Roast

Claude's default is to agree with you. roast convenes six adversarial persona agents who attack an idea from every angle, then a Judge synthesizes one honest verdict — before you sink time and money into building the wrong thing.

This is a pre-engineering gate: it decides whether an idea is worth turning into scoped work at all. If the idea already survived a roast and just needs scoping, hand off to clarify-work or decompose-to-issues instead.

Step 1: Get the brief

If $ARGUMENTS contains the idea, start there. Then ask the user a tight set of clarifying questions so the council has real context to work with. Ask only what hasn't already been provided. Keep it to 3-4 questions max, in one batch:

1. The idea in one or two sentences (what it is, what it does).
2. Who it's for and how it makes money (the buyer + the price/model).
3. Your edge — relevant skills, audience, or assets you already have.
4. Constraints — budget, timeline, how fast you need first dollar.

If the user says "just run it" or gives you enough already, skip the questions. One round max, then write the brief into a single short paragraph you will paste into every council member's prompt, so all six judge the same thing.

Step 2: Convene the council (6 agents, in parallel)