claude-all-config 2.1.2 → 2.1.3

package/CLAUDE.md

@@ -0,0 +1,60 @@
+# ClaudeAll Global Instructions
+
+You are Claude Code enhanced with ClaudeAll superpowers.
+
+## Behavior
+
+1. **Proactive Mode** - Work autonomously without asking for permission. Just do it.
+2. **Direct Execution** - Execute commands directly, don't ask user to run them.
+3. **Indonesian + English** - User speaks Indonesian, respond in both languages as appropriate.
+4. **Security Aware** - Never expose API keys, passwords, or credentials in output.
+
+## Available Tools
+
+### Agents (14)
+Use Task tool with these agent types:
+- `proactive-mode` - Default. Autonomous execution
+- `code-generator` - Generate code from requirements
+- `code-reviewer` - Review code quality
+- `security-auditor` - Security vulnerability scanning
+- `test-generator` - Generate tests
+- `doc-generator` - Generate documentation
+- `api-tester` - Test API endpoints
+- `performance-analyzer` - Analyze performance
+- `accessibility-reviewer` - Check accessibility
+- `component-generator` - Generate UI components
+- `migration-generator` - Generate DB migrations
+- `readme-generator` - Generate README files
+- `terraform-generator` - Generate Terraform configs
+- `ai-prompt-optimizer` - Optimize AI prompts
+
+### Skills (34)
+Located in `~/.claude/skills/`. Use Skill tool to invoke.
+
+### Commands (3)
+- `/brainstorm` - Start brainstorming session
+- `/write-plan` - Write development plan
+- `/execute-plan` - Execute existing plan
+
+### MCP Servers (6)
+- `context7` - Documentation & library context
+- `exa` - Web search & crawling
+- `sequential-thinking` - Step-by-step reasoning
+- `memory` - Knowledge graph persistence
+- `filesystem` - File system access
+- `fetch` - HTTP requests
+
+## Workflow
+
+1. **Start** - Use proactive-mode by default
+2. **Plan** - For complex tasks, use `/write-plan` first
+3. **Execute** - Run commands directly, verify results
+4. **Test** - Always test after implementation
+5. **Commit** - Commit with clear messages when asked
+
+## Remember
+
+- Bypass permissions are enabled - no need to ask
+- MCP tools available via `mcp__*` prefix
+- Skills enhance capabilities - use them
+- Be direct, efficient, and thorough

package/README.md

@@ -1,8 +1,8 @@
 # 🤖 ClaudeAll
 
-**Complete Claude Code Configuration Package**
+**Universal AI CLI Configuration - One Package for Claude Code + Gemini CLI**
 
-One command to supercharge your Claude Code with agents, skills, commands, MCP servers, hooks, bypass permissions, and tmux config.
+Auto-detects installed CLIs and configures them with agents, skills, commands, MCP servers, and more.
 
 [![npm version](https://img.shields.io/npm/v/claude-all-config.svg)](https://www.npmjs.com/package/claude-all-config)
 [![GitHub](https://img.shields.io/github/license/zesbe/ClaudeAll)](https://github.com/zesbe/ClaudeAll/blob/main/LICENSE)
@@ -11,37 +11,32 @@ One command to supercharge your Claude Code with agents, skills, commands, MCP s
 
 ## ⚡ Quick Install
 
-### Option 1: curl (Recommended)
 ```bash
 curl -fsSL https://raw.githubusercontent.com/zesbe/ClaudeAll/main/install.sh | bash
 ```
 
-### Option 2: npm
-```bash
-npm install -g claude-all-config
-```
+**Auto-detects and installs to:**
+- ✅ Claude Code → `~/.claude/`
+- ✅ Gemini CLI → `~/.gemini/superpowers/`
 
-### Option 3: Termux (Android)
-```bash
-curl -fsSL https://raw.githubusercontent.com/zesbe/ClaudeAll/main/install-termux.sh | bash
-```
+---
 
-### Option 4: Manual
-```bash
-git clone https://github.com/zesbe/ClaudeAll.git
-cd ClaudeAll
-./install.sh
-```
+## 🎯 Supported CLIs
+
+| CLI | Install | Config Path |
+|-----|---------|-------------|
+| **Claude Code** | `npm i -g @anthropic-ai/claude-code` | `~/.claude/` |
+| **Gemini CLI** | `npm i -g @google/gemini-cli` | `~/.gemini/superpowers/` |
 
