agentrigs
+ submit rig
~ / rigs / rZilla2 / rod-ai-toolkit

rZilla2/rod-ai-toolkit

Prompts, skills, and configs for Claude Code + Obsidian workflows. Built for ADHD brains.

↗ GitHub ★ 2 MIT updated 7mo ago project Claude Code
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~491 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 rZilla2/rod-ai-toolkit/skills ./rig-rod-ai-toolkit/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 rZilla2/rod-ai-toolkit/skills/excalidraw-diagram .claude/skills/excalidraw-diagram
$ npx degit rZilla2/rod-ai-toolkit/skills/morning-briefing .claude/skills/morning-briefing
$ npx degit rZilla2/rod-ai-toolkit/skills/notebooklm .claude/skills/notebooklm
$ npx degit rZilla2/rod-ai-toolkit/skills/obsidian-add-task-sb .claude/skills/obsidian-add-task-sb
$ npx degit rZilla2/rod-ai-toolkit/skills/reflect .claude/skills/reflect
$ npx degit rZilla2/rod-ai-toolkit/skills/session-notes-updated .claude/skills/session-notes-updated
$ npx degit rZilla2/rod-ai-toolkit/skills/start-project .claude/skills/start-project
$ npx degit rZilla2/rod-ai-toolkit/skills/youtube-research .claude/skills/youtube-research

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)

excalidraw-diagrammorning-briefingnotebooklmobsidian-add-task-sbreflectsession-notesstart-projectyoutube-research

Similar rigs

bostonaholic/reflect
An AI tool to generate your brag document
★ 36 project Claude CodeCodexCursor 1 skills 8d ago
Minimalist 2.1k tok ·
zylMozart/ClaudeTeam
Build an agent team with a single prompt, integrate with Lark (Feishu). Support Codex, Claude Code, Openclaw, and many other CLIs.
★ 235 project Claude Code 2 skills 3mo ago
Minimalist 2.0k tok ·
theantichris/dotfiles
My dotfiles, configurations, and desktop theme.
★ 4 setup Claude Code 3 skills 6d ago
Minimalist 99 tok ·
dnsatgit/aigod
Your AI agent workflow is mid. This fixes that. A structured prompt engineering framework for Claude Code. It lives in your git repo as a set of markdown files, JSON configs, and eval templates that give Claude Code consistent behavior, dom
★ 2 project Claude Code 3 skills 7mo ago
Pragmatist 3.5k tok ·
copied ✓