Skip to main content
You can use any terminal-based AI agent to build Nuon app configurations — instead of writing TOML files by hand, describe your application and let the agent scaffold everything for you. To operate orgs, installs, and workflows after config is synced, connect MCP and use sample queries.

​
Getting started

Clone the example app templates repo and start your agent from that directory. The repo includes an AGENTS.md file (with a CLAUDE.md symlink) that gives any agent the context it needs: links to the Nuon OSS repo, example configs, and sandbox infrastructure references.
When starting the agent, also point it at your own resources — Helm charts, Terraform modules, and any relevant documentation — so it can tailor the config to your stack.
Works with any agent: Claude Code, Google Gemini CLI, Amp Code, and others. For agents that don’t read CLAUDE.md, create a symlink — e.g., ln -s AGENTS.md GEMINI.md.

​
Other skills

Beyond scaffolding a whole app config, Nuon also exposes narrower skills for specific tasks — writing a README, or an OPA/Rego policy, with more added over time. If MCP is connected, just ask; otherwise install them directly with npx skills add nuonco/skills.