enabled
|
||||
agent-browser is checked @e1 # Check if checked
|
||||
\`\`\`
|
||||
|
||||
### Screenshots & PDF
|
||||
\`\`\`bash
|
||||
agent-browser screenshot # Screenshot to stdout
|
||||
agent-browser screenshot path.png # Save to file
|
||||
agent-browser screenshot --full # Full page
|
||||
agent-browser pdf output.pdf # Save as PDF
|
||||
\`\`\`
|
||||
|
||||
### Video recording
|
||||
\`\`\`bash
|
||||
agent-browser record start ./demo.webm # Start recording (uses current URL + state)
|
||||
agent-browser click @e1 # Perform actions
|
||||
agent-browser record stop # Stop and save video
|
||||
agent-browser record restart ./take2.webm # Stop current + start new recording
|
||||
\`\`\`
|
||||
Recording creates a fresh context but preserves cookies/storage from your session.
|
||||
|
||||
### Wait
|
||||
\`\`\`bash
|
||||
agent-browser wait @e1 # Wait for element
|
||||
agent-browser wait 2000 # Wait milliseconds
|
||||
agent-browser wait --text "Success" # Wait for text
|
||||
agent-browser wait --url "**/dashboard" # Wait for URL pattern
|
||||
agent-browser wait --load networkidle # Wait for network idle
|
||||
agent-browser wait --fn "window.ready" # Wait for JS condition
|
||||
\`\`\`
|
||||
|
||||
### Mouse control
|
||||
\`\`\`bash
|
||||
agent-browser mouse move 100 200 # Move mouse
|
||||
agent-browser mouse down left # Press button
|
||||
agent-browser mouse up left # Release button
|
||||
agent-browser mouse wheel 100 # Scroll wheel
|
||||
\`\`\`
|
||||
|
||||
### Semantic locators (alternative to refs)
|
||||
\`\`\`bash
|
||||
agent-browser find role button click --name "Submit"
|
||||
agent-browser find text "Sign In" click
|
||||
agent-browser find label "Email" fill "user@test.com"
|
||||
agent-browser find first ".item" click
|
||||
agent-browser find nth 2 "a" text
|
||||
\`\`\`
|
||||
|
||||
### Browser settings
|
||||
\`\`\`bash
|
||||
agent-browser set viewport 1920 1080 # Set viewport size
|
||||
agent-browser set device "iPhone 14" # Emulate device
|
||||
agent-browser set geo 37.7749 -122.4194 # Set geolocation
|
||||
agent-browser set offline on # Toggle offline mode
|
||||
agent-browser set headers '{"X-Key":"v"}' # Extra HTTP headers
|
||||
agent-browser set credentials user pass # HTTP basic auth
|
||||
agent-browser set media dark # Emulate color scheme
|
||||
\`\`\`
|
||||
|
||||
### Cookies & Storage
|
||||
\`\`\`bash
|
||||
agent-browser cookies # Get all cookies
|
||||
agent-browser cookies set name value # Set cookie
|
||||
agent-browser cookies clear # Clear cookies
|
||||
agent-browser storage local # Get all localStorage
|
||||
agent-browser storage local key # Get specific key
|
||||
agent-browser storage local set k v # Set value
|
||||
agent-browser storage local clear # Clear all
|
||||
agent-browser storage session # Get all sessionStorage
|
||||
agent-browser storage session key # Get specific key
|
||||
agent-browser storage session set k v # Set value
|
||||
agent-browser storage session clear # Clear all
|
||||
\`\`\`
|
||||
|
||||
### Network
|
||||
\`\`\`bash
|
||||
agent-browser network route <url> # Intercept requests
|
||||
agent-browser network route <url> --abort # Block requests
|
||||
agent-browser network route <url> --body '{}' # Mock response
|
||||
agent-browser network unroute [url] # Remove routes
|
||||
agent-browser network requests # View tracked requests
|
||||
