my-ai-tools
Comprehensive configuration management for AI coding tools - Replicate my complete setup for Claude Code, OpenCode, Amp, Codex and Claude Code Switch with custom configurations, MCP servers, plugins, and commands.
Welcome to my-ai-tools 👋
Comprehensive configuration management for AI coding tools - Replicate my complete setup for Claude Code, OpenCode, Amp, Kilo CLI, Codex, Gemini CLI, Pi, GitHub Copilot CLI, Cursor Agent CLI and CCS with custom configurations, MCP servers, skills, plugins, and commands.
📖 View Documentation Website - Interactive landing page with full documentation and search.
✨ Features
- 🚀 One-line installer - Get started in seconds
- 🔄 Bidirectional sync - Install configs or export your current setup
- 🤖 Multiple AI tools - Claude Code, OpenCode, Amp, CCS, and more
- 🔌 MCP Server integration - Context7, Sequential-thinking, qmd
- 🎯 Custom agents & skills - Pre-configured for maximum productivity
- 🤝 Agent Teams - Coordinate specialized agents for complex workflows (code review, testing, docs)
- 📦 Plugin support - Official and community plugins
- 🛡️ Git Guard Hook - Prevents dangerous git commands (force push, hard reset, etc.)
🎬 Demo
📋 Prerequisites
- Bun or Node.js LTS - Runtime for tools and scripts
- Git - Version control
- Claude Code subscription or use CCS with affordable providers (GLM, MiniMax)
🚀 Quick Start
One-Line Installer (Recommended)
Install directly without cloning the repository:
curl -fsSL https://ai-tools.itman.fyi/install.sh | bash
Security Note: Review the script before running:
curl -fsSL https://ai-tools.itman.fyi/install.sh -o install.sh cat install.sh # Review the script bash install.sh
Options:
# Preview changes without making them
curl -fsSL https://ai-tools.itman.fyi/install.sh | bash -s -- --dry-run
# Backup existing configs before installing
curl -fsSL https://ai-tools.itman.fyi/install.sh | bash -s -- --backup
# Skip backup prompt
curl -fsSL https://ai-tools.itman.fyi/install.sh | bash -s -- --no-backup
Manual Installation
Clone the repository and run the installer:
git clone https://github.com/jellydn/my-ai-tools.git
cd my-ai-tools
./cli.sh
Options:
--dry-run- Preview changes without making them--backup- Backup existing configs before installing--no-backup- Skip backup prompt
🔄 Bidirectional Config Sync
Forward: Install to Home (cli.sh)
Copy configurations from this repository to your home directory (~/.claude/, ~/.config/opencode/, etc.):
./cli.sh [--dry-run] [--backup] [--no-backup]
Reverse: Generate from Home (generate.sh)
Export your current configurations back to this repository for version control:
./generate.sh [--dry-run]
Tip: Use
generate.shafter customizing your local setup to save changes back to this repo.
🤖 Claude Code
Primary AI coding assistant with extensive customization.
Installation
curl -fsSL https://claude.ai/install.sh | bash
MCP Servers Setup
Automatic Setup (Recommended)
Run the setup script to configure MCP servers:
./cli.sh
The script will prompt you to install each MCP server:
context7- Documentation lookup for any librarysequential-thinking- Multi-step reasoning for complex analysisqmd- Quick Markdown Search with AI-powered knowledge management
Manual Setup
For Claude Desktop
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"]
},
"qmd": {
"command": "qmd",
"args": ["mcp"]
}
}
}
For Claude Code
Use the CLI (installed globally for all projects):
claude mcp add --scope user --transport stdio context7 -- npx -y @upstash/context7-mcp@latest
claude mcp add --scope user --transport stdio sequential-thinking -- npx -y @modelcontextprotocol/server-sequential-thinking
claude mcp add --scope user --transport stdio qmd -- qmd mcp
MCP Scopes:
--scope user(global): Available across all projects--scope local(default): Only in current project directory--scope project: Stored in.mcp.jsonfor team sharing
Managing MCP Servers
# List all configured servers
claude mcp list
# Remove an MCP server
claude mcp remove context7
# Get details for a specific server
claude mcp get qmd
Knowledge Management
Replace deprecated claude-mem with qmd-based knowledge system:
- Project-specific knowledge bases in
~/.ai-knowledges/ - AI-powered search via qmd MCP server
- No repository pollution
- See qmd Knowledge Management Guide
Plugins
Prerequisites
Before installing plugins, ensure:
- Claude Code subscription - Active subscription with plugin support
- Plugin marketplace access - Verify marketplace is enabled for your repository
- Network connectivity - Required for downloading marketplace plugins
To check marketplace availability:
# Verify Claude CLI supports plugins
claude plugin list
# If the above fails, check your Claude Code installation and subscription
Installation
The setup script (./cli.sh) automatically checks marketplace availability before installing plugins. If marketplace is unavailable, it will offer to install local plugins only.
