AI IDE Configuration Standards: From .vscode to AGENTS.md

project/
├── .vscode/
│   ├── settings.json      # Editor settings
│   ├── tasks.json         # Build tasks
│   ├── launch.json        # Debug configurations
│   ├── extensions.json    # Recommended extensions
│   └── snippets/          # Code snippets
│       ├── javascript.json
│       └── typescript.json
└── src/

{
  "editor.tabSize": 2,
  "editor.insertSpaces": true,
  "editor.formatOnSave": true,
  "editor.defaultFormatter": "esbenp.prettier-vscode",
  "editor.codeActionsOnSave": {
    "source.fixAll.eslint": "explicit"
  },
  "files.exclude": {
    "**/node_modules": true,
    "**/dist": true,
    "**/.git": true
  },
  "search.exclude": {
    "**/node_modules": true,
    "**/bower_components": true,
    "**/*.code-search": true
  },
  "typescript.tsdk": "node_modules/typescript/lib",
  "typescript.enablePromptUseWorkspaceTsdk": true,
  "eslint.validate": [
    "javascript",
    "javascriptreact",
    "typescript",
    "typescriptreact"
  ],
  "[typescript]": {
    "editor.defaultFormatter": "esbenp.prettier-vscode"
  },
  "[typescriptreact]": {
    "editor.defaultFormatter": "esbenp.prettier-vscode"
  },
  "editor.rulers": [80, 100, 120],
  "workbench.editorAssociations": {
    "*.md": "vscode.markdown.preview.editor"
  }
}

{
  "version": "2.0.0",
  "tasks": [
    {
      "label": "Build",
      "type": "npm",
      "script": "build",
      "group": "build",
      "presentation": {
        "reveal": "never"
      },
      "problemMatcher": ["$tsc"]
    },
    {
      "label": "Test",
      "type": "npm",
      "script": "test",
      "group": "test",
      "presentation": {
        "reveal": "never"
      }
    },
    {
      "label": "Start Dev Server",
      "type": "npm",
      "script": "dev",
      "group": {
        "kind": "build",
        "isDefault": true
      },
      "isBackground": true,
      "problemMatcher": {
        "pattern": {
          "regexp": "^.*ready in.*$",
          "file": 1
        },
        "background": {
          "activeOnStart": true,
          "beginsPattern": "starting",
          "endsPattern": "ready"
        }
      }
    },
    {
      "label": "Lint",
      "type": "npm",
      "script": "lint",
      "group": "test",
      "problemMatcher": ["$eslint-stylish"]
    }
  ]
}

{
  "version": "0.2.0",
  "configurations": [
    {
      "type": "node",
      "request": "launch",
      "name": "Debug Current File",
      "skipFiles": ["<node_internals>/**"],
      "program": "${file}",
      "cwd": "${workspaceFolder}",
      "console": "integratedTerminal",
      "internalConsoleOptions": "neverOpen"
    },
    {
      "type": "node",
      "request": "launch",
      "name": "Debug All Tests",
      "skipFiles": ["<node_internals>/**"],
      "program": "${workspaceFolder}/node_modules/.bin/jest",
      "args": ["--runInBand"],
      "cwd": "${workspaceFolder}",
      "console": "integratedTerminal"
    },
    {
      "type": "chrome",
      "request": "launch",
      "name": "Launch Chrome",
      "url": "http://localhost:3000",
      "webRoot": "${workspaceFolder}/src",
      "runtimeArgs": ["--disable-dev-shm-usage"]
    }
  ]
}

{
  "recommendations": [
    "dbaeumer.vscode-eslint",
    "esbenp.prettier-vscode",
    "bradlc.vscode-tailwindcss",
    "formulahendry.auto-rename-tag",
    "christian-kohler.path-intellisense",
    "streetsidesoftware.code-spell-checker",
    "GitHub.copilot",
    "GitHub.copilot-chat"
  ],
  "unwantedRecommendations": [
    "eg2.vscode-npm-script"
  ]
}

