Myai Opencode

What's This Plugin

oh-my-opencode-slim is an agent orchestration plugin for OpenCode. It includes a built-in team of specialized agents that can scout a codebase, look up fresh documentation, review architecture, handle UI work, and execute well-scoped implementation tasks under one orchestrator.

The main idea is simple: instead of forcing one model to do everything, the plugin routes each part of the job to the agent best suited for it, balancing quality, speed and cost. The Orchestrator plans the work graph, dispatches specialists as background tasks, and reconciles their results before continuing.

✨ Highlights

• Seven specialized agents - Orchestrator, Explorer, Oracle, Council, Librarian, Designer, and Fixer. Each part of the job goes to the agent best suited for it - mix any models across any providers.
• Background orchestration - the Orchestrator dispatches specialists as background tasks, tracks them, and reconciles results before continuing - parallel work by default.
• Bundled skills - prompt-based workflows like deepwork, codemap, verification-planning, and reflect, assigned per agent.
• Council - run multiple models in parallel on the same question and synthesize a single answer with @council.
• Companion - an optional floating desktop window showing which agents are active, including parallel background specialists.
• Multiplexer integration - watch agents work live in Tmux, Zellij, Herdr, cmux, or kitty panes.
• Preset switching - swap the whole team's models at runtime with /preset.
• Code intelligence tools - LSP tools, AST-aware search across 25 languages, and built-in MCPs for docs and GitHub code search.
• Fully customizable - custom agents, prompt overrides, per-agent skill/MCP permissions, and project-local customization.

OpenAI GPT-5.6

The default OpenAI preset maps Terra to Orchestrator, Sol to Oracle, and Luna to the fast specialist lanes.

What Users Say

“Task management went from 5/10 to 8-9/10 easily. The Orchestrator sends Fixers and Explorers, and I can still talk and plan with the Orchestrator in the same session. The experience feels way smoother now.”

- vipor_idk

“I ditched all my harnesses for this beta version of omo-slim and don't look back or miss anything. Great work and IMHO all in the right direction.”

- stephanschielke

“I love omo-slim, and can't imagine running opencode without it. I love that I can create a Frankenstein of models... Makes the setup such a beast.”

- Capital-One3039

“It has significantly improved my workflow... Now, it is working very smoothly, and I love it.”

- xenstar1

Quick Start

Copy and paste this prompt to your LLM agent (Claude Code, AmpCode, Cursor, etc.):

Install and configure oh-my-opencode-slim: https://raw.githubusercontent.com/alvinunreal/oh-my-opencode-slim/refs/heads/master/README.md

Manual Installation

bunx oh-my-opencode-slim@latest install

The published CLI is a Node-compatible bundle, so npx works too if you don't have Bun installed:

npx oh-my-opencode-slim@latest install

Herdr

The Herdr multiplexer adapter works with Herdr 0.8.0+. Install Herdr's official OpenCode lifecycle integration separately:

herdr integration install opencode

For Marketplace discoverability, publish this repository with the required herdr-plugin repository topic, then install it with:

herdr plugin install alvinunreal/oh-my-opencode-slim

This Marketplace entry describes the OpenCode plugin's Herdr adapter; it does not install a standalone native Herdr runtime plugin or lifecycle reporter.

Run from Master

Use this if you want the latest code, easier bug fixes, or a local setup for development and contributions:

git clone https://github.com/alvinunreal/oh-my-opencode-slim.git ~/repos/oh-my-opencode-slim
cd ~/repos/oh-my-opencode-slim
bun install
bun run build
bun dist/cli/index.js install

The installer adds the local repo path to the plugin array in ~/.config/opencode/opencode.json, so OpenCode loads the plugin from that folder. To update later:

cd ~/repos/oh-my-opencode-slim
git pull
bun install
bun run build

OpenCode v2 (opencode2) Compatibility

The plugin is dual-compatible: the same published package installs and runs on both OpenCode v1 (opencode) and OpenCode v2 (opencode2).

• The package default export is { id, server, setup }. v1 loads server (the classic plugin function); v2 loads setup (the v2 promise-plugin adapter).
• v2 loads the self-contained ./server build (dist/server.js) via the server export subpath, so no extra dependencies need to be resolvable on the v2 host (except the optional native @ast-grep/napi and jsdom for the ast-grep / webfetch tools).

