~ / rigs / kdbaustert / dotfiles

kdbaustert/dotfiles

There's lots of configurations out there, but this one is mine.

↗ GitHub ★ 6 MIT updated 8d ago personal setup Claude Code
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~14.4k tokens
Heavy · 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 kdbaustert/dotfiles/.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 kdbaustert/dotfiles/.claude/skills/database-optimizer .claude/skills/database-optimizer
$ npx degit kdbaustert/dotfiles/.claude/skills/javascript-pro .claude/skills/javascript-pro
$ npx degit kdbaustert/dotfiles/.claude/skills/nextjs-developer .claude/skills/nextjs-developer
$ npx degit kdbaustert/dotfiles/.claude/skills/php-pro .claude/skills/php-pro
$ npx degit kdbaustert/dotfiles/.claude/skills/plain .claude/skills/plain
$ npx degit kdbaustert/dotfiles/.claude/skills/react-expert .claude/skills/react-expert
$ npx degit kdbaustert/dotfiles/.claude/skills/react-native-expert .claude/skills/react-native-expert
$ npx degit kdbaustert/dotfiles/.claude/skills/swift-expert .claude/skills/swift-expert
$ npx degit kdbaustert/dotfiles/.claude/skills/vue-expert-js .claude/skills/vue-expert-js
$ npx degit kdbaustert/dotfiles/.claude/skills/vue-expert .claude/skills/vue-expert
$ curl -fsSL --create-dirs -o .claude/agents/bug-hunter.md https://raw.githubusercontent.com/kdbaustert/dotfiles/master/.claude/agents/bug-hunter.md
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/kdbaustert/dotfiles/master/.claude/agents/code-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/feature-scout.md https://raw.githubusercontent.com/kdbaustert/dotfiles/master/.claude/agents/feature-scout.md
$ curl -fsSL --create-dirs -o .claude/agents/heavy-refactor.md https://raw.githubusercontent.com/kdbaustert/dotfiles/master/.claude/agents/heavy-refactor.md
$ curl -fsSL --create-dirs -o .claude/agents/quick-lookup.md https://raw.githubusercontent.com/kdbaustert/dotfiles/master/.claude/agents/quick-lookup.md
$ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/kdbaustert/dotfiles/master/.claude/agents/researcher.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 (10)

Subagents (6)

bug-hunter
model: opus
Hunts a codebase for existing bugs and for spots where error handling is missing, silent, or inadequate. Use proactively for a standing health check of a project, or when asked to find bugs or audit e
code-reviewer
model: sonnet
Reviews a diff, PR, or specific files for correctness, security, and maintainability. Use proactively after writing or modifying code, or when asked to review changes.
feature-scout
model: sonnet
Surveys a project for gaps and opportunities, then proposes new features with a rationale for why each is worth building. Use proactively when asked "what should we add next", "what's missing", or whe
heavy-refactor
model: opus
Multi-file refactors, migrations, or architecture changes that need to hold a lot of cross-file context and get it right in one pass. Use for large, hard-to-reverse structural changes — not for a sing
quick-lookup
model: haiku
Fast, narrow lookups — find a file by name, grep for a symbol, check whether something exists. Use proactively for any single targeted search that doesn't need judgment, so the main session's context
researcher
model: sonnet
Open-ended research across the codebase or the web — tracing how something works, comparing approaches, gathering context before a decision. Use proactively when a question needs multiple searches syn

Slash commands (2)

/hunt-bugs/scout-features

Similar rigs

copied ✓