Cavecrew = three subagent presets that emit caveman output. Same job as Anthropic defaults ( , edit-style agents, reviewer); difference is the tool-result they return is compressed, so main context shrinks per delegation. When to use cavecrew vs alternatives | Task | Use | |---|---| | "Where is X defined / what calls Y / list uses of Z" | | | Same but you also want suggestions/architecture commentary | (vanilla) | | Surgical edit, ≤2 files, scope obvious | | | New feature / 3+ files / cross-cutting refactor | Main thread or | | Review diff, branch, or file for bugs | | | Deep code review with…