// settings.json - AI-specific settings
{
  "github.copilot.enable": true,
  "github.copilot.editor.enableAutoCompletions": true,
  "continue.enableTabAutocomplete": true,
  "kiloCode.provider": "qwen-code",
  "kiloCode.model": "qwen-coder-plus"
}

project/
├── .cursor/
│   ├── rules/              # AI rules directory
│   │   ├── coding-standards.md
│   │   ├── testing.md
│   │   └── security.md
│   ├── config.json         # Cursor-specific config
│   └── prompts/            # Custom prompts
│       └── code-review.md
└── src/

# .cursor/rules/coding-standards.md

## Code Style
- Always use TypeScript for new code
- Use functional components in React
- Prefer composition over inheritance
- Use async/await, not Promise chains

## Naming Conventions
- Components: PascalCase (UserProfile)
- Functions: camelCase (getUserById)
- Constants: UPPER_SNAKE_CASE (MAX_RETRY_COUNT)
- Files: kebab-case (user-profile.tsx)

## Imports
- Group imports: React, third-party, internal, relative
- Use absolute imports from @/
- No circular dependencies

## Error Handling
- Always handle errors explicitly
- Use custom error classes
- Log errors with context
- Never swallow errors silently

## Testing
- Write tests for all public functions
- Use describe/it/test pattern
- Mock external dependencies
- Aim for 80%+ coverage

{
  "ai": {
    "model": "claude-3-5-sonnet-20241022",
    "temperature": 0.3,
    "maxTokens": 8192
  },
  "indexing": {
    "enabled": true,
    "ignorePatterns": [
      "node_modules/**",
      "dist/**",
      "build/**",
      "*.min.js",
      "coverage/**"
    ],
    "maxFileSize": "1MB"
  },
  "composer": {
    "autoApprove": false,
    "requireConfirmation": true
  },
  "privacy": {
    "mode": "local",
    "sendTelemetry": false
  }
}

# Code Review Prompt

When reviewing code, follow this checklist:

## Security
- [ ] No hardcoded secrets
- [ ] Input validation present
- [ ] SQL injection prevented
- [ ] XSS prevention in place

## Performance
- [ ] No N+1 queries
- [ ] Proper indexing
- [ ] Caching where appropriate
- [ ] No memory leaks

## Code Quality
- [ ] Follows style guide
- [ ] Functions are small
- [ ] Clear variable names
- [ ] Comments explain why, not what

## Testing
- [ ] Tests cover edge cases
- [ ] Mocks used appropriately
- [ ] Test names are descriptive

Provide feedback in this format:
1. Summary
2. Critical issues (blocking)
3. Suggestions (non-blocking)
4. Questions

project/
├── .kilocode/
│   ├── config.json         # Main configuration
│   ├── mcp.json            # MCP server config
│   ├── agents.json         # Agent definitions
│   ├── skills.json         # Skills configuration
│   ├── rules/              # Steering rules
│   │   ├── coding-standards.md
│   │   ├── security.md
│   │   ├── testing.md
│   │   └── documentation.md
│   ├── agents/             # Custom agents
│   │   ├── security-reviewer.md
│   │   ├── code-reviewer.md
│   │   └── tech-writer.md
│   ├── skills/             # Custom skills
│   │   ├── docker-expert/
│   │   │   ├── skill.json
│   │   │   └── prompt.md
│   │   └── aws-helper/
│   ├── specs/              # Specifications
│   │   ├── feature-auth.md
│   │   └── feature-api.md
│   ├── tasks/              # Task definitions
│   │   └── phase-1/
│   └── index/              # Indexing data
│       └── qdrant/
├── .kilocodemodes          # Mode definitions
├── .kilocodeignore         # Indexing exclusions
└── src/

