A Claude Code plugin that provides expert explanations through distinctive personas: Shakespeare for code narratives, Einstein for deep understanding, Steve Jobs for visionary direction, and Socrates for error debugging.
Question: "What is MCP?"
MCP stands for Model Context Protocol. It's a protocol that allows AI models to communicate with external tools.
MCP (Model Context Protocol) is an open standard that defines how AI assistants communicate with external tools and data sources. Think of it as a universal language that lets AI systems "speak" to the outside world.
AI models, no matter how intelligent, are inherently isolated. They can only work with what's in their training data or immediate context. MCP solves this by creating a standardized bridge.
Imagine a genius trapped inside a house. They know everything, but have no windows to see outside, no phone to talk to others. MCP provides those windows and phones.
MCP operates through three core components:
- Host: The application where the AI assistant runs (e.g., Claude Desktop)
- Server: External programs that provide specific capabilities (e.g., file system access, database queries)
- Protocol: The communication rules between them (based on JSON-RPC 2.0)
Just as USB is a standard that connects various devices to computers, MCP is a standard that connects various tools to AI. Before USB, each device needed a different port. Before MCP, each AI tool needed a different integration method.
- Developers: Build an MCP server once, it works with all MCP-compatible AIs
- Users: AI can safely read files, search the web, access databases
- Ecosystem: AI capabilities become extensible like plugins
See the difference? Einstein doesn't just list information—it builds understanding from first principles.
Question: "What should be the next feature for my todo app?"
You could add categories, due dates, notifications, or a calendar view.
Your todo app does what every other todo app does. It's fine. But "fine" doesn't change anyone's life.
People don't need another way to list tasks. They need a way to actually complete them. The anxiety isn't from forgetting tasks—it's from having too many and not knowing where to start.
Kill the list. Show ONE task.
When users open your app, don't show 47 items screaming for attention. Show them the single most important thing they should do right now. Everything else disappears until that's done.
- The "add task" button on the home screen (hide it)
- Categories (they create more anxiety)
- Badge counts (nobody needs to see "127 tasks remaining")
Imagine opening your todo app and feeling calm instead of overwhelmed. That's not a feature. That's a revolution.
See the difference? Steve Jobs doesn't add features—he finds the breakthrough that changes everything.
Question: "NullPointerException at UserService.java:42"
You have a NullPointerException. Add a null check before line 42:
if (user != null).
The stack trace shows
NullPointerExceptionatUserService.java:42. But this is merely where the error surfaced, not where it was born.
- Where did
usercome from? Traced to line 38:userRepository.findById(userId)- When can
findById()return null? When the ID doesn't exist in the database- Why wasn't this handled? The code assumes the user always exists
// Line 38: The assumption begins User user = userRepository.findById(userId); // Can return null! // Line 42: The assumption fails return user.getDisplayName(); // NPE when user is nullThe method assumes users always exist. This fails when:
- User was deleted between validation and retrieval
- Race condition in concurrent requests
- Invalid userId passed from upstream
Scenario Why It Fails Likelihood Deleted user No existence check Medium Cache inconsistency Cached ID, deleted from DB Medium User user = userRepository.findById(userId) .orElseThrow(() -> new UserNotFoundException(userId));Transforms a mysterious NPE into a clear business exception with context.
See the difference? Socrates doesn't patch symptoms—he traces errors to their root cause.
# Step 1: Add the marketplace
/plugin marketplace add rlaope/claude-code-savant
# Step 2: Install the plugin
/plugin install claude-code-savant# Clone the repository
git clone https://github.com/rlaope/claude-code-savant.git
cd claude-code-savant
# Run Claude Code with the plugin
claude --plugin-dir .After installation, the setup wizard runs automatically! (Or run manually: /savant-setup)
Configure your preferences:
- Language: English, 한국어, 日本語, or 中文
- Default Mode: Enable/disable auto-routing
Change language anytime:
/savant-lang # Interactive selection
/savant-lang en # English
/savant-lang kr # 한국어
/savant-lang jp # 日本語
/savant-lang ch # 中文Want Savant to automatically analyze ALL your questions? Enable default mode:
/savant-default # Enable - all questions auto-routed
/savant-default-off # Disable - return to normal ClaudeWhen enabled, just ask questions naturally - no commands needed!
