What problem does it solve? Long coding sessions exhaust the main context window because vanilla subagent results are injected back verbatim as verbose prose. This Skill tells you when to delegate to caveman-compressed subagents so each delegation costs roughly one third the tokens. ## Core Features & Use Cases - Decision matrix: Maps task types (locate code, surgical edit, diff review) to the right subagent — cavecrew-investigator, cavecrew-builder, or cavecrew-reviewer — versus vanilla agents or the main thread. - Output contracts: Defines exact structured formats each subagent returns (path:line findings, change confirmations, severity-tagged review findings) so results are greppable and predictable. - Chaining patterns: Documents locate → fix → verify workflows, parallel investigator scouting, and single-shot edits. - Use Case: During a long refactoring session, spawn cavecrew-investigator to find all call sites of a function, hand the top two paths to cavecrew-builder for the edit, then have cavecrew-reviewer audit the diff — all while keeping main-context usage minimal. ## Quick Start Ask the assistant to delegate code exploration to a cavecrew investigator subagent to save context, for example by saying "use cavecrew to find where this function is defined".