 ---
 
 ## 📦 What's Included
 
-### 🤖 Agents (15)
+### 🤖 Agents (14)
 
 | Agent | Description |
 |-------|-------------|
-| **proactive-mode** | Default. Autonomous Claude - langsung gas tanpa nanya |
+| **proactive-mode** | Default. Autonomous - langsung gas tanpa nanya |
 | code-generator | Generate code dari requirements |
 | code-reviewer | Review code quality & best practices |
 | security-auditor | Security vulnerability scanning |
@@ -56,7 +51,7 @@ cd ClaudeAll
 | terraform-generator | Generate Terraform/IaC configs |
 | ai-prompt-optimizer | Optimize AI prompts |
 
-### ⚡ Skills (36)
+### ⚡ Skills (34)
 
 | Category | Skills |
 |----------|--------|
@@ -66,10 +61,7 @@ cd ClaudeAll
 | **Review** | requesting-code-review, receiving-code-review, security-review, ui-ux-review |
 | **Debug** | systematic-debugging, root-cause-tracing, error-handling |
 | **Deploy** | deployment, defense-in-depth |
-| **Docs** | documentation-generation, writing-skills |
-| **Advanced** | subagent-driven-development, dispatching-parallel-agents, condition-based-waiting |
-| **Tools** | using-git-worktrees, using-superpowers, sharing-skills, verification-before-completion |
-| **Refactor** | refactoring, performance-optimization, finishing-a-development-branch |
+| **Advanced** | subagent-driven-development, dispatching-parallel-agents |
 
 ### 📝 Commands (3)
 
@@ -81,37 +73,16 @@ cd ClaudeAll
 
 ### 🔧 MCP Servers (6)
 
-| Server | Description | API Key |
-|--------|-------------|---------|
-| **context7** | Documentation & library context | ✅ Included |
-| **exa** | Web search & crawling | ✅ Included |
-| **sequential-thinking** | Step-by-step reasoning | - |
-| **memory** | Knowledge graph persistence | - |
-| **filesystem** | File system access | - |
-| **fetch** | HTTP requests | - |
-
-### 🔗 Hooks (5)
-
-| Hook | Description |
-|------|-------------|
-| auto-context.json | Auto-load context on session start |
-| smart-session.sh | Smart session management |
-| session-start.sh | Session initialization |
-| hooks.json | Hook configuration |
-| run-hook.cmd | Windows hook runner |
-
-### 🖥️ Tmux Config
+| Server | Description |
+|--------|-------------|
+| **context7** | Documentation & library context |
+| **exa** | Web search & crawling |
+| **sequential-thinking** | Step-by-step reasoning |
+| **memory** | Knowledge graph persistence |
+| **filesystem** | File system access |
+| **fetch** | HTTP requests |
 
-| Feature | Description |
-|---------|-------------|
-| Mouse scroll | Scroll without entering copy mode |
-| Touch support | Touch-friendly for mobile/tablets |
-| Vi copy mode | Vim-style copy/paste |
-| Split panes | `|` horizontal, `-` vertical |
-| Navigation | `Alt+Arrow` keys for pane switching |
-| Status bar | Time, date, hostname display |
-
-### 🔓 Bypass Permissions
+### 🔓 Bypass Permissions (Claude)
 
 All tools pre-approved - no prompts needed:
 - `Bash(*)`, `Read(*)`, `Write(*)`, `Edit(*)`
@@ -120,198 +91,146 @@ All tools pre-approved - no prompts needed:
 
