agentrigs
+ submit rig
~ / rigs / zgeoff / dotfiles

zgeoff/dotfiles

m'dots

↗ GitHub ★ 15 Unlicense updated 1d ago personal setup Claude CodeCodex
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~630 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 zgeoff/dotfiles/home/dot_claude ./rig-dotfiles  # inspect, then merge into .claude/

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 zgeoff/dotfiles/home/dot_claude/skills/build-feature .claude/skills/build-feature
$ npx degit zgeoff/dotfiles/home/dot_claude/skills/delegate .claude/skills/delegate
$ curl -fsSL --create-dirs -o .claude/agents/locator.md https://raw.githubusercontent.com/zgeoff/dotfiles/main/home/dot_claude/agents/locator.md

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)

build-featuredelegate

Subagents (1)

locator
model: haiku
>

Similar rigs

awtotty/claude-code-setup
—
★ 1 setup Claude Code 3 skills 7mo ago
YOLO Cowboy 81 tok ·
oberon-systems/enggraph
Engineering Graph for AI coding agents. Code intelligence, persistent memory, plans and multi-project context over MCP.
★ 1 project Claude CodeGemini CLI 3 mcp 5 skills today
Pragmatist 9.0k tok ·
devduck123/swe-os
Engineering judgment for people and their coding agents. One set of Markdown files: a learning site for humans, instructions for agents.
★ 0 project Claude CodeCodex 7 skills today
Pragmatist 1.2k tok ·
stefan-jansen/coding-agent-plugins
Plugin marketplace for coding-agent-toolkit — workflow, memory, transition, development, and code-quality plugins for Claude Code.
★ 8 collection Claude Code 16 skills 3d ago
Skill Collector 1.0k tok ·
copied ✓