{
  "provider": "qwen-code",
  "model": "qwen-coder-plus",
  "mode": "orchestrator",
  "indexing": {
    "enabled": true,
    "provider": "qdrant",
    "embedding": {
      "model": "nomic-embed-text",
      "provider": "ollama",
      "endpoint": "http://localhost:11434"
    },
    "vectorStore": {
      "provider": "qdrant",
      "endpoint": "http://localhost:6333",
      "collectionName": "my-project"
    },
    "chunking": {
      "strategy": "code-aware",
      "chunkSize": 512,
      "overlap": 64
    }
  },
  "steering": {
    "rules": ["coding-standards", "security", "testing"]
  },
  "mcpServers": {
    "github": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-github"],
      "env": {
        "GITHUB_TOKEN": "${GITHUB_TOKEN}"
      }
    }
  },
  "agentManager": {
    "enabled": true,
    "maxParallelAgents": 4,
    "worktreeBasePath": "../worktrees"
  }
}

# .kilocode/rules/coding-standards.md

## TypeScript Standards

### Always Use TypeScript
- All new code must be TypeScript (.ts, .tsx)
- Never use `any` type
- Define interfaces for all objects

### Code Style
- Use functional components
- Use async/await
- Prefer const over let

### Libraries
- Use Zod for validation
- Use date-fns for dates
- Use axios for HTTP

{
  "modes": {
    "security-review": {
      "baseMode": "architect",
      "systemPrompt": "You are a security expert reviewing code.",
      "tools": ["code-scanner", "dependency-checker"],
      "restrictions": {
        "cannotModifyFiles": true
      }
    },
    "documentation": {
      "baseMode": "code",
      "systemPrompt": "You are a technical writer.",
      "tools": ["file-reader", "markdown-generator"]
    }
  }
}

# .kilocodeignore
node_modules/
dist/
build/
*.min.js
coverage/
.env
*.log
.secrets/

project/
├── .qwen/
│   ├── config.json         # Qwen configuration
│   ├── context/            # Context files
│   │   └── project-context.md
│   └── cache/              # Cached data
└── src/

{
  "model": {
    "name": "qwen-coder-plus",
    "temperature": 0.3,
    "maxTokens": 100000,
    "topP": 0.9
  },
  "context": {
    "maxTokens": 1000000,
    "smartTrimming": true,
    "priorityFiles": [
      "README.md",
      "package.json",
      "tsconfig.json"
    ]
  },
  "indexing": {
    "enabled": true,
    "strategy": "semantic",
    "chunkSize": 4096,
    "overlapSize": 512
  },
  "caching": {
    "enabled": true,
    "directory": "~/.cache/qwen-code",
    "ttl": 3600
  }
}

# Project Context

## Overview
This is a Node.js REST API for an e-commerce platform.

## Tech Stack
- Runtime: Node.js 20
- Framework: Express.js
- Database: PostgreSQL with Prisma ORM
- Authentication: JWT with refresh tokens

## Key Directories
- src/controllers/ - Request handlers
- src/services/ - Business logic
- src/models/ - Database models
- src/middleware/ - Express middleware

## Important Commands
- `npm run dev` - Start development server
- `npm run build` - Build for production
- `npm test` - Run tests
- `npm run db:migrate` - Run database migrations

## Architecture Notes
- All controllers use async/await
- Services handle business logic
- Models use Prisma Client
- Middleware handles auth and validation

# Agent Instructions

## Quick Start

To work on this project, an AI agent should:

1. Understand the project structure (see below)
2. Follow the coding standards
3. Run tests before committing
4. Update documentation for new features

## Project Structure

```
project/
├── src/
│   ├── controllers/    # HTTP request handlers
│   ├── services/       # Business logic
│   ├── models/         # Database models
│   ├── middleware/     # Express middleware
│   └── utils/          # Utility functions
├── tests/
│   ├── unit/           # Unit tests
│   ├── integration/    # Integration tests
│   └── e2e/            # End-to-end tests
├── docs/               # Documentation
└── scripts/            # Build/deploy scripts
```