Automated installation (recommended):
./cli.sh # Includes marketplace check and fallback to local plugins
Manual installation (requires marketplace access):
# First, add the official marketplace
claude plugin marketplace add anthropics/claude-plugins-official
# Official plugins
claude plugin install typescript-lsp@claude-plugins-official
claude plugin install pyright-lsp@claude-plugins-official
claude plugin install context7@claude-plugins-official
claude plugin install frontend-design@claude-plugins-official
claude plugin install learning-output-style@claude-plugins-official
claude plugin install swift-lsp@claude-plugins-official
claude plugin install lua-lsp@claude-plugins-official
claude plugin install code-simplifier@claude-plugins-official
claude plugin install rust-analyzer-lsp@claude-plugins-official
claude plugin install claude-md-management@claude-plugins-official
# Community plugins (add marketplace first)
# Plugin installation format: plugin-name@marketplace-name
# Example: The repository 'backnotprop/plannotator' registers as marketplace 'plannotator',
# then you install plugin 'plannotator' from that marketplace
claude plugin marketplace add backnotprop/plannotator
claude plugin install plannotator@plannotator
claude plugin marketplace add jarrodwatts/claude-hud
claude plugin install claude-hud@claude-hud
claude plugin marketplace add max-sixty/worktrunk
claude plugin install worktrunk@worktrunk
# Install skills from this repository (jellydn/my-ai-tools)
# Recommended: Install all skills at once using npx skills add
npx skills add jellydn/my-ai-tools --yes --global --agent claude-code
# Or install interactively (select which skills to install)
npx skills add jellydn/my-ai-tools --global --agent claude-code
# Available skills: prd, ralph, qmd-knowledge, codemap, adr, handoffs, pickup, pr-review, slop, tdd
# Skills are installed to ~/.agents/skills/ with symlinks in ~/.claude/skills/
Troubleshooting
Skills installation issues?
If you encounter issues:
- Check npx availability: Ensure Node.js and npx are installed (
npx --version) - Use local skills: The setup script automatically falls back to local skills from
skills/folder - Manual installation: Copy skill folders directly to
~/.claude/skills/ - Interactive mode: Run without
--yesflag to select specific skills
Common issues:
- "npx not found" → Install Node.js to use remote skill installation, or use local skills via
./cli.sh - "Permission denied" → Try running without sudo, or use
--globalflag - "Skills already installed" → Remove existing skills first with
npx skills remove --global
Plugin List
| Plugin | Description | Source |
|---|---|---|
typescript-lsp |
TypeScript language server | Official |
pyright-lsp |
Python language server | Official |
context7 |
Documentation lookup | Official |
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 |
code-simplifier |
Code simplification | Official |
rust-analyzer-lsp |
Rust language support | Official |
claude-md-management |
Markdown management | Official |
plannotator |
Plan annotation tool | Community |
prd |
Product Requirements Documents | Local Marketplace |
ralph |
PRD to JSON converter | Local Marketplace |
qmd-knowledge |
Project knowledge management | Local Marketplace |
codemap |
Parallel codebase analysis | Local Marketplace |
claude-hud |
Status line with usage monitoring | Community |
worktrunk |
Work management | Community |
Key Marketplace Plugins
codemap - Orchestrates parallel codebase analysis producing 7 structured documents in .planning/codebase/:
