cavecrew
We need to translate the given text from English to Korean. The text describes a decision guide for delegating to caveman-style subagents. It mentions specific names: cavecrew-investigator, cavecrew-builder, cavecrew-reviewer, and cavecrew. Also mentions "Explore" (likely a tool or function). The instruction says to preserve product names, protocol names, URLs, numbers, and technical terms. So we keep "cavecrew", "cavecrew-investigator", "cavecrew-builder", "cavecrew-reviewer", "Explore", "~60%", and "delegate to subagent", "use cavecrew", "spawn..." as is. The rest should be translated naturally. We need to output only the translated text, no extra commentary or labels. The source text is inside <text> tags, but we only output the translation. Let's translate: "Decision guide for delegating to caveman-style subagents." -> "원시인 스타일의 하위 에이전트에 위임하기 위한 결정 가
npx skills add https://github.com/juliusbrussee/caveman --skill cavecrewCavecrew = 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:
cavecrew-investigator
<Header>:
- path:line — `symbol` — short note
totals: <counts>.
Or No match. Always file-path-first, line-number-attached, backticked symbols. Safe to grep with path:\d+.
cavecrew-builder
<path:line-range> — <change ≤10 words>.
verified: <re-read OK | mismatch @ path:line>.
Or one of: too-big. / needs-confirm. / ambiguous. / regressed. (terminal first token).
cavecrew-reviewer
path:line: <emoji> <severity>: <problem>. <fix>.
totals: N🔴 N🟡 N🔵 N❓
Or No issues. Findings sorted file → line ascending.
Chaining patterns
Locate → fix → verify (most common):
cavecrew-investigatorreturns site list.- Main thread picks 1-2 sites, hands paths to
cavecrew-builder. cavecrew-revieweraudits the diff.
Parallel scout (when investigation is broad):
Spawn 2-3 cavecrew-investigator calls in one message (different angles: defs vs callers vs tests). Aggregate in main thread.
Single-shot edit (when site is already known):
Skip investigator. Hand exact path:line to cavecrew-builder directly.
What NOT to do
- Don't use
cavecrew-builderwhen you don't already know the file. Spawn investigator first or main thread will eat tokens passing context. - Don't chain
cavecrew-investigator → cavecrew-builderfor a 5-file refactor. Builder will returntoo-big.and you'll have wasted a turn. - Don't ask
cavecrew-reviewerfor "general feedback" — it returns findings only, no architecture opinions. UseCode Reviewerfor that. - Don't expect prose. Cavecrew output is structured, sometimes terse to the point of cryptic. If a human will read it directly, paraphrase.
Auto-clarity (inherited)
Subagents drop caveman → normal English for security warnings, irreversible-action confirmations, and any output where fragment ambiguity could be misread. Resume caveman after.