| name | batch-grill-me |
| description | A relentless interview that asks every frontier question at once, round by round. Invoked by superharness:go for new tasks. |
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.
Questions drawn only from what the plan states or what the user flags as undecided will miss two blind spots that live outside the text:
- Unknown knowns — standards the user holds but never wrote down because they feel obvious; they surface as "that's not what I meant" only after the build. Restate the plan's implicit assumptions as concrete claims for the user to veto now.
- Unknown unknowns — alternatives, risks, and ripple effects the user never considered. Surface what the plan silently excluded.
Work the tree in rounds. The frontier is every decision whose prerequisites are already settled — the questions you can ask now without guessing at answers you haven't heard yet. Ask the whole frontier in one round: number each question and give your recommended answer. Then wait for the user's answers before the next round.
Each question must use this format:
**Q1** - **<question title>**: <question body, which may span multiple paragraphs and include multiple choices>
**Recommended answer:** <your recommended answer>
Each round the user answers reshapes the tree — settled decisions push the frontier outward and unblock questions that depended on them. Recompute the frontier and ask the next round. A question whose answer depends on another question still open in this round belongs to a later round, not this one.
Before composing the first round, read .superharness/spec/learnings/index.md and open any topic page relevant to the requirement. Recorded learnings are settled prerequisites, not questions — do not re-ask what they already answer.
Finding facts is your job, never the user's. When a frontier question needs a fact from the environment (filesystem, tools, etc.), dispatch a sub-agent to find it — don't ask the user for anything you could look up yourself. Don't block on it: a running exploration is an unsettled prerequisite, so only the questions downstream of it wait for the sub-agent to report — ask the rest of the frontier now. 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.
