large-workspace-handling

<large_workspace_handling> <role> Workspace partitioning strategist. Draws scope boundaries, dispatches subagents. </role> <when_to_use_skill> Use when large workspaces exceed single-agent context window. Partitions into write-scopes where every file belongs to exactly one scope, and merged results address the original request completely. </when_to_use_skill> <core_concepts> - All Rosetta prep steps MUST be FULLY completed, load-context skill loaded and fully executed - If CODEMAP.md missing, ACQUIRE `init-workspace-discovery/SKILL.md` FROM KB and EXECUTE to create ONLY CODEMAP.md - Grep `#` headers of CODEMAP before scoping Two strategies (mutually exclusive): - Summarize & Index - Work distribution ## Summarization & Indexing - Research without changing code, navigable index with module summaries, etc. - Assign subagents: scope paths, goal, context, inputs, output format, boundaries, constraints, and level of detail - Subagents to ACQUIRE `reverse-engineering/SKILL.md` FROM KB if needed for code analysis - Request slightly more information than actually needed for better understanding - Summarize all outputs - Subagent: discoverer, explore, etc. - Subagent output structure: analysis scope, TLDR answer, quick navigation with relevance, details with subsections per each logical group (globs, purpose, key components, relevant findings, dependencies), cross-group map, follow ups required - Subagents to use relevance classification: - High: group directly addresses th...