ohmg
oh-my-ag (ohmg) - Multi-Agent Orchestrator
When to use this skill
- Coordinating complex multi-domain projects
- Parallelizing tasks across multiple AI agents (PM, Frontend, Backend, etc.)
- Using Serena Memory for cross-agent state management
- Setting up real-time observability dashboards for agent workflows
- Integrating multi-CLI vendors (Gemini, Claude, Codex) in a single project
Quick Start
Scenario: Platform setup for a Unity3D project
# Step 1: Install oh-my-ag
bunx oh-my-ag
# Select "Unity3D" when prompted for project type
# Step 2: Verify system is ready
bunx oh-my-ag doctor
# Step 3: Launch the monitoring dashboard and spawn your first agent
bunx oh-my-ag dashboard &
oh-my-ag agent:spawn backend "Set up Unity3D build pipeline" session-unity-01
1. Core Concepts
Specialized Agents
| Agent | Specialization | Triggers |
|---|---|---|
| Workflow Guide | Coordinates complex projects | "multi-domain", "complex project" |
| PM Agent | Requirements, task decomposition | "plan", "break down" |
| Frontend Agent | React/Next.js, styling | "UI", "component", "styling" |
| Backend Agent | API, database, auth | "API", "database", "auth" |
| Debug Agent | Bug diagnosis, RCA | "bug", "error", "crash" |
Serena Memory
Orchestrator writes structured state to .serena/memories/ for real-time monitoring and cross-agent coordination.
2. Installation & Setup
Prerequisites
- Bun (CLI and dashboards)
- uv (Serena setup)
Interactive Setup
bunx oh-my-ag
Select project type to install relevant skills to .agent/skills/.
Verification
bunx oh-my-ag doctor
3. Usage Patterns
Explicit Coordination
/coordinate
PM planning → agent spawning → QA review.
Spawning Agents via CLI
# Spawn backend agent for a specific task
oh-my-ag agent:spawn backend "Implement auth API" session-01
Dashboard Monitoring
- Terminal:
bunx oh-my-ag dashboard - Web:
bunx oh-my-ag dashboard:web(http://localhost:9847)
4. MCP Connection & Bridging
SSE Mode (Shared Server)
If environment needs stdio-to-http bridging:
bunx oh-my-ag bridge http://localhost:12341/sse
5. Configuration
Configure per-agent CLI mapping in .agent/config/user-preferences.yaml:
agent_cli_mapping:
frontend: gemini
backend: codex
pm: claude
qa: claude
Quick Reference
| Command | Action |
|---|---|
bunx oh-my-ag |
Interactive installer |
/setup |
Agent-side configuration |
bunx oh-my-ag doctor |
System check & repair |
bunx oh-my-ag update |
Update skills |
bunx oh-my-ag usage |
Show quota usage |
More from jeo-tech-ai/oh-my-unity3d
bmad-gds
AI-driven Game Development Studio using BMAD methodology. Covers the Execute and Assess phases of the BMAD TEA (Think→Execute→Assess) loop — the core Specification-Driven Development (SDD) cycle. Routes game projects through Pre-production, Design, Architecture, Production, and Game Testing phases with 6 specialized agents. Supports Unity, Unreal Engine, Godot, and custom engines.
11code-review
Conduct thorough, constructive code reviews for quality and security. Use when reviewing pull requests, checking code quality, identifying bugs, or auditing security. Handles best practices, SOLID principles, security vulnerabilities, performance analysis, and testing coverage.
10unity-mcp
|
10changelog-maintenance
Maintain a clear and informative changelog for software releases. Use when documenting version changes, tracking features, or communicating updates to users. Handles semantic versioning, changelog formats, and release notes.
9backend-testing
Write comprehensive backend tests including unit tests, integration tests, and API tests. Use when testing REST APIs, database operations, authentication flows, or business logic. Handles Jest, Pytest, Mocha, testing strategies, mocking, and test coverage.
9ralph
Specification-first AI development powered by Ouroboros. Socratic questioning exposes hidden assumptions before writing code. Evolutionary loop (Interview → Seed → Execute → Evaluate → Evolve) runs until ontology converges. Ralph mode persists until verification passes — the boulder never stops. Use when user says \"ralph\", \"ooo\", \"don't stop\", \"must complete\", \"until it works\", \"keep going\", \"interview me\", or \"stop prompting\".
9