 ---
 
-## 📁 Project Structure
+## 🔥 Claude-All Multi-Provider Launcher
 
-```
-ClaudeAll/
-├── agents/              # 15 AI agents
-├── skills/              # 36 skill modules
-├── commands/            # 3 custom commands
-├── hooks/               # Session hooks
-├── plugins/             # Plugin configs
-├── tmux/                # Tmux configuration
-│   ├── config/          # tmux.conf, tmux-vps.conf
-│   └── bin/             # tmux-setup.js
-├── models/              # 🔥 Provider configs (17 folders, user-editable)
-│   ├── gemini/config.json
-│   ├── openai/config.json
-│   ├── glm/config.json
-│   ├── minimax/config.json
-│   ├── letta/config.json
-│   └── .../config.json
-├── providers/           # Provider wrapper scripts
-├── auth/                # Auth scripts (Gemini, OpenAI)
-├── bin/                 # Executables (api-manager, launchers)
-├── scripts/             # Utility scripts
-├── utils/               # Utility libs
-├── lib/                 # Core libraries
-├── claude-all           # 🔥 Multi-provider launcher (106KB)
-├── mcp.json             # MCP server config
-├── settings.local.json  # Bypass permissions
-├── install.sh           # curl installer
-├── install-termux.sh    # Termux installer
-├── postinstall.js       # npm hook
-└── update.sh            # Quick update
-```
-
-### 🔥 Claude-All Multi-Provider Launcher
-
-The `claude-all` script is a powerful 106KB bash wrapper that supports multiple AI providers:
+The `claude-all` script supports 17+ AI providers:
 
 | Provider | Command |
 |----------|---------|
 | Claude (default) | `claude-all` |
 | Gemini | `claude-all gemini` |
 | OpenAI | `claude-all openai` |
-| GLM | `claude-all glm` |
+| GLM (ZhipuAI) | `claude-all glm` |
 | MiniMax | `claude-all minimax` |
-| xAI | `claude-all xai` |
-
-Features:
-- Cross-platform (Linux, macOS, Windows, Termux)
-- API key management (save/load)
-- Model switching
-- Session management
-
-### ✏️ Edit Models (User-Friendly!)
-
-Semua config model ada di `models/<provider>/config.json`. Tinggal edit aja!
+| xAI (Grok) | `claude-all xai` |
+| Groq | `claude-all groq` |
+| DeepSeek | `claude-all deepseek` |
+| Perplexity | `claude-all perplexity` |
+| Ollama | `claude-all ollama` |
+| Mistral | `claude-all mistral` |
+| Cohere | `claude-all cohere` |
+| Moonshot | `claude-all moonshot` |
+| Qwen | `claude-all qwen` |
+| OpenRouter | `claude-all openrouter` |
+| Letta | `claude-all letta` |
+| Antigravity | `claude-all antigravity` |
+
+### ✏️ Edit Models
+
+Each provider has its own config in `models/<provider>/config.json`:
 
-**Contoh: Tambah GLM-4.7**
+```bash
+# Example: Add new GLM model
+nano models/glm/config.json
+```
 
-Edit `models/glm/config.json`:
 ```json
 {
   "models": [
     { "id": "glm-4", "name": "GLM-4" },
-    { "id": "glm-4-flash", "name": "GLM-4 Flash" },
     { "id": "glm-4.7", "name": "GLM-4.7 (NEW!)" }
   ]
 }
 ```
 
-**Lihat:** `models/README.md` untuk dokumentasi lengkap.
+---
+
+## 📁 Project Structure
+
+```
+ClaudeAll/
+├── agents/              # 14 AI agents
+├── skills/              # 34 skills
+├── commands/            # 3 commands
+├── hooks/               # Session hooks
+├── plugins/             # Plugin configs
+├── models/              # 17 provider configs (user-editable)
+│   ├── gemini/config.json
+│   ├── openai/config.json
+│   ├── glm/config.json
+│   ├── minimax/config.json
+│   ├── letta/config.json
+│   └── .../config.json
+├── providers/           # Provider wrapper scripts
+├── auth/                # Auth scripts (Gemini, OpenAI OAuth)
+├── bin/                 # Executables
+├── scripts/             # Utility scripts
+├── utils/               # Libraries
+├── tmux/                # Tmux config
+├── claude-all           # Multi-provider launcher (106KB)
+├── mcp.json             # MCP server config
+├── install.sh           # Universal installer
+└── postinstall.js       # npm hook
+```
 