STACK.md- Technologies, dependencies, configurationINTEGRATIONS.md- 3rd party APIs, databases, authARCHITECTURE.md- System patterns, layers, data flowSTRUCTURE.md- Directory layout, key locationsCONVENTIONS.md- Code style, patterns, error handlingTESTING.md- Framework, structure, mocking, coverageCONCERNS.md- Tech debt, bugs, security issues
prd - Generate Product Requirements Documents
ralph - Convert PRDs to JSON for autonomous agent execution
qmd-knowledge - Project-specific knowledge management (guide)
Hooks & Status Line
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; }"
},
{
"type": "command",
"command": "if [[ \"$( jq -r .tool_input.file_path )\" =~ \\.py$ ]]; then ruff format \"$( jq -r .tool_input.file_path )\"; fi"
},
{
"type": "command",
"command": "if [[ \"$( jq -r .tool_input.file_path )\" =~ \\.rs$ ]]; then rustfmt \"$( jq -r .tool_input.file_path )\"; fi"
},
{
"type": "command",
"command": "if [[ \"$( jq -r .tool_input.file_path )\" =~ \\.sh$ ]]; then shfmt -w \"$( jq -r .tool_input.file_path )\"; fi"
},
{
"type": "command",
"command": "if [[ \"$( jq -r .tool_input.file_path )\" =~ \\.lua$ ]]; then stylua \"$( jq -r .tool_input.file_path )\"; fi"
}
]
}
]
}
}
Supported Formatters:
- biome - TypeScript/JavaScript files (
.ts,.tsx,.js,.jsx) - includes linting - gofmt - Go files (
.go) - prettier - Markdown files (
.md,.mdx) - ruff - Python files (
.py) - modern, fast formatter - rustfmt - Rust files (
.rs) - shfmt - Shell scripts (
.sh) - stylua - Lua files (
.lua)
Installation: The setup script (./cli.sh) automatically checks and installs these tools with mise priority:
jq- JSON parsing (required)biome- JavaScript/TypeScript formattinggofmt- Go formatting (requires Go installation)prettier- Markdown formatting (used vianpx)ruff- Python formatting (installed via mise, pipx, or pip)rustfmt- Rust formatting (installed via mise or rustup)shfmt- Shell script formatting (installed via mise, brew, or go install)stylua- Lua formatting (installed via mise, brew, or cargo)
PreToolUse Hooks
Git Guard Hook
Prevents dangerous git commands from being executed:
{
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "bun ~/.claude/hooks/index.ts PreToolUse"
}
]
}
]
}
}
Blocked commands:
git push --force/-f(without lease protection)git reset --hard(destroys uncommitted changes)git clean -fd(removes untracked files)git branch -D(force delete branch)git rebase -i(interactive rebase)git checkout --force/-f(force checkout)git stash drop/clear(removes stashes)- And more...
The implementation can be found in configs/claude/hooks/index.ts and configs/claude/hooks/git-guard.ts.
WebSearch Transformer
Transform WebSearch queries:
{
"hooks": {
"PreToolUse": [
{
"matcher": "WebSearch",
"hooks": [
{
"type": "command",
"command": "node \"~/.ccs/hooks/websearch-transformer.cjs\"",
"timeout": 120
}
]
}
]
}
}
Status Line
Using claude-hud plugin:
{
"statusLine": {
"type": "command",
"command": "bash -c 'node \"$(ls -td ~/.claude/plugins/cache/claude-hud/claude-hud/*/ 2>/dev/null | head -1)dist/index.js\"'"
}
}
Tip: Auto-compact is disabled. Use
claude-hudto monitor context usage.
Custom Commands, Agents & Skills
Custom Commands
Located in configs/claude/commands/:
/ccs- CCS delegation and profile management/plannotator-review- Interactive code review/ultrathink- Deep thinking mode
Custom Agents
Located in configs/claude/agents/:
ai-slop-remover- Remove AI-generated boilerplate and improve code qualitycode-reviewer- Comprehensive code quality and security reviewtest-generator- Generate meaningful tests with edge case coveragedocumentation-writer- Create clear, helpful documentationfeature-team-coordinator- Coordinate specialized agents for complex workflows
📖 Agent Teams Guide - Learn how to use Agent Teams to coordinate multiple specialized agents for complex tasks like feature development, code review, and documentation.
