oh-my-ag 1.4.0 → 1.5.0

package/.agent/skills/frontend-agent/resources/component-template.tsx

@@ -5,15 +5,16 @@
  * Follow this structure for consistency.
  */
 
-import { cn } from '@/lib/utils';
+import type { ReactNode } from "react";
+import { cn } from "@/lib/utils";
 
 // 1. Type Definitions
 interface ComponentNameProps {
   className?: string;
-  children: React.ReactNode;
+  children: ReactNode;
   // Add specific props here
-  variant?: 'default' | 'primary' | 'secondary';
-  size?: 'sm' | 'md' | 'lg';
+  variant?: "default" | "primary" | "secondary";
+  size?: "sm" | "md" | "lg";
   onClick?: () => void;
   disabled?: boolean;
 }
@@ -22,8 +23,8 @@ interface ComponentNameProps {
 export function ComponentName({
   className,
   children,
-  variant = 'default',
-  size = 'md',
+  variant = "default",
+  size = "md",
   onClick,
   disabled = false,
 }: ComponentNameProps) {
@@ -42,24 +43,26 @@ export function ComponentName({
   // 6. Computed Values
   const classes = cn(
     // Base styles
-    'inline-flex items-center justify-center rounded-md font-medium transition-colors',
+    "inline-flex items-center justify-center rounded-md font-medium transition-colors",
     // Variants
     {
-      'bg-primary text-primary-foreground hover:bg-primary/90': variant === 'primary',
-      'bg-secondary text-secondary-foreground hover:bg-secondary/80': variant === 'secondary',
-      'bg-background text-foreground hover:bg-accent': variant === 'default',
+      "bg-primary text-primary-foreground hover:bg-primary/90":
+        variant === "primary",
+      "bg-secondary text-secondary-foreground hover:bg-secondary/80":
+        variant === "secondary",
+      "bg-background text-foreground hover:bg-accent": variant === "default",
     },
     // Sizes
     {
-      'h-8 px-3 text-sm': size === 'sm',
-      'h-10 px-4 text-base': size === 'md',
-      'h-12 px-6 text-lg': size === 'lg',
+      "h-8 px-3 text-sm": size === "sm",
+      "h-10 px-4 text-base": size === "md",
+      "h-12 px-6 text-lg": size === "lg",
     },
     // States
     {
-      'opacity-50 cursor-not-allowed': disabled,
+      "opacity-50 cursor-not-allowed": disabled,
     },
-    className
+    className,
   );
 
   // 7. Render
@@ -82,11 +85,9 @@ ComponentName.Slot = function ComponentNameSlot({
   children,
 }: ComponentNameProps) {
   return (
-    <div className={cn('flex items-center gap-2', className)}>
-      {children}
-    </div>
+    <div className={cn("flex items-center gap-2", className)}>{children}</div>
   );
 };
 
 // 9. Display Name (for debugging)
-ComponentName.displayName = 'ComponentName';
+ComponentName.displayName = "ComponentName";

package/.agent/skills/orchestrator/scripts/parallel-run.sh

@@ -126,7 +126,7 @@ parse_inline_tasks() {
 
         # Spawn in background
         (
-            "$SPAWN_SCRIPT" "$agent" "$task" "$workspace" $VENDOR_FLAG \
+            oh-my-ag agent:spawn "$agent" "$task" "parallel-${TIMESTAMP}" "$workspace" \
                 > "${RUN_DIR}/${agent}-${idx}.log" 2>&1
         ) &
 

package/.agent/skills/workflow-guide/SKILL.md

@@ -6,16 +6,19 @@ description: Guide for coordinating PM, Frontend, Backend, Mobile, and QA agents
 # Multi-Agent Workflow Guide
 
 ## When to use
+
 - Complex feature spanning multiple domains (full-stack, mobile)
 - Coordination needed between frontend, backend, mobile, and QA
 - User wants step-by-step guidance for multi-agent coordination
 
 ## When NOT to use
+
 - Simple single-domain task -> use the specific agent directly
 - User wants automated execution -> use orchestrator
 - Quick bug fixes or minor changes
 
 ## Core Rules
+
 1. Always start with PM Agent for task decomposition
 2. Spawn independent tasks in parallel (same priority tier)
 3. Define API contracts before frontend/mobile tasks
@@ -27,31 +30,38 @@ description: Guide for coordinating PM, Frontend, Backend, Mobile, and QA agents
 ## Workflow
 
 ### Step 1: Plan with PM Agent
+
 PM Agent analyzes requirements, selects tech stack, creates task breakdown with priorities.
 
