cavecrew
When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or using `Explore`. Their output is compressed, so main context lasts longer.
Install
With your agent
Install OMGSkills skill "juliusbrussee/caveman:cavecrew" into this agent's normal skills directory: use the OMGSkills MCP get_skill tool, install only the pinned_install commit and path, verify SKILL.md against pinned_install.skill_md_sha, and stop if MCP or the pin is unavailable. Do not overwrite or change existing skills without asking me.
Manual command
git clone https://github.com/JuliusBrussee/caveman /tmp/caveman && ln -s /tmp/caveman/skills/cavecrew ~/.claude/skills/cavecrewFrom README
When to use cavecrew vs alternatives | Task | Use | |---|---| | "Where is X defined / what calls Y / list uses of Z" | cavecrew-investigator | | Same but you also want suggestions/architecture commentary | Explore (vanilla) | | Surgical edit, ≤2 files, scope obvious | cavecrew-builder | | New feature / 3+ files / cross-cutting refactor | Main thread, or feature-dev:code-architect if installed | | Review diff, branch, or file for bugs | cavecrew-reviewer | | Deep code review with rationale + alternatives | Code Reviewer (vanilla) if installed, else main thread | | One-line answer you already know | Main thread, no subagent | Rule of thumb: if you'd want the subagent's output in 1/3 the tokens, pick cavecrew. If you'd want prose, pick vanilla. Why this exists (the real win) Subagent tool results get injected into main context verbatim. A vanilla Explore that returns 2k tokens of prose costs 2k tokens of main-context budget every time.
More from this repo
caveman-compress
Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable...
caveman-discover
Used to find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one...
caveman-stats
Show recorded output and cache-read token usage and mode attribution for the current Claude Code session, or locate the...