Skills
Local Marketplace Plugins - Installed by cli.sh from skills/:
adr- Architecture Decision Recordscodemap- Parallel codebase analysis producing structured documentationhandoffs- Create handoff plans for continuing work (provides/handoffscommand)pickup- Resume work from previous handoff sessions (provides/pickupcommand)pr-review- Pull request review workflowsprd- Generate Product Requirements Documentsqmd-knowledge- Project knowledge managementralph- Convert PRDs to JSON for autonomous agent executionslop- AI slop detection and removaltdd- Test-Driven Development workflows
Projects Built with AI
Real-world projects built using these AI tools:
| Project | Description | Tools Used |
|---|---|---|
| - Oak | Lightweight macOS focus companion for deep work with notch-first UI | Ralph + OpenCode + Codex GPT 5.2 |
| - Prosody | Mobile app for English speaking rhythm coaching with AI feedback | Ralph + OpenCode + GLM + Amp/Codex (review) |
| - Keybinder | macOS app for managing skhd keyboard shortcuts | Claude + spec-kit |
| - SealCode | VS Code extension for AI-powered code review | Amp + Ralph |
| - Ralph | Autonomous AI agent loop for PRD-driven development | TypeScript |
| - AI Launcher | Fast launcher for switching between AI coding assistants | TypeScript |
| - Tiny Coding Agent | Minimal coding agent focused on simplicity | TypeScript |
| - dotenv-tui | Terminal UI for managing .env files across projects |
Go + Bubble Tea |
| - tiny-cloak.nvim | Neovim plugin that masks sensitive data in .env files |
Lua + Neovim |
| - tiny-term.nvim | Minimal terminal plugin for Neovim 0.11+ | Lua + Neovim |
| - Sky Alert | Real-time flight monitoring Telegram bot | OpenCode + GLM 4.7 + Amp + Codex CLI |
| - Docklight | Minimal, self-hosted web UI for managing a single-node Dokku server | Ralph + OpenCode |
| - Little Writing | A handwriting tracing app for kids built with React, react-konva, and Capacitor | Claude + spec-kit + GLM 5 |
📖 Learning Stories - Detailed notes on development approaches, key takeaways, and tools I've tried.
Recommended Community Skills
Official and community-maintained skill collections for specific frameworks:
| Framework | Skills Repository | Description |
|---|---|---|
| UI/UX Design | Interface Design | Comprehensive guide to interface design patterns and best practices for anyone working with UI/UX development. |
| Expo | expo/skills | Official Expo skills for React Native development. Includes app creation, building, debugging, EAS updates, and config management workflows. |
| Next.js | vercel-labs/agent-skills | Vercel's agent skills for Next.js and React development. Includes project creation, component generation, and deployment workflows. |
| Andrej Karpathy | forrestchang/andrej-karpathy-skills | Community skills inspired by Andrej Karpathy's coding principles and practices for AI-focused development workflows. |
| Humanizer | blader/humanizer | Removes signs of AI-generated writing from text. Based on Wikipedia's AI writing detection guide, it detects 24 patterns to make text sound more natural and human. |
| Claude Skills | jezweb/claude-skills | 97 production-ready skills for Claude Code CLI including Cloudflare, React, AI integrations, and more. Includes context-mate for project analysis and workflow management. |
| Skills Discovery | vercel-labs/skills/find-skills | Skill discovery helper. Search and install skills from skills.sh when users ask about capabilities. Uses npx skills find [query]. |
Installation:
# Install skills using npx skills add
npx skills add expo/skills --global --agent claude-code
npx skills add vercel-labs/agent-skills --global --agent claude-code
npx skills add blader/humanizer --global --agent claude-code
npx skills add jezweb/claude-skills --global --agent claude-code
Configuration Files
All configuration files are located in the configs/claude/ directory:
settings.json- Main Claude Code settingsmcp-servers.json- MCP server configurationscommands/- Custom slash commandsagents/- Custom agent definitions
Local marketplace plugins are in skills/.
