Home / chinkan / rustfox · .agents/skills/cavecrew/SKILL.md · GitHub

cavecrew skillA

cavecrew is agent-read markdown (skill) from chinkan/rustfox: 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/r.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

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)
…

Read the whole file at its exact version.

How to install

Latest version
mdr add chinkan/rustfox/cavecrew@git:20260804.a62331b
Exact content
mdr add chinkan/rustfox/cavecrew@sha256:b74f374f6aae6e9a

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_d6l4zki3tdp5y3op.svg)](https://markdownregistry.com/a/art_d6l4zki3tdp5y3op)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260804.a62331b latest2026-08-04 a62331b 3,936 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (3936 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

chinkan/rustfox · 9 stars · license MIT · pushed 2026-09-24 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_d6l4zki3tdp5y3op
GET https://markdownregistry.com/api/v1/resolve?ref=chinkan/rustfox/cavecrew
GET https://markdownregistry.com/api/v1/blob/b74f374f6aae6e9a31e78e7d876860406fe5833378e9298536edf176c12f379b

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from chinkan/rustfox

ask-matt skill
chinkan/rustfox · .agents/skills/ask-matt/SKILL.md · Ask which skill or flow fits your situation. A router over the skills in this repo.
git:20260922.53f91f6 · audit A · 9 stars
brainstorming skill
chinkan/rustfox · .agents/skills/brainstorming/SKILL.md · You MUST use this before any creative work - creating features, building components, adding functionality, or modifying…
git:20260408.ae338c2 · audit A · 9 stars
caveman-commit skill
chinkan/rustfox · .agents/skills/caveman-commit/SKILL.md · Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning…
git:20260804.0abefec · audit A · 9 stars
caveman-compress skill
chinkan/rustfox · .agents/skills/caveman-compress/SKILL.md · Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens…
git:20260804.0abefec · audit A · 9 stars
caveman-help skill
chinkan/rustfox · .agents/skills/caveman-help/SKILL.md · Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger…
git:20260804.0abefec · audit A · 9 stars
caveman-review skill
chinkan/rustfox · .agents/skills/caveman-review/SKILL.md · Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment…
git:20260804.0abefec · audit A · 9 stars
caveman-stats skill
chinkan/rustfox · .agents/skills/caveman-stats/SKILL.md · Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log —…
git:20260804.0abefec · audit A · 9 stars
caveman skill
chinkan/rustfox · .agents/skills/caveman/SKILL.md · Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full…
git:20260804.0abefec · audit A · 9 stars
code-review skill
chinkan/rustfox · .agents/skills/code-review/SKILL.md · Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code…
git:20260922.53f91f6 · audit A · 9 stars
codebase-design skill
chinkan/rustfox · .agents/skills/codebase-design/SKILL.md · Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find…
git:20260922.53f91f6 · audit A · 9 stars
design-an-interface skill
chinkan/rustfox · .agents/skills/design-an-interface/SKILL.md · Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to…
git:20260714.d9bd5ab · audit A · 9 stars
diagnosing-bugs skill
chinkan/rustfox · .agents/skills/diagnosing-bugs/SKILL.md · Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports…
git:20260922.53f91f6 · audit A · 9 stars

Every file in chinkan/rustfox

Other files named cavecrew

cavecrew skill
juliusbrussee/caveman · plugins/caveman/skills/cavecrew/SKILL.md · When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer`…
git:20260829.e11d002 · audit A · 107,708 stars
cavecrew skill
juliusbrussee/caveman · skills/cavecrew/SKILL.md · When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer`…
git:20260823.8909f6a · audit A · 107,708 stars

Browse by kind, by grade A, or by owner.