This is your complete reference for wiring up the Agentica SDK to use Claude CLI as the inference backend through a local proxy. You'll need three terminals running a specific stack: Claude proxy on 8080, agentica-server on 2345, and your agent script pointing at the server. The architecture is straightforward but the environment variables trip people up constantly because the SDK connects to the server and the server connects to the proxy, not the other way around. The skill documents the exact startup sequence, common connection errors, and why your agent might hallucinate success instead of actually using its Read/Write tools. If you're debugging why your Agentica agent can't talk to Claude or keeps describing actions instead of executing them, start here.
npx skills add https://github.com/parcadei/continuous-claude-v3 --skill agentica-server