Cavecrew is an AI Engineering skill for Claude Code, published by JuliusBrussee in caveman.
Cavecrew provides a decision guide for when to spawn caveman-style subagents — investigator, builder, reviewer — to locate code, make small edits, or review diffs, returning compressed output that saves main context. Use it when delegating tasks in Claude Code to reduce token usage.
Cavecrew is cataloged under AI Engineering on DirSkills. Cavecrew comes from a repository tagged ai, anthropic, caveman, claude and claude-code.
Documentation
Cavecrew = three subagent presets that emit caveman output. Same job as Anthropic defaults (Explore, edit-style agents, reviewer); difference is the tool-result they return is compressed, so main context shrinks per delegation.
This is the opening of the README. Read the full README on GitHub.
Cavecrew is one of 20 skills that DirSkills catalogs from JuliusBrussee/caveman, the repository it ships in. Its siblings there include Caveman, Caveman Commit and Caveman Compress. Each one is a separate skill with its own page in this directory, installs the same way Cavecrew does, and is maintained by JuliusBrussee in that same repository. The rest of the collection is listed on the JuliusBrussee/caveman page.
Cavecrew ranks #30 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Cavecrew against them. Open each page to compare what they document and how they install.
Cavecrew is one of 20 skills cataloged on DirSkills from JuliusBrussee/caveman.
Cavecrew is one of 2451 AI Engineering skills cataloged on DirSkills, ranked #30 by stars among them.