cavecrew
Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".
- License 许可
- MIT
- 所属仓库
- Wifabric/AISC
- 最近更新
- 2026-11-09
- Stars
- ★ 7
- Forks
- 0
01 前言 Front Matter
- name
- cavecrew
- description
- Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".
03 SKILL.md 正文
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:
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.
04 同仓库更多 Skills
topic-workshop
围绕用户选定的主题,把资料、沟通、实践与反馈沉淀为可执行的主题手册,并记录迭代依据。用于建立或接续长期主题工作、从实践完善手册、分析流程改进;单次问答、纯文件摘要和普通代码修改不自动启动本流程。
aisc-development
推进 AISC 已确认版本的功能开发、Issue 修复、贡献者 PR 集成与统一 Preview 交付。用于本仓库开发协作,不用于平台内安装扩展技能或替用户批准产品与正式发布。
karpathy-guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
grilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
grill-me
A relentless one-question-at-a-time interview to sharpen a plan, decision, or design.
document-skills
Create and edit documents, spreadsheets, presentations, PDFs, and other business artifacts using the bundled Anthropic document skills.