claudegoodies
Skill

cavecrew

From JuliusBrussee

>

Guides when to delegate to cavecrew-investigator/builder/reviewer subagents that return caveman-compressed, token-cheap output instead of prose.

Use it when

  • Locating symbols/callers across a codebase without burning main context on prose
  • Making a surgical edit to 1-2 files with an already-known scope
  • Reviewing a diff/branch/file for bugs with terse findings
  • Running many delegations in one session where context budget matters

Skip it if

  • You want prose, architecture commentary, or rationale (use vanilla Explore/Code Reviewer)
  • Task is a 3+ file refactor or new feature — builder returns 'too-big.'
  • You need general/subjective feedback, not just structured findings
  • Output will be read directly by a human — cavecrew is terse to the point of cryptic

Facts

Repository
JuliusBrussee/caveman
Status
Actively maintained
Last commit
Source file
plugins/caveman/skills/cavecrew/SKILL.md

Source preview

The instructions Claude Code reads when this skill runs.

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.

## 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` |
| Review diff, branch, or file for bugs | `cavecrew-reviewer` |
| Deep code review with rationale + alternatives | `Code Reviewer` (vanilla) |
| 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. The same finding from `cavecrew-investigator` returns ~700 tokens. Across 20 delegations in one session that's the difference between context exhaustion and finishing the task.

## Output contracts

What main thread can rely on per agent:
View full source on GitHub →

Other skills