---
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**: each decision branches into the decisions it unblocks.

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

Build the complete **frontier** before the first question.
After each answer, recompute and display every frontier decision.

Ask one frontier decision per turn.
A clarification leaves that decision open.

Format a question like so:

```
❓ **D1 — <decision title>**: <question body, might be multiple paragraphs, including multiple choices>

**Options**

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

---

❓ **D2 — <decision 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.

Before asking the next question, account for every decision that the response settles.
Record preferences as constraints.
Settle an implementation decision only after facts establish that it is viable.
A decision with unresolved prerequisites belongs outside the frontier.

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. Present every settled decision from the design tree. Do not act on it until the user confirms you have reached a shared understanding.