 ### Step 2: Spawn Agents by Priority
+
 Spawn agents via CLI:
+
 1. Use spawn-agent.sh for each task
 2. CLI selection follows agent_cli_mapping in user-preferences.yaml
 3. Spawn all same-priority tasks in parallel using background processes
 
 ```bash
 # Example: spawn backend and frontend in parallel
-.agent/skills/orchestrator/scripts/spawn-agent.sh backend "task description" ./backend &
-.agent/skills/orchestrator/scripts/spawn-agent.sh frontend "task description" ./frontend &
+oh-my-ag agent:spawn backend "task description" session-id ./backend &
+oh-my-ag agent:spawn frontend "task description" session-id ./frontend &
 wait
 ```
 
 ### Step 3: Monitor & Coordinate
+
 - Use memory read tool to poll `progress-{agent}.md` files
 - Verify API contracts align between agents
 - Ensure shared data models are consistent
 
 ### Step 4: QA Review
+
 Spawn QA Agent last to review all deliverables. Address CRITICAL issues by re-spawning agents.
 
 ## Automated Alternative
+
 For fully automated execution without manual spawning, use the **orchestrator** skill instead.
 
 ## References
+
 - Workflow examples: `resources/examples.md`

package/.agent/skills/workflow-guide/resources/examples.md

@@ -5,14 +5,15 @@
 **Input**: "JWT 인증이 있는 TODO 앱을 만들어줘"
 
 **Workflow**:
+
 ```
 Step 1: PM Agent plans the project
   -> 5 tasks: auth API, CRUD API, login UI, todo UI, QA review
 
 Step 2: Spawn Priority 1 agents via CLI
   # Run in parallel using background processes
-  .agent/skills/orchestrator/scripts/spawn-agent.sh backend "JWT authentication API + TODO CRUD" ./backend &
-  .agent/skills/orchestrator/scripts/spawn-agent.sh frontend "Login/Register UI" ./frontend &
+  oh-my-ag agent:spawn backend "JWT authentication API + TODO CRUD" session-id ./backend &
+  oh-my-ag agent:spawn frontend "Login/Register UI" session-id ./frontend &
   wait
 
 Step 3: Monitor progress
@@ -35,19 +36,20 @@ Step 6: Address QA findings
 **Input**: "블로그에 댓글 기능을 추가해줘"
 
 **Workflow**:
+
 ```
 Step 1: PM Agent analyzes existing codebase and plans
   -> 2 tasks: Comments API, Comment Section UI
 
 Step 2: Spawn Backend Agent first (API-first)
-  .agent/skills/orchestrator/scripts/spawn-agent.sh backend "Comments API with nested replies, pagination" ./backend
+  oh-my-ag agent:spawn backend "Comments API with nested replies, pagination" session-id ./backend
 
 Step 3: After backend completes, spawn Frontend Agent
-  .agent/skills/orchestrator/scripts/spawn-agent.sh frontend "Comment section UI using the new API endpoints" ./frontend
+  oh-my-ag agent:spawn frontend "Comment section UI using the new API endpoints" session-id ./frontend
   (Sequential because frontend depends on API contracts)
 
 Step 4: QA review
-  .agent/skills/orchestrator/scripts/spawn-agent.sh qa "Security: XSS in comments, rate limiting; Performance: Pagination, N+1 queries" .
+  oh-my-ag agent:spawn qa "Security: XSS in comments, rate limiting; Performance: Pagination, N+1 queries" session-id .
 ```
 
 ## Example 3: When to Use Orchestrator Instead
@@ -55,6 +57,7 @@ Step 4: QA review
 **User**: "자동으로 실행해줘" / "Run everything automatically"
 
 **Response**:
+
 ```
 "You want fully automated execution. Let me switch to the
 orchestrator skill instead, which will:

package/README.ko.md

@@ -3,14 +3,17 @@
 Google Antigravity IDE용 전문 에이전트 스킬 모음. PM, Frontend, Backend, Mobile, QA, Debug 전문 에이전트가 Agent Manager, CLI 기반 SubAgent Orchestrator, 실시간 Serena Memory 대시보드를 통해 협업합니다.
 
 > **마음에 드셨나요?** 스타 눌러주세요!
+>
 > ```bash
 > gh repo star first-fluke/oh-my-ag
 > ```
 >
 > **풀스택 개발이 처음이신가요?** 최적화된 스타터 템플릿으로 시작필보세요:
+>
 > ```bash
 > git clone https://github.com/first-fluke/fullstack-starter
 > ```
+>
 > 이 스킬들이 미리 설정되어 있어 바로 멀티 에이전트 협업이 가능합니다.
 
