Launch a new agent to handle complex, multi-step tasks autonomously. Each agent type has specific capabilities and tools available to it.

Available agent types and the tools they have access to:
{{typeList}}

Custom agents can be defined in .pi/agents/<name>.md (project) or {{agentDir}}/agents/<name>.md (global) — they are picked up automatically. Project-level agents override global ones. Creating a .md file with the same name as a default agent overrides it.

When using the Agent tool, specify a subagent_type parameter to select which agent type to use.

## When not to use

If the target is already known, use a direct tool — `read` for a known path, `grep`/`find` for a specific symbol or string. Reserve this tool for open-ended questions that span the codebase, or tasks that match an available agent type.

## Usage notes

- Always include a short (3-5 word) description summarizing what the agent will do (shown in UI).
- When you launch multiple agents for genuinely disjoint work, send them in a single message with multiple tool uses, with run_in_background: true on each, so they run concurrently. If the user specifies that they want agents run "in parallel", you MUST send a single message with multiple tool calls. Foreground calls run sequentially — only one executes at a time.
- When the agent is done, it returns a single message back to you. The result is not visible to the user — to show the user, send a text message with a concise summary.
- Foreground vs background: if the result is a prerequisite for your next read, edit, or decision, use foreground (default). Use background only when you have genuinely disjoint work to do in parallel.
- Background completion is delivered automatically — do NOT poll or sleep waiting for it. While it runs, do not repeat the agent's evidence collection or otherwise duplicate its work. A completion notice cannot retract sibling tools already issued in the same assistant turn.
- You retain responsibility for synthesis, decisions, and final verification. After the report arrives, verify only high-risk claims with targeted checks; do not rerun the agent's full grep/find/read evidence collection.
- Use resume with an agent ID to continue a previous agent's work. A new (non-resume) Agent call starts a fresh agent with no memory of prior runs, so the prompt must be self-contained.
- Use steer_subagent to send mid-run messages to a running background agent.
- Clearly tell the agent whether you expect it to write code or just to do research (search, file reads, etc.), since it is not aware of the user's intent.
- If an agent's description says it should be used proactively, try to use it without the user having to ask for it first.
- Use model to specify a different model (as "provider/modelId", or fuzzy e.g. "haiku", "sonnet").
- Use thinking to control extended thinking level.
- Use inherit_context if the agent needs the parent conversation history.
- Use isolation: "worktree" to run the agent in an isolated git worktree (safe parallel file modifications). The worktree is automatically cleaned up if the agent makes no changes; otherwise the path and branch are returned in the result.{{scheduleGuideline}}

## Writing the prompt

Provide clear, detailed prompts so the agent can work autonomously. Brief it like a smart colleague who just walked into the room — it hasn't seen this conversation, doesn't know what you've tried, doesn't understand why this task matters.
- Explain what you're trying to accomplish and why.
- Describe what you've already learned or ruled out.
- Give enough context about the surrounding problem that the agent can make judgment calls rather than just following a narrow instruction.
- If you need a short response, say so ("report in under 200 words").
- Lookups: hand over the exact command. Investigations: hand over the question — prescribed steps become dead weight when the premise is wrong.

Terse command-style prompts produce shallow, generic work.

**Never delegate understanding.** Don't write "based on your findings, fix the bug" or "based on the research, implement it." Those phrases push synthesis onto the agent instead of doing it yourself. Write prompts that prove you understood: include file paths, line numbers, what specifically to change. Retaining understanding does not mean repeating evidence collection; synthesize the report and use only targeted verification.