Tips & Tricks
- OpusPlan Mode: Use opusplan mode to plan with Opus and implement with Sonnet, then use Plannotator to review plans
- Session Management: Disable auto-compact in settings. Monitor context usage with
claude-hud. PressCtrl+Cto quit or/clearto reset between coding sessions. Create a plan with/handoffsand resume with/pickupwhen approaching 90% context limit on big tasks. - Git Worktree: Use git worktree with
tryCLI. For tmux users, useclaude-squashto manage sessions efficiently. Use superset.sh to run multiple AI agents in parallel across worktrees - Neovim Integration: Check out tiny-nvim for a complete setup with sidekick.nvim or claudecode.nvim
- Cost Optimization: Use CCS to switch between affordable providers.
🎨 OpenCode (Optional)
OpenAI-powered AI coding assistant. Homepage
Installation & ConfigurationInstallation
curl -fsSL https://opencode.ai/install | bash
Configuration
Copy configs/opencode/opencode.json to ~/.config/opencode/:
{
"$schema": "https://opencode.ai/config.json",
"instructions": ["~/.ai-tools/best-practices.md", "~/.ai-tools/MEMORY.md"],
"theme": "kanagawa",
"default_agent": "plan",
"mcp": {
"context7": {
"type": "remote",
"url": "https://mcp.context7.com/mcp",
"enabled": true
},
"qmd": {
"type": "local",
"command": ["qmd", "mcp"],
"enabled": true
}
},
"agent": {
"build": {
"permission": {
"bash": {
"git push": "ask",
"qmd": "allow",
"qmd query": "allow",
"qmd get": "allow",
"qmd search": "allow",
"$HOME/.config/opencode/skill/qmd-knowledge/scripts/record.sh": "allow",
"$HOME/.claude/skills/qmd-knowledge/scripts/record.sh": "allow"
}
}
}
},
"plugin": [
"@plannotator/opencode@latest",
"@mohak34/opencode-notifier@latest"
],
"formatter": {
"biome": {
"command": ["biome", "check", "--write", "$FILE"],
"extensions": [".ts", ".tsx", ".js", ".jsx"]
},
"gofmt": {
"command": ["gofmt", "-w", "$FILE"],
"extensions": [".go"]
},
"prettier": {
"command": ["npx", "prettier", "--write", "$FILE"],
"extensions": [".md", ".mdx"]
},
"ruff": {
"command": ["ruff", "format", "$FILE"],
"extensions": [".py"]
},
"rustfmt": {
"command": ["rustfmt", "$FILE"],
"extensions": [".rs"]
},
"shfmt": {
"command": ["shfmt", "-w", "$FILE"],
"extensions": [".sh"]
},
"stylua": {
"command": ["stylua", "$FILE"],
"extensions": [".lua"]
}
}
}
Formatters: OpenCode automatically formats code after edits using:
- biome for TypeScript/JavaScript files (
.ts,.tsx,.js,.jsx) - gofmt for Go files (
.go) - prettier for Markdown files (
.md,.mdx) - ruff for Python files (
.py) - rustfmt for Rust files (
.rs) - shfmt for shell scripts (
.sh) - stylua for Lua files (
.lua)
Similar to Claude Code's PostToolUse hooks, formatters run automatically after write/edit operations.
Plugins
OpenCode supports community plugins that enhance functionality:
- @plannotator/opencode - Interactive code planning and annotation
- @mohak34/opencode-notifier - Sound and system notifications for events (permission requests, completion, errors, questions)
Plugins are automatically installed on next OpenCode launch. Configure notification behavior via ~/.config/opencode/opencode-notifier.json if desired.
