Get started
You need an AI tool that can run commands on your computer, such as Claude Code, Codex, Cursor, or VS Code with GitHub Copilot, and Node.js 22.15 or later. Your AI tool can install Node.js for you. No account is required.
1. Paste one prompt
Create an empty folder for your course, start your AI tool in it, and paste this:
Set up a CourseCode Framework course in this folder. Check that Node.js 22.15 or later is installed and help me install it if it isn't. Then run `npx coursecode@latest create .` and tell me what to do next.
Your AI tool creates the project, installs its dependencies, and initializes Git. The project includes:
- MCP settings for Claude Code, Codex, Cursor, and VS Code, so your AI tool can preview, screenshot, lint, and test the course
- An
AGENTS.mdthat explains the authoring workflow - Workflow skills for outlining, building, reviewing, and publishing (
coursecode-outline,coursecode-build-slides,coursecode-review,coursecode-publish)
2. Restart your AI tool in the folder
AI tools load project settings when they start, so quit yours and start it again in the same folder.
- Claude Code: run
claudein the folder and approve thecoursecodeserver when asked. - Codex: run
codexin the folder and trust it. - Cursor or VS Code: open the folder and enable the
coursecodeserver if your editor asks. - Other MCP clients: configure the client to run
npx -y coursecode mcpfrom the course folder. See MCP setup.
3. Describe your course
Tell your AI tool what you want, for example “build a 20-minute safety course from the PDFs I’m adding to course/references”. It drafts an outline for your approval, builds the slides, and checks each one in a local preview at http://localhost:4173, which you can open to watch the course as it builds.
The project starts with example slides that show what CourseCode can do. Ask your AI tool to remove them when you start your own course.
4. Export or deploy
Ask your AI tool to export the course for your LMS. It builds a ZIP in the project folder:
npx coursecode build --format scorm1.2
Use --format scorm2004, --format cmi5, or --format lti for other targets. LTI 1.3 is an integration rather than a static package and needs a trusted backend for production launches. For SCORM-specific guidance, see SCORM course authoring.
CourseCode Cloud (optional). For hosted delivery, share links, analytics, or licensing, ask your AI tool to deploy the course to CourseCode Cloud, or run:
npx coursecode login
npx coursecode deploy
Cloud generates any LMS format on demand from one upload. Everything above works without it.
Without an AI tool
npx coursecode@latest create my-course
cd my-course
npx coursecode preview
Open http://localhost:4173 to view and edit the example course, which is a complete guide to CourseCode. You can open the folder in an AI tool at any time. For the shorter coursecode command, install the CLI globally with npm install -g coursecode.
Optional: Claude Code and Codex plugin
The plugin runs the CourseCode tools in every folder, so your AI tool can start a course before a project exists. It also adds setup and new-course skills and, in Claude Code, a Node.js check at session start. You don’t need it, because projects already include the tools and skills. Install it from GitHub:
# Claude Code
claude plugin marketplace add course-code-framework/coursecode
claude plugin install coursecode@coursecode
# Codex
codex plugin marketplace add course-code-framework/coursecode
codex plugin add coursecode@coursecode
Then start a new session in an empty folder and describe the course you want. For Codex updates and troubleshooting, see the Codex setup guide.
Next steps
- Framework user guide
- Troubleshooting
- CourseCode Cloud (optional)