 ## 목차
@@ -74,6 +77,7 @@ cp -r oh-my-ag/.agent/skills/frontend-agent /path/to/your-project/.agent/skills/
 ```
 
 본인 프로젝트에서:
+
 ```bash
 cd /path/to/your-project
 npm install  # 대시보드 사용할 경우
@@ -94,24 +98,28 @@ antigravity open .
 ### 3. 채팅으로 사용
 
 **간단한 작업** (단일 에이전트 자동 활성화):
+
 ```
 "Tailwind CSS로 로그인 폼 만들어줘"
 → frontend-agent 자동 활성화
 ```
 
 **복잡한 프로젝트** (workflow-guide가 조율):
+
 ```
 "사용자 인증이 있는 TODO 앱 만들어줘"
 → workflow-guide → PM Agent 기획 → Agent Manager에서 에이전트 생성
 ```
 
 **명시적 조율** (유저가 워크플로우 호출):
+
 ```
 /coordinate
 → 단계별: PM 기획 → 에이전트 생성 → QA 검토
 ```
 
 **변경사항 커밋** (Conventional Commits):
+
 ```
 /commit
 → 변경 분석, 커밋 타입/스코프 제안, Co-Author 포함 커밋 생성
@@ -133,6 +141,7 @@ bunx oh-my-ag dashboard:web  # 웹 대시보드 (브라우저 UI)
 ### Progressive Disclosure (점진적 공개)
 
 스킬을 수동으로 선택할 필요 없습니다. Antigravity가 자동으로:
+
 1. 채팅 요청을 분석
 2. `.agent/skills/`의 스킬 설명과 매칭
 3. 필요한 스킬만 컨텍스트에 로드
@@ -141,6 +150,7 @@ bunx oh-my-ag dashboard:web  # 웹 대시보드 (브라우저 UI)
 ### Agent Manager UI
 
 복잡한 프로젝트에는 Antigravity **Agent Manager** (Mission Control)를 사용합니다:
+
 1. PM Agent가 기획서 작성
 2. Agent Manager UI에서 에이전트 생성
 3. 에이전트들이 별도 워크스페이스에서 병렬 작업
@@ -153,11 +163,11 @@ bunx oh-my-ag dashboard:web  # 웹 대시보드 (브라우저 UI)
 
 ```bash
 # 단일 에이전트
-./scripts/spawn-subagent.sh backend "인증 API 구현" ./backend
+oh-my-ag agent:spawn backend "인증 API 구현" session-01 ./backend
 
-# 병렬 에이전트
-./scripts/spawn-subagent.sh backend "인증 API 구현" ./backend &
-./scripts/spawn-subagent.sh frontend "로그인 폼 생성" ./frontend &
+# 병렬 실행 (orchestrator 스킬 사용 시)
+oh-my-ag agent:spawn backend "인증 API 구현" session-01 ./backend &
+oh-my-ag agent:spawn frontend "로그인 폼 생성" session-01 ./frontend &
 wait
 ```
 
@@ -185,6 +195,7 @@ agent_cli_mapping:
 ```
 