## Coding Standards

### TypeScript
- Use strict mode
- No `any` types
- Define interfaces for objects

### Testing
- Jest for unit tests
- Supertest for API tests
- Playwright for E2E

### Code Style
- Prettier for formatting
- ESLint for linting
- 2-space indentation

## Common Tasks

### Adding a New API Endpoint

1. Create controller in `src/controllers/`
2. Create service in `src/services/`
3. Add route in `src/routes/`
4. Write tests in `tests/`
5. Update API documentation

### Fixing a Bug

1. Reproduce the bug
2. Write a failing test
3. Fix the code
4. Verify test passes
5. Run full test suite

## Testing Commands

```bash
# Run all tests
npm test

# Run specific test file
npm test -- path/to/test.ts

# Run with coverage
npm run test:coverage

# Run E2E tests
npm run test:e2e
```

## Deployment

```bash
# Build for production
npm run build

# Start production server
npm start

# Deploy to staging
npm run deploy:staging

# Deploy to production
npm run deploy:prod
```

## Troubleshooting

### Common Issues

**Database Connection Failed**
- Check DATABASE_URL environment variable
- Ensure database is running
- Run migrations: `npm run db:migrate`

**Tests Failing**
- Clear Jest cache: `npm run test:clear`
- Check for uncommitted changes
- Verify environment variables

## Contact

For questions about this project, contact the team via Slack #dev-channel.

# Claude Instructions

## How to Help

When assisting with this codebase:

1. **Read this file first** for context
2. **Check existing code** before suggesting changes
3. **Follow patterns** already established
4. **Write tests** for any new code
5. **Update docs** for new features

## What NOT to Do

- ❌ Don't use `any` types
- ❌ Don't skip error handling
- ❌ Don't add new dependencies without approval
- ❌ Don't modify config files without explanation
- ❌ Don't commit without running tests

## Preferred Patterns

### API Response Format
```typescript
{
  success: boolean;
  data?: T;
  error?: {
    code: string;
    message: string;
  };
}
```

### Error Handling
```typescript
try {
  await someOperation();
} catch (error) {
  logger.error('Operation failed', { error, context });
  throw new AppError('OPERATION_FAILED', 'Human readable message');
}
```

### Logging
```typescript
import { logger } from '@/utils/logger';

logger.info('User logged in', { userId });
logger.warn('Rate limit approaching', { current: 90, max: 100 });
logger.error('Database connection failed', { error });
```

## Review Checklist

Before suggesting code changes, verify:
- [ ] TypeScript types are correct
- [ ] Error handling is present
- [ ] Tests are included
- [ ] No console.log in production code
- [ ] Follows existing patterns

# Always commit configuration
git add .vscode/ .kilocode/ AGENTS.md
git commit -m "Add AI configuration"

templates/
├── .kilocode/
│   └── config.template.json
├── AGENTS.md.template
└── .cursorrules.template

# .kilocode/README.md

## Configuration Overview

This directory contains Kilo Code configuration:

- `config.json` - Main configuration
- `rules/` - Steering rules for AI behavior
- `agents/` - Custom agent definitions
- `skills/` - Specialized skill packages

## Adding New Rules

1. Create file in `rules/`
2. Add to `config.json` steering array
3. Test with: `kiro rules check`

// Good: Reference environment variables
{
  "apiKey": "${GITHUB_TOKEN}"
}

// Bad: Hardcoded secrets
{
  "apiKey": "ghp_xxxxxxxxxxxx"  // Never do this!
}

# Validate Kilo Code config
kiro config validate

# Validate Cursor rules
cursor rules check

# Validate AGENTS.md
kiro agents validate AGENTS.md

# Kilo Code
kiro config validate
kiro rules list
kiro agents list

# Cursor
cursor rules check

# Qwen
qwen-code config show
qwen-code context status