agent-configuration

name	agent-configuration
description	AI agent configuration policy and security guide. Project description file writing, Hooks/Skills/Plugins setup, security policy, team shared workflow definition.
allowed-tools	Read Write Bash Grep Glob
metadata	{"tags":"agent-configuration, superwork, spw, security, hooks, skills, plugins, multi-agent","platforms":"Claude, Gemini, ChatGPT, Codex","version":"2.0.0","source":"Claude Code Complete Guide 70 Tips (ykdojo + Ado Kukic)"}

AI Agent Configuration Policy (Configuration & Security)

When to use this skill

• Build AI agent environment for new projects
• Write and optimize project description files
• Configure Hooks/Skills/Plugins
• Establish security policies
• Share team configurations

---

1. Project Description File Writing Policy

Overview

Project description files (CLAUDE.md, README, etc.) are project manuals for AI. AI agents reference these files with top priority.

Auto-generate (Claude Code)

/init  # Claude analyzes the codebase and generates a draft

Required Section Structure

# Project: [Project Name]

## Tech Stack
- **Frontend**: React + TypeScript
 : Node.js + Express
 : PostgreSQL
 : Drizzle


 Use TypeScript strict mode
 Prefer server components over client components
 Use  instead of 
 Always validate user input with Zod


 Never commit  files
 Never use  type in TypeScript
 Never bypass authentication checks
 Never expose API keys in client code


 : Start development server
 : Build for production
 : Run tests