Skip to main content
Next we’re going to create a new agent using Claude Code. Because you’re running a unified platform (i.e. code, data and logs live in one place), coding agents can manage it end-to-end. The codebase ships five skills that cover the full agent development lifecycle. Let’s try /create-new-agent.

​
Run the skill

Open Claude Code (or your fav coding agent) in your agent-platform directory and run:
Claude will ask a few questions and build your agent out. Once the spec is locked in, Claude generates agents/<slug>.py, registers it in app/main.py, adds quick prompts to app/config.yaml, restarts the container, and smoke-tests it live.

​
Test your agents on the AgentOS UI

Open os.agno.com, select your new agent in the sidebar, and try a few prompts:
  • The golden path. What you built the agent for.
  • Edge cases. Unusual inputs, ambiguous questions, partial information.
  • Adversarial inputs. Prompt injection, out-of-scope requests, attempts to make it do something it shouldn’t.

​
Do it manually

The /create-new-agent skill automated the agent creation process. To do it manually:
  • Create a file in agents/<slug>.py.
  • Register the agent in app/main.py.
  • Add quick-start prompts in app/config.yaml.

​
Next

Improve the agent →