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>
2026-01-25 15:02:41 +09:00
parent 9f830e7f98
commit 893bd8b153
17 changed files with 1155 additions and 38 deletions
@@ -159,7 +159,7 @@ Available agents: `oracle`, `librarian`, `explore`, `multimodal-looker`

 Oh My OpenCode includes built-in skills that provide additional capabilities:

- **playwright**: Browser automation with Playwright MCP. Use for web scraping, testing, screenshots, and browser interactions.
+- **playwright** (default) / **agent-browser**: Browser automation for web scraping, testing, screenshots, and browser interactions. See [Browser Automation](#browser-automation) for switching between providers.
 - **git-master**: Git expert for atomic commits, rebase/squash, and history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with `delegate_task(category='quick', load_skills=['git-master'], ...)` to save context.

 Disable built-in skills via `disabled_skills` in `~/.config/opencode/oh-my-opencode.json` or `.opencode/oh-my-opencode.json`:
@@ -170,7 +170,54 @@ Disable built-in skills via `disabled_skills` in `~/.config/opencode/oh-my-openc
 }
 ```

-Available built-in skills: `playwright`, `git-master`
+Available built-in skills: `playwright`, `agent-browser`, `git-master`
+
+## Browser Automation
+
+Choose between two browser automation providers:
+
+| Provider | Interface | Features | Installation |
+|----------|-----------|----------|--------------|
+| **playwright** (default) | MCP tools | Playwright MCP server with structured tool calls | Auto-installed via npx |
+| **agent-browser** | Bash CLI | Vercel's CLI with session management, parallel browsers | Requires `bun add -g agent-browser` |
+
+**Switch providers** via `browser_automation_engine` in `oh-my-opencode.json`:
+
+```json
+{
+  "browser_automation_engine": {
+    "provider": "agent-browser"
+  }
+}
+```
+
+### Playwright (Default)
+
+Uses the official Playwright MCP server (`@playwright/mcp`). Browser automation happens through structured MCP tool calls.
+
+### agent-browser
+
+Uses [Vercel's agent-browser CLI](https://github.com/vercel-labs/agent-browser). Key advantages:
+- **Session management**: Run multiple isolated browser instances with `--session` flag
+- **Persistent profiles**: Keep browser state across restarts with `--profile`
+- **Snapshot-based workflow**: Get element refs via `snapshot -i`, interact with `@e1`, `@e2`, etc.
+- **CLI-first**: All commands via Bash - great for scripting
+
+**Installation required**:
+```bash
+bun add -g agent-browser
+agent-browser install  # Download Chromium
+```
+
+**Example workflow**:
+```bash
+agent-browser open https://example.com
+agent-browser snapshot -i  # Get interactive elements with refs
+agent-browser fill @e1 "user@example.com"
+agent-browser click @e2
+agent-browser screenshot result.png
+agent-browser close
+```

 ## Git Master

@@ -78,11 +78,15 @@ Skills provide specialized workflows with embedded MCP servers and detailed inst
 | **frontend-ui-ux** | UI/UX tasks, styling | Designer-turned-developer persona. Crafts stunning UI/UX even without design mockups. Emphasizes bold aesthetic direction, distinctive typography, cohesive color palettes. |
 | **git-master** | commit, rebase, squash, blame | MUST USE for ANY git operations. Atomic commits with automatic splitting, rebase/squash workflows, history search (blame, bisect, log -S). |

-### Skill: playwright
+### Skill: Browser Automation (playwright / agent-browser)

 **Trigger**: Any browser-related request

-Provides browser automation via Playwright MCP server:
+Oh-My-OpenCode provides two browser automation providers, configurable via `browser_automation_engine.provider`:
+
+#### Option 1: Playwright MCP (Default)
+
+The default provider uses Playwright MCP server:

 ```yaml
 mcp:
@@ -91,18 +95,41 @@ mcp:
    args: ["@playwright/mcp@latest"]
 ```

-**Capabilities**:
+**Usage**:
+```
+/playwright Navigate to example.com and take a screenshot
+```
+
+#### Option 2: Agent Browser CLI (Vercel)
+
+Alternative provider using [Vercel's agent-browser CLI](https://github.com/vercel-labs/agent-browser):
+
+```json
+{
+  "browser_automation_engine": {
+    "provider": "agent-browser"
+  }
+}
+```
+
+**Requires installation**:
+```bash
+bun add -g agent-browser
+```
+
+**Usage**:
+```
+Use agent-browser to navigate to example.com and extract the main heading
+```
+
+#### Capabilities (Both Providers)
+
 - Navigate and interact with web pages
 - Take screenshots and PDFs
 - Fill forms and click elements
 - Wait for network requests
 - Scrape content

-**Usage**:
-```
-/playwright Navigate to example.com and take a screenshot
-```
-
 ### Skill: frontend-ui-ux

 **Trigger**: UI design tasks, visual changes