OpenCode Masterclass: AI Agents, MCP, Skills & Subagents

Stop paying for expensive AI coding subscriptions. Start building your own AI-powered coding workflow. OpenCode is an open-source, provider-agnostic AI coding agent that runs directly in your terminal.

This practical crash course takes you from your first OpenCode command to building a structured, reusable agentic coding workflow using Slash Commands, Context Management, AGENTS md, MCP, Skills, and Subagents. This is not a course about simply typing prompts and hoping for the best. You’ll learn how to turn OpenCode into a reliable AI development assistant that understands your project, uses external tools, follows your instructions, and delegates specialized work to agentsWhat You’ll BuildThroughout the course, you’ll work with practical, hands-on examples and progressively build your own OpenCode toolkit:Custom Slash Commands to automate repetitive tasks and stop rewriting the same promptsA project-aware AGENTS md file that gives OpenCode persistent instructions about your projectMCP connections to GitHub, databases, and documentation using real hands-on examplesA Data Cleaning Skill for handling real-world data problemsA Data Migration Skill for specialized data workflowsA Dashboard Generation Skill for turning data into visual reportsA custom Code Reviewer Subagent that can automatically review your workA custom Orchestrator Subagent for coordinating specialized tasksWhat You’ll LearnWhat OpenCode is and how agentic coding differs from traditional codingHow the OpenCode agentic loop works internallyHow to set up OpenCode using free models, plus optional paid configurationHow to create and use Slash Commands for repeatable workflowsHow Sessions and Resume work when working across longer tasksHow OpenCode's Context Window works and why context management mattersAuto-compaction and practical techniques for keeping long AI sessions focusedHow to write, test, and maintain an AGENTS md fileWhat MCP (Model Context Protocol) actually is and how it connects OpenCode to external toolsHands-on MCP integrations with GitHub, databases, and Context7MCP Tools, Permissions, and the Allow / Ask / Deny trust modelThe most useful MCP servers developers should know, including Notion, Slack, Jira, AWS, Docker, and FilesystemHow OpenCode Skills work and why they are useful for specialized workflowsSkills architecture, including YAML front matter and Markdown instructionsHow to create your own Data Cleaning, Data Migration, and Dashboard Generation SkillsHow to install Skills from the OpenCode MarketplaceWhat Subagents are and how OpenCode's built-in agents workHow to use the built-in Explore, Plan, and General-Purpose subagentsHow to build your own Custom Subagents for specialized workflowsSkills vs Subagents — when to use each and how they complement one anotherHow to build an Orchestrator Agent that coordinates complex workflowsWho This Course Is ForThis course is designed for developers, data analysts, data scientists, engineers, freelancers, and AI enthusiasts who want to move beyond basic AI prompting and learn how to build practical agentic coding workflows.

It’s especially useful if you want to:Automate repetitive coding and data tasksBuild reusable AI-powered workflowsConnect your coding agent to external tools and dataCreate specialized Skills and SubagentsUnderstand context management and improve AI reliabilityLearn how modern agentic coding systems actually workYou don’t need to be an AI expert. If you’re comfortable working with a terminal and have basic programming knowledge, you can follow along and start building your own OpenCode workflows.