Ultra-compressed communication mode. Cuts 65% of output tokens (measured) while keeping full technical accuracy by speaking like a caveman.
/plugin install caveman@datou-market/plugin marketplace add https://github.com/Garretqaq/plugins-marketDecision guide. When to delegate to caveman subagents instead of doing the work inline.
Tells the main thread when to spawn a caveman-style subagent versus the vanilla equivalent. The win: subagent tool-results inject back into main context verbatim, and caveman output is roughly 1/3 the size of vanilla prose. Across 20 delegations in one session, that is the difference between context exhaustion and finishing the task.
Three subagents:
| Subagent | Job | Use when |
|---|---|---|
cavecrew-investigator | Locate code (read-only) | "Where is X defined / what calls Y / list uses of Z" |
cavecrew-builder | Surgical edit, 1-2 files | Scope is obvious, ≤2 files. Refuses 3+ file scope. |
cavecrew-reviewer | Diff/file review | One-line findings with severity emoji |
Use vanilla Explore or Code Reviewer when you want prose, architecture commentary, or rationale. Use main thread directly for one-line answers and 3+ file refactors.
This skill is a decision guide, not a slash command. It activates when the conversation mentions delegation.
Triggers on phrases like "delegate to subagent", "use cavecrew", "spawn investigator", "save context", "compressed agent output".
Locate → fix → verify (most common):
cavecrew-investigator returns site list (path:line — symbol — note)cavecrew-buildercavecrew-reviewer audits the resulting diffParallel scout: spawn 2-3 cavecrew-investigator calls in one message with different angles (defs, callers, tests). Aggregate in main.
By default, cavecrew-reviewer and cavecrew-investigator pin model: haiku in their frontmatter; cavecrew-builder has no model: line (uses the API session default). Set env vars in your shell before launching Claude Code to override per-agent:
| Env var | Agent |
|---|---|
CAVECREW_REVIEWER_MODEL | cavecrew-reviewer |
CAVECREW_BUILDER_MODEL | cavecrew-builder |
CAVECREW_INVESTIGATOR_MODEL | cavecrew-investigator |
Example — run reviewer on sonnet, keep others on default:
export CAVECREW_REVIEWER_MODEL=sonnet
Use the same model name strings you'd use in any Claude Code agent frontmatter (e.g. haiku, sonnet, opus).
Overrides patch only the model: line in the installed agent's frontmatter; the prompt body is untouched and keeps receiving upstream updates. Plugin installs only — standalone hook installs have no local agent files to patch. Unset or blank = no change. The patch persists in the installed file until the plugin is updated or reinstalled.
SKILL.md — full decision matrix and output contractsagents/cavecrew-investigator.mdagents/cavecrew-builder.mdagents/cavecrew-reviewer.md