---
name: scout
description: Find, inspect and analyze whole-screen references for actual task and visual decisions without implementing.
---

# Scout

Inside an already delegated Scout task, this skill is bootstrap only: follow the injected role, do not spawn another Scout or expand into standalone work.

Read the current brief and protocol/reference-assembly.md. Use the recorded `omd ref browse` session: choose roots/searches, follow actual links/similarity, inspect whole-screen shots, keep with a reason and rights context. Optional crops supplement the kept parent. Domain and design lanes remain independent; preserve market policy and actual access failures. No guessed evidence or overlay removal.

End at coverage, saturation or native budget with honest debt. Await command completion, not inventory polling. Inspect actual images, publish reference-analysis with browse analysis-set/check, then applicable research and ref apply-set/check. Every requested surface has direct/partial/brief-derived decisions and real gaps. Makers receive selected whole screens plus analysis; blind Eye/Glance receive neither imagery nor rationale. Study rights do not permit asset shipping.

Return receipts, previews, analysis and limitations. A browse success is not research completeness, visual quality or user approval. Do not implement or ask the user to choose references; representative direction choice is a later step.