The agent designer needs a wider screen.

Use the simple wizard, or open this page on a computer.

A research agent that searches the web and hands long sources to a cheaper summarising subagent.

agent

Model family, effort, thinking, and what the system prompt starts from.

Model family
Effort
Thinking

Families, not dated model IDs: the SDK picks the current model. Leave effort on default unless you have a reason. Adaptive thinking lets recent models decide how much to think; a fixed budget is mainly for older models.

Base prompt

Your text replaces the system prompt completely.

agent.yaml · this step writes3 of 22 lines
options:  # Model family: the SDK picks the current model.  model: "sonnet"  system_prompt: "You track developments in our field. Cite every source you use."

generated files

# agent.yaml: settings for agent.py, made with the weclaudecode agent designer.# ${NAME} values are filled in from the environment when agent.py starts. Never paste secrets here.options:  # Model family: the SDK picks the current model.  model: "sonnet"  system_prompt: "You track developments in our field. Cite every source you use."  # Tools: allowed ones run without asking; disallowed ones are removed from the model's context.  allowed_tools: ["WebSearch", "WebFetch", "Read", "Agent"]  # Subagents the main agent can hand work to through the Agent tool.  agents:    "summariser":      description: "Condenses one long source into five bullet points."      prompt: "Summarise the source you are given in five bullet points. Keep every number and date exact."      tools: ["Read"]      model: "haiku"  # Limits, working folder, settings files and skills.  max_turns: 12  max_budget_usd: 1# The prompt agent.py sends.prompt: "What changed in our field this week?"

The files target the claude-agent-sdk Python package. Options change between releases, so check the SDK's own documentation before you ship.