Prompt capture
Agent tool description
10 model strings share this prompt. 1 line differs between them; everything else is identical.
1Launch a new agent to handle complex, multi-step tasks. Each agent type has specific capabilities and tools available to it.
3Available agent types are listed in <system-reminder> messages in the conversation.
5When using the Agent tool, specify a subagent_type parameter to select which agent type to use. If omitted, the general-purpose agent is used.
7## When to use
9For a single-fact lookup where you already know the file, symbol, or value, search directly. Once you've delegated a search, don't also run it yourself — wait for the result.1
claude-fable-5, claude-mythos-5, claude-opus-4-8, defaultReach for this when the task matches an available agent type, when you have independent work to run in parallel, or when answering would mean reading across several files — delegate it and you keep the conclusion, not the file dumps. For a single-fact lookup where you already know the file, symbol, or value, search directly. Once you've delegated a search, don't also run it yourself — wait for the result.
11- The agent's final report is not shown to the user — relay what matters.
12- Use SendMessage with the agent's ID or name to continue a previously spawned agent with its context intact; a new Agent call starts fresh.
13- Each agent type's model, reasoning effort, and tools come from its definition (`.claude/agents/*.md` frontmatter or SDK `agents`).
14- `isolation: "worktree"` gives the agent its own git worktree (auto-cleaned if unchanged).
15- Subagents run in the background by default; you'll be notified when one completes. Pass `run_in_background: false` only when your very next action depends on the result and nothing else could usefully happen while it runs — otherwise background it so the user can interject. Never fabricate or predict a pending agent's results — the notification is never something you write yourself; if the user asks before it arrives, say it's still running.