tuan-finhay/vnsc-claude-code-setup
Best practice to setup Claude Code
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit tuan-finhay/vnsc-claude-code-setup/.claude ./rig-vnsc-claude-code-setup # 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.
$ curl -fsSL --create-dirs -o .claude/agents/backend-tech-lead.md https://raw.githubusercontent.com/tuan-finhay/vnsc-claude-code-setup/main/.claude/agents/backend-tech-lead.md $ curl -fsSL --create-dirs -o .claude/agents/database-performance-engineer.md https://raw.githubusercontent.com/tuan-finhay/vnsc-claude-code-setup/main/.claude/agents/database-performance-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/mobile-tech-lead.md https://raw.githubusercontent.com/tuan-finhay/vnsc-claude-code-setup/main/.claude/agents/mobile-tech-lead.md $ curl -fsSL --create-dirs -o .claude/agents/security-scanner.md https://raw.githubusercontent.com/tuan-finhay/vnsc-claude-code-setup/main/.claude/agents/security-scanner.md $ curl -fsSL --create-dirs -o .claude/agents/solution-architect.md https://raw.githubusercontent.com/tuan-finhay/vnsc-claude-code-setup/main/.claude/agents/solution-architect.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 (5)
| backend-tech-lead model: sonnet | Use this agent when you need expert code review for backend systems. Examples:\n\n1. After implementing a new API endpoint:\nuser: "I just wrote a new REST endpoint for user authentication. Can you re |
| database-performance-engineer model: sonnet | Use this agent when you need to review code for database-related performance issues, optimization opportunities, and potential problems. Examples: <example>Context: The user has just written a new dat |
| mobile-tech-lead model: sonnet | Use this agent when working on mobile development tasks, architectural decisions, code reviews, or technical guidance for iOS, Android, or cross-platform mobile applications. Examples: 1) User asks 'C |
| security-scanner model: sonnet | Use this agent when you need to identify security vulnerabilities, risks, and potential exploits in your codebase. This includes analyzing code for common security flaws, reviewing authentication/auth |
| solution-architect model: sonnet | Use this agent when you need guidance on system architecture decisions, design pattern selection, technology stack choices, scalability considerations, or structural code organization. Examples:\n\n- |
Similar rigs
bijutharakan/multi-agent-squad
Production-ready multi-agent orchestration framework for Claude Code. Features specialized AI agents, automated Git workflows, and comprehensive development automation.
Orchestrator 1.5k tok ·
motock/fagan
Spend tokens on judgment, not typing. An MCP-native autonomous SDLC pipeline: frontier models plan and review, local models implement — engineering discipline on a $20/month budget.
Orchestrator 35.4k tok ·
levu304/claude-code-boilerplate
Universal coding standards and AI agent configurations for Claude Code projects
Orchestrator 14.5k tok ·
serhii-baksheiev/create-agent-rig
Repo-native workflow layer for Codex and Claude Code: coordination, safety gates, TDD evidence, reviews, continuation, and parallel work.
Orchestrator 7.1k tok ·