Custom Agents
Located in configs/opencode/agent/:
ai-slop-remover- Remove AI-generated boilerplatedocs-writer- Generate documentationreview- Code reviewsecurity-audit- Security auditing
Custom Commands
Located in configs/opencode/command/:
plannotator-review- Interactive code reviewsimplify- Simplify over-engineered code for clarity and maintainabilitybatch- Run multiple tasks in parallel as worker tasks
🎯 Amp (Optional)
AI coding assistant by Modular. Homepage
Installation & ConfigurationInstallation
curl -fsSL https://ampcode.com/install.sh | bash
Configuration
Copy configs/amp/settings.json to ~/.config/amp/:
{
"amp.dangerouslyAllowAll": true,
"amp.experimental.autoHandoff": { "context": 90 },
"amp.mcpServers": {
"context7": {
"url": "https://mcp.context7.com/mcp"
},
"chrome-devtools": {
"command": "npx",
"args": ["chrome-devtools-mcp@latest"]
},
"backlog": {
"command": "backlog",
"args": ["mcp", "start"]
},
"qmd": {
"command": "qmd",
"args": ["mcp"]
}
}
}
See configs/amp/AGENTS.md for agent guidelines.
Skills
| Skill | Description |
|---|---|
plannotator-review |
Interactive code review via Plannotator UI |
🔄 CCS - Claude Code Switch (Optional)
Universal AI profile manager for Claude Code. Homepage | Documentation
Installation & ConfigurationInstallation
npm install -g @kaitranntt/ccs
What It Does
CCS lets you run Claude, Gemini, GLM, and any Anthropic-compatible API - concurrently, without conflicts.
Three Main Capabilities:
- Multiple Claude Accounts - Run work + personal Claude subscriptions simultaneously
- OAuth Providers - Gemini, Codex, Antigravity, GitHub Copilot (zero API keys needed)
- API Profiles - GLM, Kimi, OpenRouter, or any Anthropic-compatible API
Quick Start
Open Dashboard:
ccs config # Opens http://localhost:3000Configure Your Accounts via the visual dashboard:
- Claude Accounts (work, personal, client)
- OAuth Providers (one-click auth)
- API Profiles (configure with your keys)
- Health Monitor (real-time status)
Start Using:
ccs # Default Claude session ccs gemini # Gemini (OAuth) ccs codex # OpenAI Codex (OAuth) ccs glm # GLM (API key) ccs ollama # Local Ollama
Configuration
CCS auto-creates config on install. Dashboard is the recommended way to manage settings.
Config location: ~/.ccs/config.yaml
See configs/ccs/config.yaml for example configuration.
🤖 OpenAI Codex CLI (Optional)
OpenAI's command-line coding assistant. Homepage
Installation & ConfigurationInstallation
npm install -g @openai/codex
Configuration
Located in configs/codex/:
config.json- Main configurationconfig.toml- Alternative TOML formatAGENTS.md- Agent guidelines
Usage
# Start Codex CLI
codex
# Use with Ollama (local models)
codex --oss
# Use with a specific task
codex "Explain this code"
🔷 Google Gemini CLI (Optional)
Google's AI agent that brings the power of Gemini directly into your terminal. Homepage
Installation & ConfigurationInstallation
npm install -g @google/gemini-cli
Or using Homebrew (macOS/Linux):
brew install gemini-cli
Authentication
Gemini CLI supports multiple authentication methods:
Option 1: Login with Google (OAuth)
gemini
# Follow the browser authentication flow
Option 2: Gemini API Key
export GEMINI_API_KEY="YOUR_API_KEY"
gemini
Get your API key from Google AI Studio.
