{"skill":{"slug":"oh-my-openagent","displayName":"Oh-my-openagent","summary":"Configure and operate oh-my-openagent (OmO), the OpenCode plugin that adds multi-agent orchestration, skills, hooks, MCPs, and multi-provider model routing....","description":"---\nname: oh-my-openagent\ndescription: Configure and operate oh-my-openagent (OmO), the OpenCode plugin that adds multi-agent orchestration, skills, hooks, MCPs, and multi-provider model routing. Use this skill when the user asks about OmO configuration, agent setup, model selection, category tuning, hook management, or provider authentication.\nhomepage: https://github.com/code-yeongyu/oh-my-openagent\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\"}}\n---\n\n# oh-my-openagent\n\noh-my-openagent (OmO) is an OpenCode plugin that transforms a single-agent coding assistant into a multi-agent orchestration system with 11 specialized agents, 8 task categories, 40+ hooks, built-in skills, MCPs, and multi-provider model routing.\n\nRepository: https://github.com/code-yeongyu/oh-my-openagent\nDiscord: https://discord.gg/PUwSMR9XNk\nConfig schema: https://raw.githubusercontent.com/code-yeongyu/oh-my-openagent/dev/assets/oh-my-opencode.schema.json\n\n## When to use this skill\n\n- User asks how to configure oh-my-openagent or oh-my-opencode\n- User wants to change which model an agent or category uses\n- User asks about the agent system (Sisyphus, Oracle, Hephaestus, etc.)\n- User wants to add, disable, or configure hooks\n- User asks about task delegation, categories, or background tasks\n- User needs help with provider authentication or model routing\n- User wants to create or manage custom skills\n- User asks about slash commands like /ralph-loop, /start-work, /refactor\n\n## Installation\n\n```bash\nbunx oh-my-opencode install\n```\n\nOn Windows, interactive mode may crash. Configure manually instead:\n\n1. Edit `~/.config/opencode/opencode.json`:\n```json\n{\n  \"plugin\": [\"oh-my-opencode@latest\"]\n}\n```\n\n2. Edit `~/.config/opencode/oh-my-opencode.json` for agent/category overrides.\n\n## Core concepts\n\n### Agents\n\nOmO provides 11 agents, each with a default model and role:\n\n| Agent | Role | Default Model |\n|-------|------|---------------|\n| Sisyphus | Main orchestrator | claude-opus-4-6 |\n| Hephaestus | Deep worker (code-heavy) | gpt-5.3-codex |\n| Oracle | Architecture consultant (read-only) | gpt-5.4 |\n| Librarian | Documentation and reference search | gemini-3-flash |\n| Explore | Fast codebase grep | grok-code-fast-1 |\n| Multimodal-Looker | Vision / image analysis | gpt-5.3-codex |\n| Prometheus | Planner | claude-opus-4-6 |\n| Metis | Plan consultant | claude-opus-4-6 |\n| Momus | Plan reviewer | gpt-5.4 |\n| Atlas | Todo orchestrator | claude-sonnet-4-6 |\n| Sisyphus-Junior | Delegated task worker | (category-dependent) |\n\nSee `references/agents.md` for full details including fallback chains.\n\n### Categories\n\n8 built-in task categories determine which model Sisyphus-Junior uses:\n\n| Category | Best For | Default Model |\n|----------|----------|---------------|\n| visual-engineering | Frontend, UI/UX, design | gemini-3.1-pro |\n| ultrabrain | Hard logic-heavy tasks | gpt-5.4 |\n| deep | Autonomous problem-solving | gpt-5.3-codex |\n| artistry | Creative, unconventional approaches | gemini-3.1-pro |\n| quick | Trivial single-file changes | claude-haiku-4-5 |\n| unspecified-low | Low-effort misc tasks | claude-sonnet-4-6 |\n| unspecified-high | High-effort misc tasks | claude-opus-4-6 |\n| writing | Documentation, prose | gemini-3-flash |\n\nSee `references/categories.md` for full details including fallback chains.\n\n### Configuration\n\nAll config lives in `~/.config/opencode/oh-my-opencode.json`.\n\nOverride any agent:\n```json\n{\n  \"agents\": {\n    \"sisyphus\": {\n      \"model\": \"my-preferred-model\",\n      \"fallback_models\": [\"fallback-1\", \"fallback-2\"]\n    }\n  }\n}\n```\n\nOverride any category:\n```json\n{\n  \"categories\": {\n    \"quick\": {\n      \"model\": \"fast-cheap-model\"\n    }\n  }\n}\n```\n\nSee `references/configuration.md` for the full config reference.\n\n### Provider priority\n\nOmO resolves models through a provider priority chain:\n\n1. Native (built-in to OpenCode)\n2. Kimi for Coding\n3. GitHub Copilot\n4. Venice\n5. OpenCode Go\n6. OpenCode Zen\n7. Z.ai Coding Plan\n\nEach agent's default model has a fallback chain. If no provider can serve a model, OmO tries the next fallback. See `references/providers.md`.\n\n### Tools\n\nOmO injects 40+ tools into agents. See `references/tools.md` for the full list.\n\n### Hooks\n\n40+ built-in hooks that fire on events (session start, file save, pre-commit, etc.). See `references/hooks.md`.\n\n### Skills\n\nBuilt-in skills: playwright, playwright-cli, agent-browser, dev-browser, git-master, frontend-ui-ux. See `references/skills.md`.\n\n### Slash commands\n\n`/ralph-loop`, `/ulw-loop`, `/start-work`, `/refactor`, `/init-deep`, `/handoff`, `/cancel-ralph`, `/stop-continuation`. See `references/commands.md`.\n\n### MCPs\n\nBuilt-in MCP servers: websearch (Exa), context7 (docs), grep_app (GitHub code search). See `references/mcps.md`.\n\n## Security and privacy\n\n- OmO runs locally as an OpenCode plugin\n- No data is sent to oh-my-openagent servers\n- Model API calls go directly to the configured providers (GitHub Copilot, Google, OpenAI, etc.)\n- Config files are stored locally in `~/.config/opencode/`\n- Auth tokens are stored in `~/.local/share/opencode/auth.json`\n","topics":["Multi Agent","Orchestration"],"tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":796,"installsAllTime":30,"installsCurrent":3,"stars":0,"versions":1},"createdAt":1773525341029,"updatedAt":1778999779931},"latestVersion":{"version":"1.0.0","createdAt":1773525341029,"changelog":"oh-my-openagent 1.0.0\n\n- Initial release introducing a multi-agent orchestration plugin for OpenCode.\n- Adds 11 specialized agents, 8 configurable task categories, and automatic multi-provider model routing.\n- Includes over 40 built-in hooks, specialized skills, tools, and MCP (Multi-Channel Provider) integrations.\n- Offers flexible configuration for models, agents, categories, and provider priorities via local config files.\n- Supports advanced features like slash commands, provider authentication, and deep customization for agent roles and behaviors.","license":"MIT-0"},"metadata":{"setup":[],"os":null,"systems":null},"owner":{"handle":"kolyanberoks-23loud","userId":"s17c8v62qcbz3p76rs00bd38f1885ymy","displayName":"enjoyer","image":"https://avatars.githubusercontent.com/u/264371152?v=4"},"moderation":{"isSuspicious":false,"isMalwareBlocked":false,"verdict":"clean","reasonCodes":["review.llm_review"],"summary":"Review: review.llm_review","engineVersion":"v2.4.24","updatedAt":1780089889741}}