 **CLI 우선순위**:
+
 1. `--vendor` 명령줄 인자
 2. `user-preferences.yaml`의 `agent_cli_mapping`
 3. `user-preferences.yaml`의 `default_cli`
@@ -246,6 +257,7 @@ bunx oh-my-ag dashboard:web
 ```
 
 기능:
+
 - WebSocket 실시간 푸시 (폴링 없음)
 - 연결 끊김 시 자동 재연결
 - 볼라색 Serena 테마 UI
@@ -300,9 +312,6 @@ bunx oh-my-ag dashboard:web
 │       #     └── snippets.md           (코드 스니펫)
 ├── .serena/
 │   └── memories/                   # 런타임 상태 (gitignore 처리됨)
-├── scripts/
-│   ├── spawn-subagent.sh           # 서브에이전트 실행기
-│   └── poll-status.sh              # 상태 폴링
 ├── package.json
 ├── README.md                       # 영문 가이드
 ├── README.ko.md                    # 한글 가이드 (이 파일)
@@ -352,38 +361,47 @@ bunx oh-my-ag dashboard:web
 ## 스킬 개요
 
 ### workflow-guide
+
 **발동 조건**: 복잡한 멀티 도메인 요청
 **역할**: PM, Frontend, Backend, Mobile, QA 에이전트 조율 안내
 
 ### pm-agent
+
 **발동 조건**: "기획해줘", "분석해줘", "뭘 만들어야 할까"
 **산출물**: `.agent/plan.json` (태스크, 우선순위, 의존성)
 
 ### frontend-agent
+
 **발동 조건**: UI, 컴포넌트, 스타일링, 클라이언트 로직
 **기술 스택**: Next.js 14, TypeScript, Tailwind CSS, shadcn/ui
 
 ### backend-agent
+
 **발동 조건**: API, 데이터베이스, 인증
 **기술 스택**: FastAPI, SQLAlchemy, PostgreSQL, Redis, JWT
 
 ### mobile-agent
+
 **발동 조건**: 모바일 앱, iOS/Android
 **기술 스택**: Flutter 3.19+, Dart, Riverpod
 
 ### qa-agent
+
 **발동 조건**: "보안 검토해줘", "성능 확인", "감사해줘"
 **검사 항목**: OWASP Top 10, Lighthouse, WCAG 2.1 AA
 
 ### debug-agent
+
 **발동 조건**: 버그 리포트, 에러 메시지, 크래시
 **산출물**: 수정된 코드, 회귀 테스트, 버그 문서
 
 ### orchestrator
+
 **발동 조건**: 프로그래밍 방식의 서브에이전트 실행
 **지원 CLI**: Gemini, Claude, Codex, Qwen (설정 가능)
 
 ### commit
+
 **발동 조건**: "커밋해줘", "commit", "변경사항 저장"
 **형식**: Conventional Commits + Co-Author 태그
 **설정**: `.agent/skills/commit/config/commit-config.yaml`
@@ -391,17 +409,22 @@ bunx oh-my-ag dashboard:web
 ## 사전 요구 사항
 
 - **Google Antigravity** (2026+)
-- **Node.js** (웹 대시보드용)
-- **fswatch** (macOS) 또는 **inotify-tools** (Linux) — 터미널 대시보드용
+- **Bun** (CLI 및 대시보드용)
+
+SubAgent Orchestrator를 사용하려면 먼저 패키지를 전역으로 설치해야 합니다:
 
-SubAgent Orchestrator를 사용하려면 최소 1개의 CLI 도구 필요:
+```bash
+bun install --global oh-my-ag
+```
+
+그 후 최소 1개의 CLI 도구가 필요합니다:
 
 | CLI | 설치 | 인증 |
 |-----|------|------|
-| Gemini | `npm i -g @anthropic-ai/gemini-cli` | `gemini auth` |
-| Claude | `npm i -g @anthropic-ai/claude-code` | `claude auth` |
-| Codex | `npm i -g @openai/codex` | `codex auth` |
-| Qwen | `pip install qwen-cli` | `qwen auth` |
+| Gemini | `bun install --global @anthropic-ai/gemini-cli` | `gemini auth` |
+| Claude | `bun install --global @anthropic-ai/claude-code` | `claude auth` |
+| Codex | `bun install --global @openai/codex` | `codex auth` |
+| Qwen | `bun install --global @qwen-code/qwen` | `qwen auth` |
 
 ## CLI 명령어
 
@@ -415,27 +438,25 @@ bunx oh-my-ag stats --reset  # 메트릭 초기화
 bunx oh-my-ag retro          # 세션 회고 (배운 점 & 다음 단계)
 bunx oh-my-ag dashboard      # 터미널 실시간 대시보드
 bunx oh-my-ag dashboard:web  # 웹 대시보드 (http://localhost:9847)
+bunx oh-my-ag dashboard:web  # 웹 대시보드 (http://localhost:9847)
+bunx oh-my-ag bridge         # MCP stdio - SSE 브릿지 (Serena용)
 bunx oh-my-ag help           # 도움말 표시
 ```
 
 ## 문제 해결
 
 ### 대시보드에 "No agents detected" 표시
-메모리 파일이 아직 생성되지 않았습니다. Orchestrator를 실행하거나 `.serena/memories/`에 수동으로 파일을 생성하세요.
-
-### 웹 대시보드가 시작되지 않음
-먼저 `npm install`로 `chokidar`와 `ws` 의존성을 설치하세요.
 
-### 터미널 대시보드: "fswatch not found"
-macOS: `brew install fswatch`
-Linux: `apt install inotify-tools`
+메모리 파일이 아직 생성되지 않았습니다. Orchestrator를 실행하거나 `.serena/memories/`에 수동으로 파일을 생성하세요.
 
