agentrigs
+ submit rig
~ / rigs / JuliusBrussee / cavekit

JuliusBrussee/cavekit

Frozen — compressed spec-driven development plugin for Claude Code. Still works; active development moved to JuliusBrussee/caveman.

↗ GitHub ★ 1,148 mit updated 2mo ago project Claude Code Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~75 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit JuliusBrussee/cavekit/skills ./rig-cavekit/skills

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit JuliusBrussee/cavekit/skills/backprop .claude/skills/backprop
$ npx degit JuliusBrussee/cavekit/skills/caveman .claude/skills/caveman
$ npx degit JuliusBrussee/cavekit/skills/check .claude/skills/check
$ npx degit JuliusBrussee/cavekit/skills/deepen .claude/skills/deepen
$ npx degit JuliusBrussee/cavekit/skills/grill .claude/skills/grill
$ npx degit JuliusBrussee/cavekit/skills/research .claude/skills/research
$ npx degit JuliusBrussee/cavekit/skills/review .claude/skills/review
$ npx degit JuliusBrussee/cavekit/skills/spec .claude/skills/spec

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (8)

backpropcavemancheckdeepengrillresearchreviewspec

Similar rigs

mr-min-max/staledocs
Finds documentation that no longer matches your code. Deterministic AST check for pull requests; no API key. TypeScript, JavaScript, Python.
★ 1 project Codex 1 mcp 3 skills today
Pragmatist 2.8k tok ·
yanis-vroland/fieldops
Plateforme fictive de maintenance industrielle avec IA intégrée : API NestJS, app Flutter, RAG, MCP et agents. Projet portfolio de développement agentique.
★ 0 project Claude Code 3 skills 2 agents 2 hooks today
Fort Knox 2.0k tok ·
iamvonpasion/hashb
Dev workflow toolkit for Claude Code — 14 skills that turn AI into a structured development partner. Spec → Design → Eng → TDD → Review → QA → Ship.
★ 2 project Claude Code 20 skills 1 agents 5mo ago
Skill Collector 2.5k tok ·
enapt/SwarmLLM
Free, open-source app that runs AI chat models on your own computer — and lets computers team up over the internet to run models too big for one machine. No account, no crypto. OpenAI- and Anthropic-compatible API.
★ 59 project Claude Code 6 skills 1 agents 4 hooks today
Fort Knox 3.6k tok ·
copied ✓