agent-browser network requests --filter api # Filter requests
|
||||
\`\`\`
|
||||
|
||||
### Tabs & Windows
|
||||
\`\`\`bash
|
||||
agent-browser tab # List tabs
|
||||
agent-browser tab new [url] # New tab
|
||||
agent-browser tab 2 # Switch to tab
|
||||
agent-browser tab close # Close tab
|
||||
agent-browser window new # New window
|
||||
\`\`\`
|
||||
|
||||
### Frames
|
||||
\`\`\`bash
|
||||
agent-browser frame "#iframe" # Switch to iframe
|
||||
agent-browser frame main # Back to main frame
|
||||
\`\`\`
|
||||
|
||||
### Dialogs
|
||||
\`\`\`bash
|
||||
agent-browser dialog accept [text] # Accept dialog
|
||||
agent-browser dialog dismiss # Dismiss dialog
|
||||
\`\`\`
|
||||
|
||||
### JavaScript
|
||||
\`\`\`bash
|
||||
agent-browser eval "document.title" # Run JavaScript
|
||||
\`\`\`
|
||||
|
||||
## Global Options
|
||||
|
||||
| Option | Description |
|
||||
|--------|-------------|
|
||||
| \`--session <name>\` | Isolated browser session (\`AGENT_BROWSER_SESSION\` env) |
|
||||
| \`--profile <path>\` | Persistent browser profile (\`AGENT_BROWSER_PROFILE\` env) |
|
||||
| \`--headers <json>\` | HTTP headers scoped to URL's origin |
|
||||
| \`--executable-path <path>\` | Custom browser binary (\`AGENT_BROWSER_EXECUTABLE_PATH\` env) |
|
||||
| \`--args <args>\` | Browser launch args (\`AGENT_BROWSER_ARGS\` env) |
|
||||
| \`--user-agent <ua>\` | Custom User-Agent (\`AGENT_BROWSER_USER_AGENT\` env) |
|
||||
| \`--proxy <url>\` | Proxy server (\`AGENT_BROWSER_PROXY\` env) |
|
||||
| \`--proxy-bypass <hosts>\` | Hosts to bypass proxy (\`AGENT_BROWSER_PROXY_BYPASS\` env) |
|
||||
| \`-p, --provider <name>\` | Cloud browser provider (\`AGENT_BROWSER_PROVIDER\` env) |
|
||||
| \`--json\` | Machine-readable JSON output |
|
||||
| \`--headed\` | Show browser window (not headless) |
|
||||
| \`--cdp <port\\|wss://url>\` | Connect via Chrome DevTools Protocol |
|
||||
| \`--debug\` | Debug output |
|
||||
|
||||
## Example: Form submission
|
||||
|
||||
\`\`\`bash
|
||||
agent-browser open https://example.com/form
|
||||
agent-browser snapshot -i
|
||||
# Output shows: textbox "Email" [ref=e1], textbox "Password" [ref=e2], button "Submit" [ref=e3]
|
||||
|
||||
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
|
||||
\`\`\`
|
||||
|
||||
## Example: Authentication with saved state
|
||||
|
||||
\`\`\`bash
|
||||
# Login once
|
||||
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
|
||||
|
||||
# Later sessions: load saved state
|
||||
agent-browser state load auth.json
|
||||
agent-browser open https://app.example.com/dashboard
|
||||
\`\`\`
|
||||
|
||||
### Header-based Auth (Skip login flows)
|
||||
\`\`\`bash
|
||||
# Headers scoped to api.example.com only
|
||||
agent-browser open api.example.com --headers '{"Authorization": "Bearer <token>"}'
|
||||
# Navigate to another domain - headers NOT sent (safe)
|
||||
agent-browser open other-site.com
|
||||
# Global headers (all domains)
|
||||
agent-browser set headers '{"X-Custom-Header": "value"}'
|
||||
\`\`\`
|
||||
|
||||
## Sessions & Persistent Profiles
|
||||
|
||||
### Sessions (parallel browsers)
|
||||
\`\`\`bash
|
||||
agent-browser --session test1 open site-a.com
|
||||
agent-browser --session test2 open site-b.com
|
||||
agent-browser session list
|
||||
\`\`\`
|
||||
|
||||
### Persistent Profiles
|
||||
Persists cookies, localStorage, IndexedDB, service workers, cache, login sessions across browser restarts.
