agentrigs
+ submit rig
~ / rigs / Tatsukiyoshi / dotfiles

Tatsukiyoshi/dotfiles

Personal dotfiles including Claude Code global skills

↗ GitHub ★ 0 no license updated 8d ago personal setup Codex
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~140 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/Tatsukiyoshi/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 Tatsukiyoshi/dotfiles/claude/skills/implement-issue .claude/skills/implement-issue
$ npx degit Tatsukiyoshi/dotfiles/claude/skills/react-best-practices .claude/skills/react-best-practices
$ npx degit Tatsukiyoshi/dotfiles/claude/skills/think-issue .claude/skills/think-issue

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 (3)

implement-issuevercel-react-best-practicesthink-issue

Similar rigs

getclawe/clawe
Multi-agent coordination system: think Trello for OpenClaw agents.
★ 748 project Claude CodeCodex 2 skills 8mo ago
Pragmatist 3.3k tok ·
Blackskydev555/Kanban-board
A Kanban-style desktop app for managing parallel GitHub work sessions.
★ 0 project Claude CodeCodex 2 skills 8mo ago
Pragmatist 2.8k tok ·
christophergyman/Antler
Kanban board for managing multi agent workflows - rust + typescript
★ 0 project Claude CodeCodex 2 skills 8mo ago
Pragmatist 2.8k tok ·
JiinSeok/dotfiles-claude-public
석지인의 Claude Code(생성형 AI) 설정 공개판 — 개인 코드 스타일 가이드·작업 규칙 (민감정보 제외)
★ 0 setup Claude CodeCodex 3 skills 4mo ago
Pragmatist 15.7k tok ·
copied ✓