cavecrew SKILL.md skillA

cavecrew from juliusbrussee/caveman is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add juliusbrussee/caveman/cavecrew@git:20261006.4ec0d9b

Pins git:20261006.4ec0d9b in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
juliusbrussee/caveman
Path
plugins/caveman/skills/cavecrew/SKILL.md
Versions recorded
6
Latest version
git:20261006.4ec0d9b, committed Oct 6, 2026
First version recorded
Apr 30, 2026
Size
3,777 bytes
Repository stars
116,476
License
Apache-2.0

When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or using `Explore`. Their output is compressed, so main context lasts longer.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

Cavecrew = three subagent presets that answer in ultracave voice (tool runs: one status line in, one out; nothing between routine calls). 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` if installed |
| Review diff, branch, or file for bugs | `cavecrew-reviewer` |
| Deep code review with rationale + alternatives | `Code Reviewer` (vanilla) if installed, else main thread |
| 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

The exact contents, by fingerprint
mdr add juliusbrussee/caveman/cavecrew@sha256:534c0a70d4c77288

The line at the top of this page pins the label git:20261006.4ec0d9b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_7atv5x4o5eoj64se.svg)](https://markdownregistry.com/a/art_7atv5x4o5eoj64se)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 6 versions of this file, between Apr 30, 2026 and Oct 6, 2026, about one every 32 days.

versioncommittedcommitsizeaudit
git:20261006.4ec0d9b latest2026-10-06 4ec0d9b 3,777 BA view · diff
git:20261002.613fcfd2026-10-02 613fcfd 3,744 BA view · diff
git:20261002.f7c2cab2026-10-02 f7c2cab 3,666 BA view · diff
git:20260829.e11d0022026-08-29 e11d002 3,606 BA view · diff
git:20260501.83ec61c2026-05-01 83ec61c 3,936 BA view · diff
git:20260430.56875e82026-04-30 56875e8 2,294 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the 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 (3777 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

juliusbrussee/caveman · 116,476 stars · license Apache-2.0 · pushed 2026-10-31 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_7atv5x4o5eoj64se
GET https://markdownregistry.com/api/v1/resolve?ref=juliusbrussee/caveman/cavecrew
GET https://markdownregistry.com/api/v1/blob/534c0a70d4c7728815214a11e80e66cecbd2104f905f96414e6e32504381c002

Your AI assistant 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.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from juliusbrussee/caveman

AGENTS.md AGENTS.md file
juliusbrussee/caveman · AGENTS.md
git:20260902.d9faebc · audit A · 116,476 stars
CLAUDE.md CLAUDE.md file
juliusbrussee/caveman · CLAUDE.md
git:20261010.505ac30 · audit B · 116,476 stars
CLAUDE.md@browse CLAUDE.md file
juliusbrussee/caveman · browse/CLAUDE.md
git:20260816.f71f6df · audit A · 116,476 stars
AGENTS.md@engine AGENTS.md file
juliusbrussee/caveman · engine/AGENTS.md
git:20260812.d4ef06b · audit A · 116,476 stars
CLAUDE.md@engine CLAUDE.md file
juliusbrussee/caveman · engine/CLAUDE.md
git:20261006.2f6ebbf · audit A · 116,476 stars
AGENTS.md@extension AGENTS.md file
juliusbrussee/caveman · extension/AGENTS.md
git:20261003.2ec7194 · audit A · 116,476 stars
CLAUDE.md@extension CLAUDE.md file
juliusbrussee/caveman · extension/CLAUDE.md
git:20261003.2ec7194 · audit A · 116,476 stars
CLAUDE.md@integrations CLAUDE.md file
juliusbrussee/caveman · integrations/CLAUDE.md
git:20260812.d4ef06b · audit A · 116,476 stars
AGENTS.md@mcp AGENTS.md file
juliusbrussee/caveman · mcp/AGENTS.md
git:20260924.921eab8 · audit A · 116,476 stars
CLAUDE.md@mcp CLAUDE.md file
juliusbrussee/caveman · mcp/CLAUDE.md
git:20260924.921eab8 · audit A · 116,476 stars
AGENTS.md@mem AGENTS.md file
juliusbrussee/caveman · mem/AGENTS.md
git:20260924.921eab8 · audit A · 116,476 stars
CLAUDE.md@mem CLAUDE.md file
juliusbrussee/caveman · mem/CLAUDE.md
git:20261009.30b22b7 · audit A · 116,476 stars

Every file in juliusbrussee/caveman

Other files named cavecrew

cavecrew SKILL.md 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:20261006.4ec0d9b · audit A · 116,476 stars
cavecrew SKILL.md skill
chinkan/rustfox · .agents/skills/cavecrew/SKILL.md · Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator`…
git:20260804.a62331b · audit A · 11 stars
cavecrew SKILL.md skill
chadixearth/graphyloop · skills/cavecrew/SKILL.md · Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator`…
git:20261029.d65aaec · audit A · 3 stars

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