Skip to content

From Zero to Multi-Agent Engineer with OpenCode

Learn OpenCode from first terminal session to confident multi-agent workflows. This hands-on, comprehensive course is designed for complete beginners who want a practical path into AI-assisted engineering.

By the end, you will be able to:

  • Use OpenCode's Plan and Build agents with good judgment.
  • Write reusable commands, skills, and custom agents.
  • Run multi-agent workflows with clear handoffs.
  • Connect MCP servers and plugins safely.
  • Evaluate, harden, and version agent workflows for real team use.
  • Complete a capstone multi-agent PR-review pipeline.

Start Here

Begin with Module 1 — What Is This World?.

Follow the course in order:

  1. Read the lesson.
  2. Complete each lab before moving on.
  3. Finish the reflection so the workflow becomes your own.

If you are new to the terminal, that is expected. Module 1 starts there.

Get The Course Files

The lessons are readable on the website, but the labs use local sample repos from the course repository. Before the first lab, clone or download the course files:

git clone <course-repo-url> opencode-course
cd opencode-course

Use the course repo as the source of fixtures. When a lab asks you to edit a sample repo, copy it into ~/opencode-labs/ so your experiments do not modify the course package itself.

What You Need

You do not need prior experience with AI coding tools, agent loops, or command-line development.

You will need:

  • A computer running macOS, Linux, or Windows with WSL2.
  • An internet connection.
  • A free OpenCode Zen account (sign up at opencode.ai/auth).

Zen free models are sufficient for the entire course. Upgrade to OpenCode Go only if you want premium models for advanced modules.

Course Map

Phase Modules What you learn
Foundations 1-2 AI and LLM mental models, terminal basics, git basics, OpenCode setup, and your first agent session
Core Mastery 3-6 Plan vs. Build judgment, custom commands, reusable skills, and custom agents
Advanced + Capstone 7-10 Multi-agent workflows, MCP and plugins, production safety, evals, and the final capstone

Module Path

Module Focus Start
Module 1 AI, agents, terminal, and git foundations Lesson
Module 2 Installing OpenCode and running the first task Lesson
Module 3 Plan mode, Build mode, and safe execution judgment Lesson
Module 4 Custom slash commands for repeated workflows Lesson
Module 5 Skills as reusable on-demand knowledge Lesson
Module 6 Custom agents and permission boundaries Lesson
Module 7 Multi-agent workflows and handoff contracts Lesson
Module 8 MCP servers, plugins, and external capabilities Lesson
Module 9 Production practices, evals, cost, context, and secrets Lesson
Module 10 Capstone multi-agent PR-review pipeline Spec

How Each Module Works

Each module follows the same rhythm:

  • Concept: learn one new primitive or judgment pattern.
  • Demo: watch the workflow in a realistic setting.
  • Lab: practice in a real repo or course exercise.
  • Reflection: write down what worked, what failed, and how you will apply it.

The course introduces one major primitive per module so the pieces stack cleanly.

Quick References

Keep these open while you work:

For Instructors And Authors

Instructors should read PLAN.md first, then use instructor-guide/pacing.md for pacing, common failure modes, and grading support.

Authors should treat PLAN.md as the course design contract. Module content has its own review workflow, so update lesson and lab files intentionally.

Repository Layout

modules/module-XX-<name>/  Lessons, labs, and reflections
labs/                      Sample repos used across multiple labs
instructor-guide/          Pacing notes, failure modes, and rubrics
reference/                 Glossary, cheat sheet, and prompt patterns
PLAN.md                    Course design contract and curriculum rationale

Site Status

All course modules are currently marked status: done.

This learner site is published at opencode-course.pages.dev. GitHub Actions builds the MkDocs site and deploys it to Cloudflare Pages on pushes to master. Required Cloudflare deployment secrets are configured in GitHub Actions.