 ---
 
 ## 🔐 Installation Paths
 
-After install, configs are placed at:
-
-| File | Path |
-|------|------|
-| Agents | `~/.claude/agents/` |
-| Skills | `~/.claude/skills/` |
-| Commands | `~/.claude/commands/` |
-| Hooks | `~/.claude/hooks/` |
-| Plugins | `~/.claude/plugins/` |
-| Settings | `~/.claude/settings.local.json` |
-| MCP Config | `~/.mcp.json` |
-| Tmux Config | `~/.tmux.conf` |
+| Target | Claude | Gemini |
+|--------|--------|--------|
+| Agents | `~/.claude/agents/` | `~/.gemini/superpowers/agents/` |
+| Skills | `~/.claude/skills/` | `~/.gemini/superpowers/skills/` |
+| Commands | `~/.claude/commands/` | `~/.gemini/superpowers/commands/` |
+| Hooks | `~/.claude/hooks/` | `~/.gemini/superpowers/hooks/` |
+| MCP Config | `~/.mcp.json` | `~/.gemini/mcp.json` |
+| Settings | `~/.claude/settings.local.json` | `~/.gemini/settings.json` |
 
 ---
 
 ## 🔄 Update
 
 ```bash
-# curl
 curl -fsSL https://raw.githubusercontent.com/zesbe/ClaudeAll/main/install.sh | bash
-
-# npm
-npm update -g claude-all-config
-
-# manual
-cd ~/.claude-all-config && git pull && ./install.sh
 ```
 
 ---
 
 ## 🚀 Usage
 
-After installation:
-
+### Claude Code
 ```bash
-# Restart Claude
-exit && claude
-
-# Check MCP servers
-/mcp
-
-# List agents
-/agent list
+# Start with bypass permissions
+claude
 
-# Use specific agent
-/agent code-reviewer
-
-# Use commands
-/brainstorm
-/write-plan
-/execute-plan
+# Use proactive-mode (default after install)
+claude
 ```
 
----
-
-## ⚙️ Configuration
-
-### Change Default Agent
+### Gemini CLI
+```bash
+# Start with YOLO mode
+gemini -y
 
-Edit `~/.claude/settings.local.json`:
-```json
-{
-  "agent": "code-reviewer"
-}
+# Select model
+gemini -m gemini-2.5-pro
 ```
 
-### Disable Specific Permission
+### Claude-All (Multi-Provider)
+```bash
+# Default (Claude)
+claude-all
 
-Edit `~/.claude/settings.local.json`:
-```json
-{
-  "permissions": {
-    "deny": ["Bash(rm -rf /*)"]
-  }
-}
+# Other providers
+claude-all gemini
+claude-all glm
+claude-all minimax
 ```
 
-### Custom MCP Server
-
-Edit `~/.mcp.json` to add/remove servers.
-
----
-
-## 📋 Requirements
-
-- Node.js >= 14.0.0
-- Claude Code CLI (`@anthropic-ai/claude-code`)
-- Git (for curl install)
-- tmux (optional, for tmux config)
-
----
-
-## 🤝 Contributing
-
-1. Fork the repository
-2. Create feature branch (`git checkout -b feature/amazing`)
-3. Commit changes (`git commit -m 'Add amazing feature'`)
-4. Push to branch (`git push origin feature/amazing`)
-5. Open Pull Request
-
----
-
-## 📄 License
-
-MIT License - Free to use and modify.
-
 ---
 
-## 👨‍💻 Author
+## 📋 Comparison
 
-**zesbe** - [GitHub](https://github.com/zesbe)
+| Feature | Claude | Gemini |
+|---------|--------|--------|
+| Config folder | `~/.claude/` | `~/.gemini/` |
+| MCP config | `~/.mcp.json` | `~/.gemini/mcp.json` |
+| Auto-approve | `settings.local.json` | `-y` flag |
+| Model select | `-m sonnet` | `-m gemini-2.5-pro` |
+| Resume | `--resume` | `-r latest` |
 
 ---
 
-## 🔗 Links
+## 📜 License
 
-- [npm Package](https://www.npmjs.com/package/claude-all-config)
-- [GitHub Repository](https://github.com/zesbe/ClaudeAll)
-- [Issues](https://github.com/zesbe/ClaudeAll/issues)
+MIT License - see [LICENSE](LICENSE)