|
||||
\`\`\`bash
|
||||
agent-browser --profile ~/.myapp-profile open myapp.com
|
||||
# Or via env var
|
||||
AGENT_BROWSER_PROFILE=~/.myapp-profile agent-browser open myapp.com
|
||||
\`\`\`
|
||||
- Use different profile paths for different projects
|
||||
- Login once → restart browser → still logged in
|
||||
- Stores: cookies, localStorage, IndexedDB, service workers, browser cache
|
||||
|
||||
## JSON output (for parsing)
|
||||
|
||||
Add \`--json\` for machine-readable output:
|
||||
\`\`\`bash
|
||||
agent-browser snapshot -i --json
|
||||
agent-browser get text @e1 --json
|
||||
\`\`\`
|
||||
|
||||
## Debugging
|
||||
|
||||
\`\`\`bash
|
||||
agent-browser open example.com --headed # Show browser window
|
||||
agent-browser console # View console messages
|
||||
agent-browser errors # View page errors
|
||||
agent-browser record start ./debug.webm # Record from current page
|
||||
agent-browser record stop # Save recording
|
||||
agent-browser connect 9222 # Local CDP port
|
||||
agent-browser --cdp "wss://browser-service.com/cdp?token=..." snapshot # Remote via WebSocket
|
||||
agent-browser console --clear # Clear console
|
||||
agent-browser errors --clear # Clear errors
|
||||
agent-browser highlight @e1 # Highlight element
|
||||
agent-browser trace start # Start recording trace
|
||||
agent-browser trace stop trace.zip # Stop and save trace
|
||||
\`\`\`
|
||||
|
||||
---
|
||||
Install: \`bun add -g agent-browser && agent-browser install\`. Run \`agent-browser --help\` for all commands. Repo: https://github.com/vercel-labs/agent-browser`,
|
||||
allowedTools: ["Bash(agent-browser:*)"],
|
||||
}
|
||||
|
||||
const frontendUiUxSkill: BuiltinSkill = {
|
||||
name: "frontend-ui-ux",
|
||||
description: "Designer-turned-developer who crafts stunning UI/UX even without design mockups",
|
||||
@@ -1198,6 +1496,14 @@ POTENTIAL ACTIONS:
|
||||
- Bisect without proper good/bad boundaries -> Wasted time`,
|
||||
}
|
||||
|
||||
export function createBuiltinSkills(): BuiltinSkill[] {
|
||||
return [playwrightSkill, frontendUiUxSkill, gitMasterSkill]
|
||||
export interface CreateBuiltinSkillsOptions {
|
||||
browserProvider?: BrowserAutomationProvider
|
||||
}
|
||||
|
||||
export function createBuiltinSkills(options: CreateBuiltinSkillsOptions = {}): BuiltinSkill[] {
|
||||
const { browserProvider = "playwright" } = options
|
||||
|
||||
const browserSkill = browserProvider === "agent-browser" ? agentBrowserSkill : playwrightSkill
|
||||
|
||||
return [browserSkill, frontendUiUxSkill, gitMasterSkill]
|
||||
}
|
||||
|
||||
@@ -265,3 +265,66 @@ describe("resolveMultipleSkillsAsync", () => {
|
||||
expect(result.notFound).toEqual([])
|
||||
})
|
||||
})
|
||||
|
||||
describe("resolveSkillContent with browserProvider", () => {
|
||||
it("should resolve agent-browser skill when browserProvider is 'agent-browser'", () => {
|
||||
// #given: browserProvider set to agent-browser
|
||||
const options = { browserProvider: "agent-browser" as const }
|
||||
|
||||
// #when: resolving content for 'agent-browser'
|
||||
const result = resolveSkillContent("agent-browser", options)
|
||||
|
||||
// #then: returns agent-browser template
|
||||
expect(result).not.toBeNull()
|
||||
expect(result).toContain("agent-browser")
|
||||
})
|
||||
|
||||
it("should return null for agent-browser when browserProvider is default", () => {
|
||||
// #given: no browserProvider (defaults to playwright)
|
||||
|
||||
// #when: resolving content for 'agent-browser'
|
||||
const result = resolveSkillContent("agent-browser")
|
||||
|
||||
// #then: returns null because agent-browser is not in default builtin skills
|
||||
expect(result).toBeNull()
|
||||
})
|
||||
|
||||
it("should return null for playwright when browserProvider is agent-browser", () => {
|
||||
// #given: browserProvider set to agent-browser
|
||||
const options = { browserProvider: "agent-browser" as const }
|
||||
|
||||
// #when: resolving content for 'playwright'
|
||||
const result = resolveSkillContent("playwright", options)
|
||||
|
||||
// #then: returns null because playwright is replaced by agent-browser
|
||||
expect(result).toBeNull()
|
||||
})
|
||||
})
|
||||
|
||||
describe("resolveMultipleSkills with browserProvider", () => {
|
||||
it("should resolve agent-browser when browserProvider is set", () => {
|
||||
// #given: agent-browser and git-master requested with browserProvider
|
||||
const skillNames = ["agent-browser", "git-master"]
|
||||
const options = { browserProvider: "agent-browser" as const }
|
||||
|
||||
// #when: resolving multiple skills
|
||||