Enjoying Claude Code Savant? If this plugin helps you, consider giving it a ⭐ on GitHub!
Don't know which persona to use? Just use /savant and let the AI analyze your question!
/savant [your question here]The Smart Router will:
- Analyze your question using Opus model
- Recommend the best persona with reasoning
- Ask for your confirmation before proceeding
- Execute with your chosen persona
| Command | Persona | Best For |
|---|---|---|
/savant-setup |
Setup Wizard | First-time configuration (language, default mode) |
/savant-lang |
Language | Change response language (en/kr/jp/ch) |
/savant-default |
Enable Default | Auto-route ALL questions (always-on mode) |
/savant-default-off |
Disable Default | Return to normal Claude behavior |
/savant |
Smart Router | Auto-detects and recommends the best persona |
/savant-question |
Einstein | General questions, deep explanations |
/savant-code |
Shakespeare | Code analysis with flowcharts |
/savant-new |
Steve Jobs | Project vision and next-step ideas |
/savant-fix |
Socrates | Error analysis, root cause debugging |
/savant-update |
Update | Check for updates and upgrade |
claude-code-savant:router # Smart question analyzer (uses Opus)
claude-code-savant:einstein # First principles explanations
claude-code-savant:shakespeare # Narrative with diagrams
claude-code-savant:stevejobs # Visionary direction and ideas
claude-code-savant:socrates # Error debugging and root cause analysis
# Let AI choose the best persona (Smart Router)
/savant What is dependency injection and why do we need it?
# Ask a question (Einstein)
/savant-question What is MCP?
# Analyze code (Shakespeare)
/savant-code Analyze this code
function fibonacci(n) {
if (n <= 1) return n;
return fibonacci(n-1) + fibonacci(n-2);
}
# Get project direction (Steve Jobs)
/savant-new What should be the next feature for this project?
# Debug an error (Socrates)
/savant-fix NullPointerException at UserService.java:42- Style: First principles thinking, scientific precision
- Strength: Deep understanding, thorough explanations
- Output: Structured analysis with analogies and practical implications
- Use when: You want to truly understand something, not just know about it
- Style: Narrative storytelling, dramatic structure
- Strength: Making complex flows understandable through story
- Output: Rich narratives with Mermaid flowcharts
- Use when: Analyzing code structure and flow visually
- Style: Bold, direct, user-obsessed thinking
- Strength: Seeing the next evolution and breakthrough opportunities
- Output: Clear vision with actionable ideas and what to kill
- Use when: You need direction on where to take your project next
- Style: Socratic questioning, systematic investigation
- Strength: Tracing errors to root causes, finding edge cases
- Output: Thorough error analysis with fixes and prevention strategies
- Use when: You have an error, stack trace, or bug to investigate
claude-code-savant/
├── .claude-plugin/
│ └── plugin.json # Plugin manifest
├── agents/
│ ├── router.md # Smart Router (question analyzer)
│ ├── einstein.md # Einstein persona definition
│ ├── shakespeare.md # Shakespeare persona definition
│ ├── stevejobs.md # Steve Jobs persona definition
│ └── socrates.md # Socrates persona definition
├── commands/
│ ├── install.md # Auto-runs on first install
│ ├── setup.md # /savant-setup (manual setup wizard)
│ ├── lang.md # /savant-lang (language settings)
│ ├── default.md # /savant-default (enable always-on mode)
│ ├── default-off.md # /savant-default-off (disable default mode)
│ ├── savant.md # /savant (smart router command)
│ ├── savant-question.md # /savant-question command
│ ├── savant-code.md # /savant-code command
│ ├── savant-new.md # /savant-new command
│ ├── savant-fix.md # /savant-fix command
│ └── update.md # /savant-update command
└── src/ # MCP server (alternative)
# Clone and test locally
git clone https://github.com/rlaope/claude-code-savant.git
cd claude-code-savant
claude --plugin-dir .
# Run tests
npm testCheck for updates and upgrade:
/savant-updateOr manually:
/plugin update claude-code-savantMIT