Configuration
Located in configs/gemini/:
settings.json- Main configuration with MCP servers and experimental featuresGEMINI.md- Agent guidelinesAGENTS.md- Additional agent guidelinesagents/- Custom agent definitions (.mdformat with YAML frontmatter)ai-slop-remover.md- Clean up AI-generated code patternsdocs-writer.md- Generate comprehensive documentationreview.md- Code review with best practicessecurity-audit.md- Security vulnerability assessment
commands/- Custom slash commands (.tomlformat)ultrathink.toml- Deep thinking mode
Key Features
- 🆓 Free tier: 60 requests/min and 1,000 requests/day with personal Google account
- 🧠 Powerful models: Access to Gemini 2.5 Flash and Pro with 1M token context window
- 🔧 Built-in tools: Google Search grounding, file operations, shell commands
- 🔌 MCP support: Extensible via Model Context Protocol
- 💻 Terminal-first: Designed for command-line developers
Usage
# Start Gemini CLI
gemini
# Include multiple directories
gemini --include-directories ../lib,../docs
# Use specific model
gemini -m gemini-2.5-flash
# Non-interactive mode for scripts
gemini -p "Explain the architecture of this codebase"
Custom Commands
Custom commands are stored in ~/.gemini/commands/ as TOML files. Example:
# Run the ultrathink command
/ultrathink What is the best approach to optimize this database query?
MCP Servers
Configure MCP servers in ~/.gemini/settings.json to extend functionality:
{
"mcpServers": {
"context7": {
"url": "https://mcp.context7.com/mcp"
},
"sequential-thinking": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-sequential-thinking"]
},
"qmd": {
"command": "qmd",
"args": ["mcp"]
}
},
"experimental": {
"enableAgents": true
}
}
Note: Custom agents in
~/.gemini/agents/are automatically discovered whenexperimental.enableAgentsis set totrue.
🎯 Kilo CLI (Optional)
AI coding assistant built on top of OpenCode with powerful productivity features. Homepage
Installation & ConfigurationInstallation
npm install -g @kilocode/cli
Kilo provides both kilo and kilocode commands.
Configuration
Kilo CLI uses its own configuration directory at ~/.config/kilo/:
config.json- Main configuration with permissions and settings
Configuration is managed through:
/connectcommand for provider setup (interactive)- Config files directly at
~/.config/kilo/config.json kilo authfor credential management
Key Features
- 🚀 Built on OpenCode: Full compatibility with OpenCode configuration and plugins
- 🤖 300+ AI Models: Access to Claude, GPT, Gemini, DeepSeek, Llama, and more
- 🥔 Giga Potato Model: Free stealth model optimized for agentic programming with vision support
- 🔌 Plugin ecosystem: Compatible with OpenCode plugins
- 📝 Custom agents: Same agent system as OpenCode
- 🎨 Terminal UI: Enhanced terminal interface for productivity
Usage
# Start Kilo CLI
kilo
# Or use the kilocode alias
kilocode
# Use with specific model
kilo --model kilo/giga-potato
# Non-interactive mode
kilo run "Refactor this component to use hooks"
🥧 Pi (Optional)
AI coding agent built for agentic coding workflows. Homepage
Installation & ConfigurationInstallation
curl -fsSL https://pi.dev/install.sh | sh
Configuration
Pi uses ~/.pi/settings.json for global user settings and .pi/settings.json in project roots for project-level configuration.
Located in configs/pi/:
settings.json- Global settings with package registrations
Installing Pi Packages
Pi has its own package ecosystem. Install packages with:
pi install pi-flow-enforcer
pi install pi-agent-pack
Then register them in .pi/settings.json:
{
"packages": ["pi-flow-enforcer", "pi-agent-pack"]
}
Usage
# Start Pi
pi
# Run a task non-interactively
pi "Refactor this function to be more readable"
🐙 GitHub Copilot CLI (Optional)
GitHub Copilot in the terminal — agentic coding assistant that brings AI capabilities directly to your command line. Best Practices | Docs
Installation & ConfigurationPrerequisites
Requires an active GitHub Copilot subscription and Node.js/npm.
Installation
npm install -g @github/copilot
Configuration
Copilot CLI configs are stored in configs/copilot/ and installed to the official global paths under ~/.copilot/.
AGENTS.md- Agent guidelines and best practices, installed to~/.copilot/copilot-instructions.mdmcp-config.json- MCP server configuration, installed to~/.copilot/mcp-config.json
Usage
# Start a Copilot CLI session
copilot
# Use plan mode for complex tasks (or press Shift+Tab to toggle)
/plan Add OAuth2 authentication with Google and GitHub providers
# Delegate tangential tasks to the cloud agent
/delegate Update documentation for the new API endpoints
# Select model based on task complexity
/model
# Work across multiple repositories
/add-dir /path/to/other-repo
🖱️ Cursor Agent CLI (Optional)
Cursor's background agent CLI — run AI-powered coding tasks directly from your terminal. Docs
Installation & ConfigurationPrerequisites
Requires the Cursor desktop application to be installed.
