my-ai-tools

Welcome to my-ai-tools 👋

Comprehensive guide to replicate my AI coding tools setup with custom configurations, MCP servers, plugins, and commands.

📋 Prerequisites

🚀 Quick Start

sh cli.sh

Options:

🤖 Claude Code (Required)

Primary AI coding assistant with extensive customization.

Installation

npm install -g @anthropic-ai/claude-code

MCP Servers

Add to ~/.claude/mcp-servers.json:

{
  "mcpServers": {
    "context7": {
      "command": "npx",
      "args": ["-y", "@upstash/context7-mcp@latest"]
    },
    "sequential-thinking": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-sequential-thinking"]
    }
  }
}

Available MCP Servers:

Plugins

Enable in Claude Code settings:

Plugin Description Link
claude-mem Context memory across sessions GitHub
typescript-lsp TypeScript language server Official
pyright-lsp Python language server Official
context7 Documentation lookup GitHub
frontend-design UI/UX design assistance Official
learning-output-style Interactive learning mode Official
swift-lsp Swift language support Official
lua-lsp Lua language support Official
beads Issue tracking & project management GitHub
plannotator Plan annotation tool GitHub
claude-hud Status line with usage monitoring GitHub

Hooks

Configure in ~/.claude/settings.json:

PostToolUse Hooks - Auto-format after file edits:

{
  "hooks": {
    "PostToolUse": [
      {
        "matcher": "Write|Edit|MultiEdit",
        "hooks": [
          {
            "type": "command",
            "command": "jq -r '.tool_input.file_path' | { read file_path; if echo \"$file_path\" | grep -q '\\.(ts|tsx|js|jsx)$'; then biome check --write \"$file_path\"; fi; }"
          },
          {
            "type": "command",
            "command": "if [[ \"$( jq -r .tool_input.file_path )\" =~ \\.go$ ]]; then gofmt -w \"$( jq -r .tool_input.file_path )\"; fi"
          },
          {
            "type": "command",
            "command": "jq -r '.tool_input.file_path' | { read file_path; if echo \"$file_path\" | grep -q '\\.(md|mdx)$'; then npx prettier --write \"$file_path\"; fi; }"
          }
        ]
      }
    ]
  }
}

PreToolUse Hooks - Transform WebSearch queries:

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "WebSearch",
        "hooks": [
          {
            "type": "command",
            "command": "node \"/Users/YOUR_USERNAME/.ccs/hooks/websearch-transformer.cjs\"",
            "timeout": 120
          }
        ]
      }
    ]
  }
}

Custom Commands

Plus all commands from installed plugins.

💡 Tips & Tricks

Configuration Files

Copy from configs/claude/ directory:

🔄 Bidirectional Config Sync

This repository supports two-way synchronization:

Forward: Install to Home (cli.sh)

Copy configs from this repository to your home directory:

./cli.sh [--dry-run] [--backup] [--no-backup]

Options:

Reverse: Generate from Home (generate.sh)

Copy your current configs FROM home TO this repository:

./generate.sh [--dry-run]

This is useful for:

Note: Sensitive files (like *.settings.json containing API keys) are automatically excluded from CCS config sync.

🎨 OpenCode (Optional)

Alternative AI coding assistant with custom agents and skills.

Installation

# Terminal (recommended)
curl -fsSL https://opencode.ai/install | bash

# Or via npm
npm install -g opencode-ai

# Or via bun
bun add -g opencode-ai

# Or via Homebrew
brew install opencode

Configuration

Copy configs/opencode/opencode.json to ~/.config/opencode/:

{
  "$schema": "https://opencode.ai/config.json",
  "instructions": ["./configs/best-practices.md"],
  "theme": "kanagawa",
  "default_agent": "plan",
  "mcp": {
    "context7": {
      "type": "remote",
      "url": "https://mcp.context7.com/mcp"
    }
  },
  "agent": {
    "build": {
      "permission": {
        "bash": {
          "git push": "ask"
        }
      }
    }
  },
  "plugin": ["@plannotator/opencode@latest"]
}

Custom Agents

Agent Description Mode
ai-slop-remover Cleans AI-generated code patterns subagent
docs-writer Technical documentation writer subagent
review Code review for quality & best practices subagent
security-audit Security vulnerability identification subagent

Custom Commands

Skills

🎯 Amp (Optional)

Lightweight AI assistant with browser and backlog integration.

Installation

# Recommended: via install script (supports auto-updating)
curl -fsSL https://ampcode.com/install.sh | bash

# Or via npm (if necessary)
npm install -g @sourcegraph/amp@latest

Configuration

Copy configs/amp/settings.json to ~/.config/amp/:

{
  "amp.dangerouslyAllowAll": true,
  "amp.mcpServers": {
    "context7": {
      "url": "https://mcp.context7.com/mcp"
    },
    "chrome-devtools": {
      "command": "npx",
      "args": ["chrome-devtools-mcp@latest"]
    },
    "backlog": {
      "command": "backlog",
      "args": ["mcp", "start"]
    }
  }
}

MCP Servers

🔄 CCS - Claude Code Switch (Optional)

CCS (Claude Code Switch) - Seamlessly switch between multiple Claude accounts and API providers.

Installation

npm install -g @kaitranntt/ccs

Features

Configuration

Copy all files from configs/ccs/ to ~/.ccs/:

version: 7

profiles:
  glm:
    type: api
    settings: ~/.ccs/glm.settings.json
  kimi:
    type: api
    settings: ~/.ccs/kimi.settings.json
  mm:
    type: api
    settings: ~/.ccs/mm.settings.json

cliproxy:
  providers:
    - gemini
    - codex
    - agy
    - qwen
    - iflow

websearch:
  enabled: true
  providers:
    gemini:
      enabled: true
      model: gemini-2.5-flash

Usage

# Switch to a profile
ccs kimi

# Create new account profile
ccs auth create work

# List available profiles
ccs auth list

🛠️ Companion Tools

Plannotator

Plannotator - Annotate plans outside the terminal for better collaboration. (GitHub)

Claude-Mem

Claude-Mem - Stop explaining context repeatedly. Build faster with persistent memory. (GitHub)

Note: Auto-compact is disabled in this setup to preserve full session history. image

Claude HUD

Claude HUD - Status line monitoring plugin for tracking context usage, active tools, running agents, and todo progress.

# Inside Claude Code, run:
/claude-hud:setup

image

The HUD appears immediately — no restart needed.

Try

Try - Fresh directories for every vibe. Instantly navigate through experiment directories with fuzzy search, smart sorting, and auto-dating. (Interactive Demo)

Claude Squad

Claude Squad - Terminal app to manage multiple AI agents (Claude Code, Aider, Codex, Gemini, etc.) in separate workspaces. Work on multiple tasks simultaneously with isolated git worktrees.

Spec Kit

Spec Kit - Toolkit for Spec-Driven Development. Create specifications, implementation plans, and task lists for new features and greenfield projects with AI-native workflow. (GitHub)

Backlog.md

Backlog.md - Markdown-native task manager and Kanban visualizer. Manage project backlogs entirely in Git with CLI, web interface, and AI integration. (npm)

📚 Best Practices

Setup includes best-practices.md with comprehensive software development guidelines based on:

Copy configs/best-practices.md to your preferred location and reference it in your AI tools.

📖 Resources

👤 Author

Dung Huynh

⭐ Show your support

Give a ⭐️ if this project helped you!

ko-fi

📝 Contributing

Contributions, issues and feature requests are welcome! See CONTRIBUTING.md.

Made with ❤️ by Dung Huynh