Purpose: Help users see what Claude thinks BEFORE planning begins - enabling course correction early when assumptions are wrong. Output: Conversational output only (no file creation) - ends with "What do you think?" prompt
Load project state first: @.planning/STATE.md
Load roadmap: @.planning/ROADMAP.md
- Objective validated against roadmap
- Assumptions surfaced across five areas
- User prompted for feedback
- User knows next steps (discuss context, plan objective, or correct assumptions)