kdcokenny/opencode-workspace

Bundled multi-agent orchestration harness for OpenCode. One install, complete control.

What it solves

It provides a comprehensive, pre-configured multi-agent orchestration environment for AI-driven software development. Instead of setting up individual agents and tools manually, it bundles them into a single "harness" that manages the entire workflow from planning and research to coding and review.

How it works

The system uses a hierarchical architecture where high-level Orchestrators (plan and build) delegate tasks to specialized agents. These specialists have strictly defined permission boundaries to ensure security and focus:

  • Researcher: Uses MCP tools for external research (read-only).
  • Coder: Handles implementation with full file and bash access.
  • Scribe: Manages documentation (write access, no bash).
  • Reviewer: Performs code reviews (read-only and git inspection).

This orchestration is supported by a suite of plugins for plan management, async delegation, and Git worktree isolation, as well as MCP servers for web search and GitHub code search.

Who it’s for

Developers using OpenCode V1 who want a turnkey, professional AI development workspace with established protocols for planning, coding philosophy, and quality assurance.

Highlights

  • Complete Toolset: Includes 4 plugins, 3 MCP servers, 4 specialized agents, and 4 skill sets.
  • Strict Permissioning: Implements security boundaries (e.g., denying direct web fetching globally) to control agent capabilities.
  • Specialized Skills: Comes with built-in guidelines for code and frontend philosophy and review methodologies.
  • Integrated Workflow: Features a dedicated /review command and a differential context protocol.

Related

  • Project
    openagents-org/openagents

    An open-source collaborative OS for AI agents that provides a unified workspace where multiple agents can share threads, files, and a browser to work together.

  • Project
    ip2a/mcpstore

    A high-performance MCP management system built with Rust that orchestrates Model Context Protocol services for AI agents and applications.

  • Project
    morpheuslord/HackBot

    An agentic cybersecurity research team that uses multi-agent orchestration and MCP/ACP protocols to analyze security reports and research vulnerabilities.

  • Project
    awslabs/agent-plugins

    A collection of plugins for AI coding agents that provide specialized skills, MCP servers, and workflows to help developers architect, deploy, and operate on AWS.