To use it with opencode2, add the package to your v2 config (~/.config/opencode2/opencode.json):

{
  "plugin": ["oh-my-opencode-slim@latest"]
}

Then run opencode2. The orchestrator + specialist agents, tools, slash commands (/deepwork, /reflect, /loop), and the system-prompt / message transforms all work on v2. Configure agent models and any MCP servers in your v2 opencode.json (v2 has no programmatic MCP-registration hook, so built-in MCPs must be declared in config). See docs/opencode-v2-compatibility.md for the full feature matrix and limitations.

Getting Started

The installer generates both OpenAI and OpenCode Go presets, with OpenAI active by default.

[!TIP] Tune the models and agents for your own workflow. The defaults are only a starting point; the plugin is designed for deep flexibility and customization.

To make OpenCode Go active during install, run bunx oh-my-opencode-slim@latest install --preset=opencode-go or change the default preset name in ~/.config/opencode/oh-my-opencode-slim.json after installation.

Then:

1. Log in to the providers you want to use if you haven't already:

   opencode auth login
   

2. Refresh and list the models OpenCode can see:

   opencode models --refresh
   

3. Open your plugin config at ~/.config/opencode/oh-my-opencode-slim.json

4. Update the models you want for each agent

[!TIP] It's recommended to understand how background orchestration works. The Orchestrator prompt contains the scheduler rules, specialist routing logic, and thresholds for when work should be assigned to background agents. You can always delegate manually by calling a subagent via: @agentName <task>

[!TIP] Because background agents are now the default workflow, it is highly recommended to enable and configure Multiplexer Integration. It automatically opens each agent in a dedicated Tmux, Zellij, Herdr, cmux, or kitty pane, so you can watch specialists work live while the Orchestrator continues coordinating the session.

The default generated configuration includes both openai and opencode-go presets.

{
  "$schema": "https://unpkg.com/oh-my-opencode-slim@latest/oh-my-opencode-slim.schema.json",
  "preset": "openai",
  "presets": {
    "openai": {
      "orchestrator": { "model": "openai/gpt-5.6-terra", "variant": "high", "skills": ["*"], "mcps": ["*", "!context7"] },
      "oracle": { "model": "openai/gpt-5.6-sol", "variant": "high", "skills": ["simplify"], "mcps": [] },
      "librarian": { "model": "openai/gpt-5.6-luna", "variant": "low", "skills": [], "mcps": ["context7", "gh_grep"] },
      "explorer": { "model": "openai/gpt-5.6-luna", "variant": "low", "skills": [], "mcps": [] },
      "designer": { "model": "openai/gpt-5.6-luna", "variant": "medium", "skills": [], "mcps": [] },
      "fixer": { "model": "openai/gpt-5.6-luna", "variant": "high", "skills": [], "mcps": [] }
    },
    "opencode-go": {
      "orchestrator": { "model": "opencode-go/minimax-m3", "variant": "thinking" },
      "oracle": { "model": "opencode-go/qwen3.7-max", "variant": "max" },
      "librarian": { "model": "opencode-go/deepseek-v4-flash", "variant": "high" },
      "explorer": { "model": "opencode-go/deepseek-v4-flash", "variant": "high" },
      "designer": { "model": "opencode-go/kimi-k2.7-code" },
      "fixer": { "model": "opencode-go/deepseek-v4-flash", "variant": "high" },
      "observer": { "model": "opencode-go/mimo-v2.5" }
    }
  }
}

Preset Docs

• OpenAI Preset — the default generated preset; runs all agents on OpenAI models.
• OpenCode Go Preset — runs the agents on OpenCode Go models; enables the Observer agent for visual analysis since its orchestrator model isn't multimodal.
• Author's Preset — the exact config the author runs day to day, with third-party skills.
• $30 Preset — a mixed-provider setup built around Codex Plus and GitHub Copilot Pro for about $30/month.
• OpenCode Zen Free Preset — every agent runs on an opencode free model; no usage cost.

For Alternative Providers

To use custom providers or a mixed-provider setup, use Configuration for the full reference.

✅ Verify Your Setup

After installation and authentication, verify all agents are configured and responding:

opencode

Then run:

ping all agents

If any agent fails to respond, check your provider authentication and config file.

