AugmentClaude
BackendDevOps

Cavecrew

By JuliusBrussee· JuliusBrussee/caveman· 0

Delegate code tasks to compressed subagents that save context space.

Installation

  1. Make sure Claude is on your device and in your terminal.

    Skills load from ~/.claude/skills/ when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then run claude in any terminal to verify.

    One-time setup
    npm i -g @anthropic-ai/claude-code

    Already have it? Skip ahead.

  2. Paste into Claude Code or into your terminal.
    Install
    Sign up to copy
    Sign up free to reveal

    This copies the whole skill folder into ~/.claude/skills/cavecrew-juliusbrussee/ — the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.

    Faster alternative (instruction-only skills)

    Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.

    Quick install (SKILL.md only)
    Sign up to copy
    Sign up free to reveal
  3. Restart Claude Code.

    Quit and reopen Claude Code (or any other agent that loads from ~/.claude/skills/). New skills are picked up on startup.

  4. Just ask Claude.

    Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.

Prefer to read the source first? Open on GitHub.

When Claude uses it

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".

What this skill does

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

TaskUse
"Where is X defined / what calls Y / list uses of Z"cavecrew-investigator
Same but you also want suggestions/architecture commentaryExplore (vanilla)
Surgical edit, ≤2 files, scope obviouscavecrew-builder
New feature / 3+ files / cross-cutting refactorMain thread or feature-dev:code-architect
Review diff, branch, or file for bugscavecrew-reviewer
Deep code review with rationale + alternativesCode Reviewer (vanilla)
One-line answer you already knowMain 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):

  1. cavecrew-investigator returns site list.
  2. Main thread picks 1-2 sites, hands paths to cavecrew-builder.
  3. cavecrew-reviewer audits 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-builder when you don't already know the file. Spawn investigator first or main thread will eat tokens passing context.
  • Don't chain cavecrew-investigator → cavecrew-builder for a 5-file refactor. Builder will return too-big. and you'll have wasted a turn.
  • Don't ask cavecrew-reviewer for "general feedback" — it returns findings only, no architecture opinions. Use Code Reviewer for 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.

Related skills

G

Generative Code Art

anthropics

Create algorithmic art with p5.js using randomness and interactive parameters.

OfficialComplete terms in LICENSE.txt
P

Poster & Visual Design

anthropics

Create original posters and visual art in PNG and PDF formats.

OfficialComplete terms in LICENSE.txt
C

Claude API Helper

anthropics

Build, debug, and optimize Claude API applications with caching and model migration support.

OfficialComplete terms in LICENSE.txt
M

MCP Server Builder

anthropics

Build protocol servers that connect language models to external APIs and services.

OfficialComplete terms in LICENSE.txt