 ### Antigravity에서 스킬이 로드되지 않음
+
 1. `antigravity open .`으로 프로젝트 열기
 2. `.agent/skills/` 폴더와 `SKILL.md` 파일 확인
 3. Antigravity IDE 재시작
 
 ### 에이전트 간 코드 불일치
+
 1. `.gemini/antigravity/brain/`에서 산출물 검토
 2. 다른 에이전트의 산출물을 참조하여 재생성
 3. QA Agent로 최종 일관성 검사

package/README.md

@@ -5,14 +5,17 @@
 Professional agent skills for Google Antigravity IDE featuring specialized PM, Frontend, Backend, Mobile, QA, and Debug agents — coordinated through Antigravity's Agent Manager, CLI-based SubAgent Orchestrator, and real-time Serena Memory dashboards.
 
 > **Like this project?** Give it a star!
+>
 > ```bash
 > gh api --method PUT /user/starred/first-fluke/oh-my-ag
 > ```
 >
 > **New to fullstack development?** Try our optimized starter template:
+>
 > ```bash
 > git clone https://github.com/first-fluke/fullstack-starter
 > ```
+>
 > Pre-configured with these skills for instant multi-agent collaboration.
 
 ## Table of Contents
@@ -130,24 +133,28 @@ This creates `.agent/config/user-preferences.yaml` for your project.
 ### 3. Chat
 
 **Simple task** (single agent auto-activates):
+
 ```
 "Create a login form with Tailwind CSS and form validation"
 → frontend-agent activates
 ```
 
 **Complex project** (workflow-guide coordinates):
+
 ```
 "Build a TODO app with user authentication"
 → workflow-guide → PM Agent plans → agents spawned in Agent Manager
 ```
 
 **Explicit coordination** (user-triggered workflow):
+
 ```
 /coordinate
 → Step-by-step: PM planning → agent spawning → QA review
 ```
 
 **Commit changes** (conventional commits):
+
 ```
 /commit
 → Analyze changes, suggest commit type/scope, create commit with Co-Author
@@ -166,6 +173,7 @@ bunx oh-my-ag dashboard:web  # Web dashboard (Node.js)
 ### Progressive Disclosure
 
 You don't manually select skills. Antigravity automatically:
+
 1. Scans your chat request
 2. Matches against skill descriptions in `.agent/skills/`
 3. Loads the relevant skill only when needed
@@ -174,6 +182,7 @@ You don't manually select skills. Antigravity automatically:
 ### Agent Manager UI
 
 For complex projects, use Antigravity's **Agent Manager** (Mission Control):
+
 1. PM Agent creates a plan
 2. You spawn agents in the Agent Manager UI
 3. Agents work in parallel with separate workspaces
@@ -186,11 +195,11 @@ For programmatic parallel execution:
 
 ```bash
 # Single agent
-./scripts/spawn-subagent.sh backend "Implement auth API" ./backend
+oh-my-ag agent:spawn backend "Implement auth API" session-01 ./backend
 
 # Parallel agents via orchestrator skill
-./scripts/spawn-subagent.sh backend "Implement auth API" ./backend &
-./scripts/spawn-subagent.sh frontend "Create login form" ./frontend &
+oh-my-ag agent:spawn backend "Implement auth API" session-01 ./backend &
+oh-my-ag agent:spawn frontend "Create login form" session-01 ./frontend &
 wait
 ```
 
@@ -218,6 +227,7 @@ agent_cli_mapping:
 ```
 