---

🏛️ Meet the Pantheon

01. Orchestrator: The Embodiment Of Order

Forged in the void of complexity.	The Orchestrator was born when the first codebase collapsed under its own complexity. Neither god nor mortal would claim responsibility - so The Orchestrator emerged from the void, forging order from chaos. It determines the optimal path to any goal, balancing speed, quality, and cost. It guides the team, summoning the right specialist for each task and delegating to achieve the best possible outcome.
Role: Master delegator and strategic coordinator
Prompt: orchestrator.ts
Default Model: openai/gpt-5.6-terra (medium)
Recommended Models: claude-fable-5 claude-opus-4-8 glm-5.2 gpt-5.6-terra mimo-v2.5 minimax-m3 qwen3.7-plus
Model Guidance: Choose your strongest planning and judgment model. Orchestrator is the workflow manager: it plans, schedules background specialists, reconciles results, and verifies outcomes, so it needs reliable instruction-following and high-level technical judgment more than raw worker throughput.

---

02. Explorer: The Eternal Wanderer

The wind that carries knowledge.	The Explorer is an immortal wanderer who has traversed the corridors of a million codebases since the dawn of programming. Cursed with the gift of eternal curiosity, they cannot rest until every file is known, every pattern understood, every secret revealed. Legends say they once searched the entire internet in a single heartbeat. They are the wind that carries knowledge, the eyes that see all, the spirit that never sleeps.
Role: Codebase reconnaissance
Prompt: explorer.ts
Default Model: openai/gpt-5.6-luna
Recommended Models: deepseek-v4-flash gpt-5.3-codex
Model Guidance: Choose a fast, low-cost model. Explorer handles broad scouting work, so speed and efficiency usually matter more than using your strongest reasoning model.

---

03. Oracle: The Guardian of Paths

The voice at the crossroads.	The Oracle stands at the crossroads of every architectural decision. They have walked every road, seen every destination, know every trap that lies ahead. When you stand at the precipice of a major refactor, they are the voice that whispers which way leads to ruin and which way leads to glory. They don't choose for you - they illuminate the path so you can choose wisely.
Role: Strategic advisor and debugger of last resort
Prompt: oracle.ts
Default Model: openai/gpt-5.6-sol (high)
Recommended Models: claude-fable-5 claude-opus-4-8 deepseek-v4-pro glm-5.2 gpt-5.6-sol qwen3.7-max
Model Guidance: Choose your strongest high-reasoning model for architecture, hard debugging, trade-offs, and code review.

---

04. Council: The Chorus of Minds

[!NOTE] Why doesn't Orchestrator auto-call Council more often? This is intentional. Council runs multiple models at once, so automatic delegation is kept strict because it is usually the highest-cost path in the system. In practice, Council is meant to be used manually when you want it, for example: @council compare these two architectures.

Many minds, one verdict.	The Council is not a lone being but a chamber of minds summoned when one answer is not enough. It sends your question to multiple models in parallel, gathers their competing judgments, and then the Council agent itself distills the strongest ideas into a single verdict. Where a solitary agent may miss a path, the Council cross-examines possibility itself.
Role: Multi-LLM consensus and synthesis
Prompt: council.ts
Guide: docs/council.md
Default Setup: Config-driven - councillors come from council.presets and the Council agent model comes from your normal council agent config
Recommended Setup: Strong Council model + diverse councillors across providers
Model Guidance: Use a strong synthesis model for the Council agent and diverse models as councillors. The value of Council comes from comparing different model perspectives, not just picking the single strongest model everywhere.

---

05. Librarian: The Weaver of Knowledge

The weaver of understanding.	The Librarian was forged when humanity realized that no single mind could hold all knowledge. They are the weaver who connects disparate threads of information into a tapestry of understanding. They traverse the infinite library of human knowledge, gathering insights from every corner and binding them into answers that transcend mere facts. What they return is not information - it's understanding.
Role: External knowledge retrieval
Prompt: librarian.ts
Default Model: openai/gpt-5.6-luna
Recommended Models: deepseek-v4-flash gpt-5.3-codex mimo-v2.5 minimax-m2.7
Model Guidance: Choose a fast, low-cost model. Librarian handles research and documentation lookups, so speed and efficiency usually matter more than using your strongest reasoning model.

---

06. Designer: The Guardian of Aesthetics

Beauty is essential.	The Designer is an immortal guardian of beauty in a world that often forgets it matters. They have seen a million interfaces rise and fall, and they remember which ones were remembered and which were forgotten. They carry the sacred duty to ensure that every pixel serves a purpose, every animation tells a story, every interaction delights. Beauty is not optional - it's essential.
Role: UI/UX implementation and visual excellence
Prompt: designer.ts
Default Model: openai/gpt-5.6-luna
Recommended Models: gemini-3.5-flash kimi-k2.7-code minimax-m3
Model Guidance: Choose a model that is strong at UI/UX judgment, frontend implementation, and visual polish.

