d4kine/claude-code-setup
My personal setup of claude code with custom agents, commands, etc.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code $ npx degit d4kine/claude-code-setup/agents ./rig-claude-code-setup/agents $ npx degit d4kine/claude-code-setup/commands ./rig-claude-code-setup/commands
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.
$ curl -fsSL --create-dirs -o .claude/agents/ai-engineer.md https://raw.githubusercontent.com/d4kine/claude-code-setup/main/agents/ai-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/speech-to-prompt.md https://raw.githubusercontent.com/d4kine/claude-code-setup/main/agents/speech-to-prompt.md $ curl -fsSL --create-dirs -o .claude/agents/ui-ux-designer-modern.md https://raw.githubusercontent.com/d4kine/claude-code-setup/main/agents/ui-ux-designer-modern.md $ curl -fsSL --create-dirs -o .claude/agents/vue-nuxt-typescript-pro.md https://raw.githubusercontent.com/d4kine/claude-code-setup/main/agents/vue-nuxt-typescript-pro.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 *)"
]
}
} Subagents (4)
| ai-engineer model: sonnet | LLM application specialist for building AI features, RAG systems, and prompt pipelines. Use PROACTIVELY when implementing chatbots, vector search, agent orchestration, or any AI/LLM-powered functional |
| speech-to-prompt model: claude-sonnet-4-5-20250929 | Transform vague voice instructions into complete, runnable applications |
| ui-ux-designer-modern model: sonnet | Create interface designs, wireframes, and design systems. Masters user research, accessibility standards, and modern design tools. Specializes in design tokens, component libraries, and inclusive desi |
| vue-nuxt-typescript-pro model: sonnet | Master Vue 3/Nuxt 4 with TypeScript, advanced composition API patterns, and strict type safety. Handles complex reactive systems, component typing, and enterprise-grade SSR/SSG applications. Use PROAC |
Slash commands (2)
/prompt-optimizer/trigger
Similar rigs
benjaminr/claude-code-essentials
A collection of prompts, templates and slash commands for supercharging Claude Code.
Orchestrator 8.4k tok ·
DNYoussef/Spek-template
The template is now production-ready with comprehensive setup instructions for: - Claude Code, Gemini CLI, Codex CLI - All MCP servers and API integrations - Security scanning and quality gates - Complete workflow automation
MCP Hoarder 25.4k tok ·
jiaheyi-maggie/claude-code-config
Personal Claude Code configuration — commands, hooks, settings, and global instructions
Orchestrator 7.0k tok ·
sagullapalli/claude-code-setup
Claude Code Setup for building fullstack applications
Orchestrator 1.5k tok ·