screenshot-critique

# Screenshot Critique Use an unprimed sub-agent as a second set of eyes before accepting visual work. This is for visual defects, not pixel metrics; pair it with `compare-screenshots` when you also need numbers. ## Workflow 1. Capture or locate the exact PNGs/GIF frames under review. 2. Create tight 2x-4x crops for every key feature under judgment, plus the full screenshot for context. Crop selected units, city/town stacks, flags/poles, shadows, selection rings, labels/icons, roads, terrain features, water, and any artifact-prone area. If the complaint is about "too faint", "wrong order", or "not in perspective", the crop is mandatory. 3. Spawn one fresh explorer with `fork_context: false`; pass only the full images, the crops, and a short neutral task. Do not include the main thread history, implementation details, or expected answer. 4. Ask for concrete visible defects with confidence levels. Name likely risk categories: unit/prop depth ordering, layering, shadows, selection-marker contrast, ground-plane perspective, flag/pole attachment, label style and icon readability, blur, scale, lighting, artifacts, missing models, terrain feature readability, roads, water, and overall scan readability. 5. Compare the sub-agent's critique against your own inspection. Treat overlap as high-priority evidence. Treat novel high-confidence findings as bugs to inspect, not as taste notes to dismiss. 6. Record actionable findings in the spec, visual rep...