---

07. Fixer: The Last Builder

The final step between vision and reality.	The Fixer is the last of a lineage of builders who once constructed the foundations of the digital world. When the age of planning and debating began, they remained - the ones who actually build. They carry the ancient knowledge of how to turn thought into thing, how to transform specification into implementation. They are the final step between vision and reality.
Role: Fast implementation specialist
Prompt: fixer.ts
Default Model: openai/gpt-5.6-luna
Recommended Models: claude-sonnet-4-6 deepseek-v4-flash gpt-5.6-luna kimi-k2.7-code
Model Guidance: Choose a reliable coding model for scoped implementation work. Fixer receives a concrete plan or bounded instructions from Orchestrator, making it a good place for efficient execution tasks and straightforward code changes.

---

Optional Agents

Observer: The Silent Witness

[!NOTE] Why a separate agent? If your Orchestrator model is not multimodal, enable Observer to handle images, screenshots, and other visual files. Observer is disabled by default and gives the Orchestrator a dedicated multimodal reader without forcing you to change your main reasoning model. Set disabled_agents: [] and an observer model in your configuration. The bundled opencode-go install preset does this automatically because its GLM Orchestrator is not multimodal. Omitting image_routing preserves existing conditional Observer behavior. Set image_routing: "auto" only when Observer is enabled, or "direct" to always pass image attachments to the Orchestrator.

The eye that reads what others cannot.	Read-only visual analysis - interprets images, screenshots, PDFs, and diagrams. Returns structured observations to the orchestrator without loading raw file bytes into the main context window. Images, screenshots, diagrams → read tool (native image support) PDFs and binary documents → read tool (text + structure extraction) Disabled by default - enable with "disabled_agents": [] and configure a vision-capable model; installing with --preset=opencode-go enables it with opencode-go/mimo-v2.5. Image attachments route to Observer by default when it is enabled; set "image_routing": "direct" to keep them on the Orchestrator.
Prompt: observer.ts
Default Model: openai/gpt-5.6-luna - configure a vision-capable model to enable
Recommended Models: mimo-v2.5 qwen3.5-plus
Model Guidance: Choose a vision-capable model if you want the agent to read screenshots, images, PDFs, and other visual files.

---

🧩 Skills

Skills are prompt-based instructions injected into an agent's system prompt to guide decisions, workflows, and tool use. Unlike MCPs (which are running servers), a skill runs no process — it is a focused playbook an agent activates when the task calls for it. The installer bundles eight skills and keeps them updated on plugin auto-update; local customizations are preserved.

[!TIP] To discard local bundled-skill customizations and receive package updates, run bunx oh-my-opencode-slim install --skills=force. This deliberately replaces installed bundled skills with the package versions.

Skill	Purpose	Default agent	How to invoke
codemap	Hierarchical repository maps so agents understand codebases without re-reading everything	orchestrator	run codemap
deepwork	Structured workflow for large, risky, multi-phase coding sessions with review gates	orchestrator	/deepwork <task>
verification-planning	Plans a project-specific evidence path before non-trivial changes	orchestrator	automatic before non-trivial work
simplify	Behavior-preserving simplification for readability and maintainability	oracle	ask for simplification or during review
worktrees	Git worktrees as safe, isolated coding lanes for risky or parallel work	orchestrator	work in a worktree
clonedeps	Clones dependency source locally so agents can inspect library internals	orchestrator	clone dependencies
reflect	Turns repeated workflow friction into reusable skills, agents, or config	orchestrator	/reflect
oh-my-opencode-slim	Configures and safely improves the plugin setup itself	orchestrator	ask to tune your setup

Skill assignments are permission grants — an agent can only activate skills it has been given. Configure them per agent with the skills array in ~/.config/opencode/oh-my-opencode-slim.json: an explicit list, "*" for everything, or "!skill-name" to deny one.

See Skills for full documentation, or browse the illustrated overview at ohmyopencodeslim.com/skills.

---

🖥️ Companion

The optional Companion is a floating desktop status window for live agent activity. It shows the current session state and which agents are active, so background work is easier to follow at a glance.

During interactive install, the installer asks whether to enable Companion and defaults to no. For automation, enable it explicitly with:

bunx oh-my-opencode-slim@latest install --companion=yes

See Companion for configuration, positions, sizes, and install details.