const result = resolveMultipleSkills(skillNames, options)
|
||||
|
||||
// #then: both resolved
|
||||
expect(result.resolved.has("agent-browser")).toBe(true)
|
||||
expect(result.resolved.has("git-master")).toBe(true)
|
||||
expect(result.notFound).toHaveLength(0)
|
||||
})
|
||||
|
||||
it("should not resolve agent-browser without browserProvider option", () => {
|
||||
// #given: agent-browser requested without browserProvider
|
||||
const skillNames = ["agent-browser"]
|
||||
|
||||
// #when: resolving multiple skills
|
||||
const result = resolveMultipleSkills(skillNames)
|
||||
|
||||
// #then: agent-browser not found
|
||||
expect(result.resolved.has("agent-browser")).toBe(false)
|
||||
expect(result.notFound).toContain("agent-browser")
|
||||
})
|
||||
})
|
||||
|
||||
@@ -3,24 +3,27 @@ import { discoverSkills } from "./loader"
|
||||
import type { LoadedSkill } from "./types"
|
||||
import { parseFrontmatter } from "../../shared/frontmatter"
|
||||
import { readFileSync } from "node:fs"
|
||||
import type { GitMasterConfig } from "../../config/schema"
|
||||
import type { GitMasterConfig, BrowserAutomationProvider } from "../../config/schema"
|
||||
|
||||
export interface SkillResolutionOptions {
|
||||
gitMasterConfig?: GitMasterConfig
|
||||
browserProvider?: BrowserAutomationProvider
|
||||
}
|
||||
|
||||
let cachedSkills: LoadedSkill[] | null = null
|
||||
const cachedSkillsByProvider = new Map<string, LoadedSkill[]>()
|
||||
|
||||
function clearSkillCache(): void {
|
||||
cachedSkills = null
|
||||
cachedSkillsByProvider.clear()
|
||||
}
|
||||
|
||||
async function getAllSkills(): Promise<LoadedSkill[]> {
|
||||
if (cachedSkills) return cachedSkills
|
||||
async function getAllSkills(options?: SkillResolutionOptions): Promise<LoadedSkill[]> {
|
||||
const cacheKey = options?.browserProvider ?? "playwright"
|
||||
const cached = cachedSkillsByProvider.get(cacheKey)
|
||||
if (cached) return cached
|
||||
|
||||
const [discoveredSkills, builtinSkillDefs] = await Promise.all([
|
||||
discoverSkills({ includeClaudeCodePaths: true }),
|
||||
Promise.resolve(createBuiltinSkills()),
|
||||
Promise.resolve(createBuiltinSkills({ browserProvider: options?.browserProvider })),
|
||||
])
|
||||
|
||||
const builtinSkillsAsLoaded: LoadedSkill[] = builtinSkillDefs.map((skill) => ({
|
||||
@@ -44,8 +47,9 @@ async function getAllSkills(): Promise<LoadedSkill[]> {
|
||||
const discoveredNames = new Set(discoveredSkills.map((s) => s.name))
|
||||
const uniqueBuiltins = builtinSkillsAsLoaded.filter((s) => !discoveredNames.has(s.name))
|
||||
|
||||
cachedSkills = [...discoveredSkills, ...uniqueBuiltins]
|
||||
return cachedSkills
|
||||
const allSkills = [...discoveredSkills, ...uniqueBuiltins]
|
||||
cachedSkillsByProvider.set(cacheKey, allSkills)
|
||||
return allSkills
|
||||
}
|
||||
|
||||
async function extractSkillTemplate(skill: LoadedSkill): Promise<string> {
|
||||
@@ -118,7 +122,7 @@ export function injectGitMasterConfig(template: string, config?: GitMasterConfig
|
||||
}
|
||||
|
||||
export function resolveSkillContent(skillName: string, options?: SkillResolutionOptions): string | null {
|
||||
const skills = createBuiltinSkills()
|
||||
const skills = createBuiltinSkills({ browserProvider: options?.browserProvider })
|
||||
const skill = skills.find((s) => s.name === skillName)
|
||||
if (!skill) return null
|
||||
|
||||
@@ -133,7 +137,7 @@ export function resolveMultipleSkills(skillNames: string[], options?: SkillResol
|
||||
resolved: Map<string, string>
|
||||
notFound: string[]
|
||||
} {
|
||||
const skills = createBuiltinSkills()
|
||||
const skills = createBuiltinSkills({ browserProvider: options?.browserProvider })
|
||||
const skillMap = new Map(skills.map((s) => [s.name, s.template]))
|
||||
|
||||
const resolved = new Map<string, string>()
|
||||
@@ -159,7 +163,7 @@ export async function resolveSkillContentAsync(
|
||||
skillName: string,
|
||||
options?: SkillResolutionOptions
|
||||
): Promise<string | null> {
|
||||
const allSkills = await getAllSkills()
|
||||
const allSkills = await getAllSkills(options)
|
||||
const skill = allSkills.find((s) => s.name === skillName)
|
||||
if (!skill) return null
|
||||
|
||||
@@ -179,7 +183,7 @@ export async function resolveMultipleSkillsAsync(
|
||||
resolved: Map<string, string>
|
||||
notFound: string[]
|
||||
}> {
|
||||
const allSkills = await getAllSkills()
|
||||
const allSkills = await getAllSkills(options)
|
||||
const skillMap = new Map<string, LoadedSkill>()
|
||||
for (const skill of allSkills) {
|
||||
skillMap.set(skill.name, skill)
|
||||
|
||||
Reference in New Issue
Block a user