Oh My Opencode Medium

---

Forked from alvinunreal/oh-my-opencode-slim and independently maintained by SamWang32191. Issues for this fork should be filed at SamWang32191/oh-my-opencode-medium.

---

Migration from oh-my-opencode-slim

If you were using oh-my-opencode-slim:

1. Package name changed: Use oh-my-opencode-medium for installation
2. Reinstall the plugin: Re-run the installer with the new package name
3. Rename your config files:
   • ~/.config/opencode/oh-my-opencode-slim.json → ~/.config/opencode/oh-my-opencode-medium.json (or .jsonc)
   • ~/.config/opencode/oh-my-opencode-slim.jsonc → ~/.config/opencode/oh-my-opencode-medium.jsonc
   • .opencode/oh-my-opencode-slim.json → .opencode/oh-my-opencode-medium.json (or .jsonc)
   • Project-local prompt directories also need renaming

The installer no longer auto-reads old slim config files—manual renaming is required.

---

📦 Installation

Quick Start

bunx oh-my-opencode-medium@latest install

The installer generates an OpenAI configuration by default (using gpt-5.4 and gpt-5.4-mini). No provider questions asked.

For non-interactive mode:

bunx oh-my-opencode-medium@latest install --no-tui --tmux=no --skills=yes

To force overwrite of an existing configuration:

bunx oh-my-opencode-slim@latest install --reset

For Alternative Providers

The default configuration uses OpenAI. To use Kimi, GitHub Copilot, or ZAI Coding Plan, see Provider Configurations for step-by-step instructions and config examples.

JSON Schema

An official JSON Schema is included in the package for editor validation and autocomplete. Add a $schema reference to your config file:

{
  "$schema": "https://unpkg.com/oh-my-opencode-medium@latest/oh-my-opencode-medium.schema.json",
  // your config...
}

This enables autocomplete and inline validation in VS Code, Neovim, and other editors that support JSON Schema.

Hash-Anchored Editing

The hashline workflow is enabled by default. Add this to your project config only if you want to disable it:

{
  "hashline_edit": false
}

When enabled, read output is rewritten to include stable LINE#ID anchors:

11#VK| function hello() {
22#XJ|   return 'world';
33#MB| }

Use the feature as a read -> edit -> re-read loop:

1. Run read and copy the current LINE#ID anchors.
2. Run edit using those anchors instead of reproducing surrounding text.
3. Re-run read and use the new anchors for the next change.

If the file changed after the last read, the edit is rejected and the tool returns fresh >>> LINE#ID recovery snippets so the agent can retry against the current file instead of applying a stale edit.

Skill Slash Commands

Discovered skills are converted into slash commands by default. Add this only if you want to keep installed skills available on disk without auto-registering their slash commands:

{
  "skill_slash_command_conversion": false
}

This disables only skill-backed slash command generation. Built-in commands such as /handoff and any commands you define directly in OpenCode config still stay registered.

For LLM Agents

Paste this into any coding agent:

Install and configure by following the instructions here:
https://raw.githubusercontent.com/SamWang32191/oh-my-opencode-medium/medium/README.md

Detailed installation guide: docs/installation.md

Additional guides:

• Provider Configurations - Config examples for all supported providers
• Tmux Integration - Real-time agent monitoring with tmux Quick Reference - Config, fallback behavior, skills, MCPs

Built-in command: use /handoff to generate a phase-1 continuation brief from the current conversation context plus git context when available. In this first iteration, it does not transfer session history or todo state (and it still works without git context).

✅ 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-5.4
Recommended Models: openai/gpt-5.4 anthropic/claude-opus-4.6

---

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-5.4-mini
Recommended Models: cerebras/zai-glm-4.7 fireworks-ai/accounts/fireworks/routers/kimi-k2p5-turbo openai/gpt-5.4-mini

---

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-5.4 (high)
Recommended Models: openai/gpt-5.4 (high) google/gemini-3.1-pro-preview (high)

---

Council: The Chorus of Minds

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 places them before a master who 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 — council master + councillors are chosen from your configured preset
Recommended Setup: Strong master + diverse councillors across providers

---

04. 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-5.4-mini
Recommended Models: cerebras/zai-glm-4.7 fireworks-ai/accounts/fireworks/routers/kimi-k2p5-turbo openai/gpt-5.4-mini

---

05. 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-5.4-mini
Recommended Models: google/gemini-3.1-pro-preview kimi-for-coding/k2p5

---

06. 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-5.4-mini
Recommended Models: cerebras/zai-glm-4.7 fireworks-ai/accounts/fireworks/routers/kimi-k2p5-turbo openai/gpt-5.4-mini

---

📚 Documentation

🚀 Getting Started

Doc	Contents
Installation Guide	CLI flags, --reset, auth, troubleshooting
Provider Configurations	OpenAI, Kimi, Copilot, ZAI, Fireworks AI — mixing providers, fallback chains

✨ Features

Feature	Doc	What it does
Council	council.md	Run N models in parallel, synthesize one answer (@council)
Tmux Integration	tmux-integration.md	Watch agents work in real-time with auto-spawned panes
Cartography Skill	cartography.md	Auto-generate hierarchical codemaps for any codebase

⚙️ Config & Reference

Doc	Contents
Skills	simplify, agent-browser, cartography — assignment syntax
MCPs	websearch, context7, grep_app — permissions per agent
Tools	Background tasks, LSP, code search, formatters
Configuration	Config files, prompt overriding, JSONC, full option reference

💡 Author's Setup

Doc	Contents
Author's Preset	The exact config the author runs daily — OpenAI + Fireworks AI + GitHub Copilot

---

🏛️ 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 💻

---

📄 License

MIT

---