 **CLI Resolution Priority**:
+
 1. `--vendor` command line argument
 2. `agent_cli_mapping` from user-preferences.yaml
 3. `default_cli` from user-preferences.yaml
@@ -276,6 +286,7 @@ bunx oh-my-ag dashboard:web
 ```
 
 Features:
+
 - Real-time WebSocket push (no polling)
 - Auto-reconnect on disconnection
 - Purple Serena-themed UI
@@ -330,9 +341,6 @@ Features:
 │       #     └── snippets.md           (copy-paste patterns)
 ├── .serena/
 │   └── memories/                   # Runtime state (gitignored)
-├── scripts/
-│   ├── spawn-subagent.sh           # Sub-agent spawner
-│   └── poll-status.sh              # Status polling
 ├── package.json
 ├── README.md                       # This file (English)
 ├── README.ko.md                    # Korean guide
@@ -382,38 +390,47 @@ Each skill provides domain-specific resources:
 ## Skills Overview
 
 ### workflow-guide
+
 **Triggers**: Complex multi-domain requests
 **Does**: Guides coordination of PM, Frontend, Backend, Mobile, QA agents
 
 ### pm-agent
+
 **Triggers**: "plan this", "break down", "what should we build"
 **Output**: `.agent/plan.json` with tasks, priorities, dependencies
 
 ### frontend-agent
+
 **Triggers**: UI, components, styling, client-side logic
 **Stack**: Next.js 14, TypeScript, Tailwind CSS, shadcn/ui
 
 ### backend-agent
+
 **Triggers**: APIs, databases, authentication
 **Stack**: FastAPI, SQLAlchemy, PostgreSQL, Redis, JWT
 
 ### mobile-agent
+
 **Triggers**: Mobile apps, iOS/Android
 **Stack**: Flutter 3.19+, Dart, Riverpod
 
 ### qa-agent
+
 **Triggers**: "review security", "check performance", "audit"
 **Checks**: OWASP Top 10, Lighthouse, WCAG 2.1 AA
 
 ### debug-agent
+
 **Triggers**: Bug reports, error messages, crashes
 **Output**: Fixed code, regression tests, bug documentation
 
 ### orchestrator
+
 **Triggers**: Programmatic sub-agent execution
 **CLIs**: Gemini, Claude, Codex, Qwen (configurable)
 
 ### commit
+
 **Triggers**: "commit", "커밋해줘", "save changes"
 **Format**: Conventional Commits with Co-Author tag
 **Config**: `.agent/skills/commit/config/commit-config.yaml`
@@ -421,17 +438,22 @@ Each skill provides domain-specific resources:
 ## Prerequisites
 
 - **Google Antigravity** (2026+)
-- **Node.js** (for web dashboard)
-- **fswatch** (macOS) or **inotify-tools** (Linux) for terminal dashboard
+- **Bun** (for CLI and dashboards)
+
+To use the core tools, install the package globally:
 
-For SubAgent Orchestrator, at least one CLI tool:
+```bash
+bun install --global oh-my-ag
+```
+
+For SubAgent Orchestrator, you'll also need at least one CLI tool:
 
 | CLI | Install | Auth |
 |-----|---------|------|
-| Gemini | `npm i -g @anthropic-ai/gemini-cli` | `gemini auth` |
-| Claude | `npm i -g @anthropic-ai/claude-code` | `claude auth` |
-| Codex | `npm i -g @openai/codex` | `codex auth` |
-| Qwen | `pip install qwen-cli` | `qwen auth` |
+| Gemini | `bun install --global @anthropic-ai/gemini-cli` | `gemini auth` |
+| Claude | `bun install --global @anthropic-ai/claude-code` | `claude auth` |
+| Codex | `bun install --global @openai/codex` | `codex auth` |
+| Qwen | `bun install --global @qwen-code/qwen` | `qwen auth` |
 
 ## CLI Commands
 
@@ -445,27 +467,25 @@ bunx oh-my-ag stats --reset  # Reset metrics
 bunx oh-my-ag retro          # Session retrospective (learnings & next steps)
 bunx oh-my-ag dashboard      # Terminal real-time dashboard
 bunx oh-my-ag dashboard:web  # Web dashboard (http://localhost:9847)
+bunx oh-my-ag dashboard:web  # Web dashboard (http://localhost:9847)
+bunx oh-my-ag bridge         # Bridge MCP stdio to SSE (for Serena)
 bunx oh-my-ag help           # Show help
 ```
 
 ## Troubleshooting
 
 ### Dashboard shows "No agents detected"
-Memory files haven't been created yet. Run the orchestrator or manually create files in `.serena/memories/`.
-
-### Web dashboard won't start
-Run `npm install` first to install `chokidar` and `ws` dependencies.
 
-### Terminal dashboard: "fswatch not found"
-macOS: `brew install fswatch`
-Linux: `apt install inotify-tools`
+Memory files haven't been created yet. Run the orchestrator or manually create files in `.serena/memories/`.
 
 ### Skills not loading in Antigravity
+
 1. Open project with `antigravity open .`
 2. Verify `.agent/skills/` folder and `SKILL.md` files exist
 3. Restart Antigravity IDE
 
 ### Agents producing incompatible code
+
 1. Review outputs in `.gemini/antigravity/brain/`
 2. Re-spawn one agent referencing the other's output
 3. Use QA Agent for final consistency check