agentrigs
+ submit rig
~ / rigs / OzzyCzech / dotfiles

OzzyCzech/dotfiles

This is a collection of my personal dotfiles for configuring macOS.

↗ GitHub ★ 136 no license updated 23d ago personal setup Claude Code
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~275 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/OzzyCzech/dotfiles

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 OzzyCzech/dotfiles/claude/skills/gitlab-cli .claude/skills/gitlab-cli
$ npx degit OzzyCzech/dotfiles/claude/skills/npm-release .claude/skills/npm-release

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 (2)

gitlab-clinpm-release

Similar rigs

GantisStorm/essentials-claude-code
Loops and swarms on Claude Code's Task System. Both enforce exit criteria—swarm is faster with parallel queue execution. Plans define what "done" means. Optional: Beads for persistent memory, Ralph TUI for dashboard.
★ 57 project Claude Code 5 skills 9mo ago
Pragmatist 163 tok ·
edloidas/skills
Agent skills for planning, building, reviewing, auditing, maintaining, and shipping software — one collection for Claude Code, Codex, OpenCode, and pi.
★ 2 collection Claude CodeCodex 34 skills today
Skill Collector 14.8k tok ·
multica-ai/andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
★ 217k collection Claude CodeCursor 1 skills 6mo ago
Minimalist 723 tok ·
shareAI-lab/learn-claude-code
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
★ 78.0k project Claude Code 4 skills 11d ago
Minimalist 156 tok ·
copied ✓