---
name: grill
description: Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
---

Interview the user relentlessly until you reach a shared understanding. Map this as a **design tree**: every decision branches into the decisions that hang off it.

Maintain the design tree in a new Markdown file. Use the file as the source of truth.

Work the tree one question at a time. The **frontier** is every decision whose prerequisites are already settled: the questions you can ask now without guessing at answers you have not heard yet. Record the next frontier question in the file, then ask it and wait for the user's answer.

Format a question like so:

```
❓ **Q1** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>

**Options**

1. <option>
...
<n>. **<recommended option>** — recommended

---

❓ **Q2** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>

**Options**

1. <option>
...
<n>. **<recommended option>** — recommended
```

List every viable answer in an ordered list and mark your recommended answer.
Word each question so "yes" accepts your recommended answer.

Each user answer reshapes the tree: settled decisions push the frontier outward and unblock questions that depended on them. Recompute the frontier in the file and ask the next question. A question whose answer depends on another open question belongs later, not next.

Finding _facts_ is your job, never the user's. When a frontier question needs a fact from the environment (filesystem, tools, etc.), find it with available tools; don't ask the user for anything you could look up yourself. The _decisions_ are the user's: put each to them and wait.

The session is done when the frontier is empty: every branch of the design tree visited, nothing left silently assumed. Do not act on it until the user confirms you have reached a shared understanding.