todo-refine

Refine

Read brain/todos.md and refine unclear items into actionable prompts through targeted questioning.

Workflow

1. Read brain/todos.md and review open items.
2. Triage each item: is it clear enough to act on without further context? A clear item specifies what is wrong, where it happens, and what the fix should be. Skip items that already meet this bar.
3. Ask clarifying questions about unclear items. Group related questions — aim for one round of questions, not a back-and-forth (to minimize back-and-forth and user fatigue). Good clarifying questions target:
   • What — what exactly is the problem or desired behavior?
   • Where — which part of the app, which component, which flow?
   • How — how should it work instead? What does "fixed" look like?
4. Rewrite unclear items in-place, incorporating the user's answers. Each rewritten item should be a self-contained prompt that another agent could act on without additional context.
5. Remove any items the user says are already done or no longer relevant.
6. Report a summary of what changed.