Hugging Face · Course
Context Course
The Hugging Face Context Course teaches context engineering for AI code agents: structuring knowledge so an agent finds what it needs when it needs it. Across six units you build skills, MCP tools, plugins, sub-agents and hooks, and study a minimal agent loop.
Who it suits
- Developers who use code agents such as Claude Code, Codex or OpenCode and want better results from them.
- People who want to build portable agent skills and MCP integrations.
What it covers
- Agent skills: what they are, how to build and share them and how agents load them.
- The Model Context Protocol: connecting tools and APIs to agents.
- Plugins, sub-agents and hooks for observing, blocking and automating the agent lifecycle.
- A bonus unit that builds a minimal agent loop from scratch.
Common questions about Context Course
- What do I need first?
- Hugging Face lists Python basics, command-line comfort, a Hugging Face account and at least one code agent installed and configured.
- Which agents does it use?
- Claude Code, Codex and OpenCode as reference agents; Hugging Face says Cursor and GitHub Copilot work with the same ideas but are not covered step by step.
- How many units?
- Six core units plus onboarding, per the course page.
More like this
Keep learning on Infrato
- Path: AI for software developers
- More from Hugging Face: all Hugging Face listings in the directory
- Explore all AI courses
Where this comes from
Written from Hugging Face’s own pages, read on 2026-10-14. Content, prices and availability change, so the provider’s page is the source. We are not affiliated with Hugging Face and this is not an endorsement.