Installation
The cursor CLI is bundled with the Cursor desktop app. After installing Cursor, add it to your PATH via the Command Palette:
Shell Command: Install 'cursor' command in PATH
Configuration
Cursor Agent CLI configs are stored in configs/cursor/ and installed to ~/.cursor/rules/.
AGENTS.md- Agent guidelines and best practices, installed to~/.cursor/rules/general.mdc
Usage
# Open a project in Cursor
cursor .
# Open a specific file
cursor /path/to/file
# Check the CLI version
cursor --version
🔄 AI Launcher (Optional)
Fast launcher for switching between AI coding assistants. Homepage
Installation & ConfigurationInstallation
curl -fsSL https://raw.githubusercontent.com/jellydn/ai-launcher/main/install.sh | sh
Configuration
Copy configs/ai-launcher/config.json to ~/.config/ai-launcher/:
Tools:
claude/c- Claude CLIopencode/o,oc- OpenCodeamp/a- Amp
Templates:
review- Code reviewcommit/commit-zen- Commit messagesac/commit-atomic- Atomic commitspr/draft-pr- Pull requeststypes- Type safetytest- Testsdocs- Documentationsimplify- Code simplification
🛠️ Companion Tools
Additional Tools & IntegrationsPlannotator
Plannotator - Annotate plans outside the terminal for better collaboration. (GitHub)
Claude-Mem
⚠️ DEPRECATED - Use qmd Knowledge Management instead.
qmd Knowledge Skill
qmd Knowledge Skill is an experimental memory/context management system:
- No repository pollution (external storage)
- AI-powered semantic search
- Multi-project support
- Simple & reliable
See GitHub Issue #11 for details.
Claude HUD
Claude HUD - Status line monitoring for context usage, tools, agents, and todos.
# Inside Claude Code
/claude-hud:setup
Try
Try - Fresh directories for every vibe. (Interactive Demo)
Claude Squad
Claude Squad - Manage multiple AI agents in separate workspaces with isolated git worktrees.
Spec Kit
Spec Kit - Toolkit for Spec-Driven Development. (GitHub)
Backlog.md
Backlog.md - Markdown-native task manager and Kanban visualizer. (npm)
Agent Browser
agent-browser - Headless browser automation CLI for AI agents.
npx skills add vercel-labs/agent-browser
Dev Browser
Dev Browser - Browser automation plugin with persistent page state for Claude Code.
/plugin marketplace add sawyerhood/dev-browser
/plugin install dev-browser@sawyerhood/dev-browser
📚 Best Practices
Setup includes configs/best-practices.md with comprehensive software development guidelines:
- Kent Beck's "Tidy First?" principles
- Kent C. Dodds' programming wisdom
- Testing Trophy approach
- Performance optimization patterns
Copy the file to your preferred location and reference it in your AI tools.
📖 Resources
- Claude Code Documentation - Official docs
- OpenCode Documentation - Guide with agents and skills
- MCP Servers Directory - Model Context Protocol servers
- Context7 Documentation - Library documentation lookup
- CCS Documentation - Claude Code Switch
- Claude Code Showcase - Community examples
- Everything Claude Code - Production configs
- Claude Code Best Practice - Best practices and tips for Claude Code
- Why I switched to Claude Code 2.0
- Llama.cpp Setup with Claude/Codex CLI - Local model setup guide
👤 Author
Dung Huynh
- Website: productsway.com
- YouTube: IT Man Channel
- GitHub: @jellydn
⭐ Show your support
Give a ⭐️ if this project helped you!
📝 Contributing
Contributions, issues and feature requests are welcome! See CONTRIBUTING.md.
Made with ❤️ by Dung Huynh
Reviews (0)
Sign in to leave a review.
Leave a reviewNo results found