---

📚 Documentation

Use this section as a map: start with installation, then jump to features, configuration, or example presets depending on what you need.

✨ Features & Workflows

Doc	What it covers
Council	Run multiple models in parallel and synthesize a single answer with @council
Custom Agents	Define your own specialists with custom prompts, models, MCP access, and Orchestrator delegation rules
ACP Agents	Connect external ACP-compatible agents such as Claude Code ACP or Gemini ACP as delegatable subagents
Multiplexer Integration	Watch agents work live in Tmux, Zellij, Herdr, cmux, or kitty panes
Codemap	Generate hierarchical codemaps to understand large codebases faster
Clonedeps	Clone selected dependency source into an ignored local workspace for inspection
Worktrees	Use .slim/worktrees/ lanes for isolated parallel or risky coding work
Preset Switching	Switch agent model presets at runtime with /preset
Interview	Turn rough ideas into a structured markdown spec through a browser-based Q&A flow
Companion	Floating window companion for parsing, help, and types

⚙️ Config & Reference

Doc	What it covers
Installation Guide	Install the plugin, use CLI flags, reset config, and troubleshoot setup
Configuration	Config file locations, JSONC support, prompt overrides, and full option reference
Project Customization	Repository-specific custom agents, prompt overrides, per-agent skills, and precedence
Background Orchestration	Scheduler-first orchestrator model built around native background subagents
Maintainer Guide	Issue triage rules, label meanings, support routing, and repo maintenance workflow
Skills	Bundled skills such as simplify, codemap, clonedeps, deepwork, verification-planning, reflect, worktrees, and oh-my-opencode-slim
MCPs	context7, gh_grep, and how MCP permissions work per agent
Tools	Built-in tool capabilities like webfetch, LSP tools, code search, and formatters

---

🏛️ Contributors

Alvin 💻	alvinreal 💻	imw 💻	Adithya Kozham Burath Bijoy 💻	ReqX 💻	Abhideep Maity 💻
Ruben 💻	Gabriel Rodrigues 💻	John Michael Vincent Bambico 💻	Molt Founders 💻	Muen Yu 💻	NocturnesLK 💻
Riccardo Sallusti 💻	Yan Li 💻	Hoàng Văn Anh Nghĩa 💻	Jacob Myers 💻	Kassie Povinelli 💻	KyleHilliard 💻
j5hjun 💻	marcFernandez 💻	mister-test 💻	n24q02m 💻	oribi 💻	pelidan 💻
xLillium 💻	⁢4.435km/s 💻	Drin 💻	Hakim Zulkufli 💻	Simon Klakegg 💻	Kiwi 💻
Raxxoor 💻	nyanyani 💻	nettee 💻	Link 💻	Bartosz Łaszewski 💻	huilang021x 💻
Dusan Kovacevic 💻	jwcrystal 💻	Nguyen Canh Toan 💻	Thomas Dyar 💻	zero 💻	Denis Balan 💻
Gustavo Caiano 💻	Thomas Mulder 💻	魔王少年(maou shonen) 💻	Jelasin 💻	Hannes 💻	mooozfxs 💻
Luke Hines 💻	m.seomoon 💻	Yolo 💻	XinXing 💻	Ikko Eltociear Ashimine 💻	GWANWOO KIM 💻
Omer Faruk Oruc 💻	Omar Mohamed Khallaf 💻	Knowingthesea_Qesire 💻	FENG Hao 💻	Matheus Nogueira Silveira 💻	sktr 💻
Insomnia 💻	Andres Castañeda 💻	Zaradacht Taifour (Zack) 💻	fslse 💻	萧瑟 💻	Zhi 💻
lilili 💻	Mike Henke 💻	Vinay Pandya 💻	Shank 💻	Robin Gutzen 💻	Yash 💻
Liu Jiajun 💻	Ulises Millán 💻	HighColdHC 💻	Stephan Schielke 💻	Daniel Maly 💻	Chewji 💻
Daniel Maly 💻	Giuseppe Bellamacina 💻	Zhanyuanium 💻	かぜ 💻	Tsanko Tsanev 💻	cyril 💻
Patricio Molina 💻	vinilouz 💻	Homura 💻	Major Hayden 💻	Davide Ladisa 💻	Max-Null 💻
Bruce 💻	zhaohaofan 💻	adevwithpurpose 💻	Gold John King 💻	pxmps 💻	raphaelwdrf 💻
Brant 💻	Erman HAVUÇ 💻	HeZzz 💻

---

📄 License

MIT

---