Note: The original unmodified leaked source is preserved in the backup branch.

Claude Code - Leaked Source (2026-03-31)

On March 31, 2026, the full source code of Anthropic's Claude Code CLI was leaked via a .map file exposed in their npm registry.

How It Leaked

Chaofan Shou (@Fried_rice) discovered the leak and posted it publicly:

"Claude code source code has been leaked via a map file in their npm registry!"

• @Fried_rice, March 31, 2026

The source map file in the published npm package contained a reference to the full, unobfuscated TypeScript source, which was downloadable as a zip archive from Anthropic's R2 storage bucket.

Overview

Claude Code is Anthropic's official CLI tool that lets you interact with Claude directly from the terminal to perform software engineering tasks - editing files, running commands, searching codebases, managing git workflows, and more.

This repository contains the leaked src/ directory.

• Leaked on: 2026-03-31
• Language: TypeScript
• Runtime: Bun
• Terminal UI: React + Ink (React for CLI)
• Scale: ~1,900 files, 512,000+ lines of code

Directory Structure

src/
|- main.tsx                 # Entrypoint (Commander.js-based CLI parser)
|- commands.ts              # Command registry
|- tools.ts                 # Tool registry
|- Tool.ts                  # Tool type definitions
|- QueryEngine.ts           # LLM query engine (core Anthropic API caller)
|- context.ts               # System/user context collection
|- cost-tracker.ts          # Token cost tracking
|
|- commands/                # Slash command implementations (~50)
|- tools/                   # Agent tool implementations (~40)
|- components/              # Ink UI components (~140)
|- hooks/                   # React hooks
|- services/                # External service integrations
|- screens/                 # Full-screen UIs (Doctor, REPL, Resume)
|- types/                   # TypeScript type definitions
|- utils/                   # Utility functions
|
|- bridge/                  # IDE integration bridge (VS Code, JetBrains)
|- coordinator/             # Multi-agent coordinator
|- plugins/                 # Plugin system
|- skills/                  # Skill system
|- keybindings/             # Keybinding configuration
|- vim/                     # Vim mode
|- voice/                   # Voice input
|- remote/                  # Remote sessions
|- server/                  # Server mode
|- memdir/                  # Memory directory (persistent memory)
|- tasks/                   # Task management
|- state/                   # State management
|- migrations/              # Config migrations
|- schemas/                 # Config schemas (Zod)
|- entrypoints/             # Initialization logic
|- ink/                     # Ink renderer wrapper
|- buddy/                   # Companion sprite (Easter egg)
|- native-ts/               # Native TypeScript utils
|- outputStyles/            # Output styling
|- query/                   # Query pipeline
+- upstreamproxy/           # Proxy configuration

Core Architecture

1. Tool System (src/tools/)

Every tool Claude Code can invoke is implemented as a self-contained module. Each tool defines its input schema, permission model, and execution logic.

2. Command System (src/commands/)

User-facing slash commands invoked with / prefix.

3. Service Layer (src/services/)

4. Bridge System (src/bridge/)

A bidirectional communication layer connecting IDE extensions (VS Code, JetBrains) with the Claude Code CLI.

• bridgeMain.ts - Bridge main loop
• bridgeMessaging.ts - Message protocol
• bridgePermissionCallbacks.ts - Permission callbacks
• replBridge.ts - REPL session bridge
• jwtUtils.ts - JWT-based authentication
• sessionRunner.ts - Session execution management

5. Permission System (src/hooks/toolPermission/)

Checks permissions on every tool invocation. Either prompts the user for approval/denial or automatically resolves based on the configured permission mode (default, plan, bypassPermissions, auto, etc.).

6. Feature Flags

Dead code elimination via Bun's bun:bundle feature flags:

import { feature } from 'bun:bundle'

// Inactive code is completely stripped at build time
const voiceCommand = feature('VOICE_MODE')
  ? require('./commands/voice/index.js').default
  : null

Notable flags: PROACTIVE, KAIROS, BRIDGE_MODE, DAEMON, VOICE_MODE, AGENT_TRIGGERS, MONITOR_TOOL

Key Files in Detail

QueryEngine.ts (~46K lines)

The core engine for LLM API calls. Handles streaming responses, tool-call loops, thinking mode, retry logic, and token counting.

Tool.ts (~29K lines)

Defines base types and interfaces for all tools - input schemas, permission models, and progress state types.

commands.ts (~25K lines)

Manages registration and execution of all slash commands. Uses conditional imports to load different command sets per environment.

main.tsx

Commander.js-based CLI parser + React/Ink renderer initialization. At startup, parallelizes MDM settings, keychain prefetch, and GrowthBook initialization for faster boot.

Tech Stack

Notable Design Patterns

Parallel Prefetch

Startup time is optimized by prefetching MDM settings, keychain reads, and API preconnect in parallel - before heavy module evaluation begins.

// main.tsx - fired as side-effects before other imports
startMdmRawRead()
startKeychainPrefetch()

Lazy Loading

Heavy modules (OpenTelemetry ~400KB, gRPC ~700KB) are deferred via dynamic import() until actually needed.

Agent Swarms

Sub-agents are spawned via AgentTool, with coordinator/ handling multi-agent orchestration. TeamCreateTool enables team-level parallel work.

Skill System

Reusable workflows defined in skills/ and executed through SkillTool. Users can add custom skills.

Plugin Architecture

Built-in and third-party plugins are loaded through the plugins/ subsystem.

GitPretty Setup (Per-File Pretty Commits)

If you want GitHub's file UI to show visually distinct commit messages per file, use the helper script in this repo:

bash ./gitpretty-apply.sh .

This will:

1. Clone gitpretty into ~/.gitpretty (first run only)
2. Make scripts executable
3. Run emoji-file-commits.sh against this repo

Optional: install auto-emoji hooks for future commits:

bash ./gitpretty-apply.sh . --hooks

After running, push as usual:

git push origin main

Use It in Claude Code (MCP Server)

This repo includes an MCP server that lets you explore the Claude Code source directly from any Claude session. One command to set it up:

Quick Start

# Clone the repo (if you haven't already)
git clone https://github.com/Atharvsinh-codez/claude-code.git
cd claude-code/mcp-server

# Install dependencies and build
npm install && npm run build

# Add to Claude Code (run from the repo root)
claude mcp add claude-code-explorer -- node /absolute/path/to/claude-code/mcp-server/dist/index.js

Replace /absolute/path/to/claude-code with the actual path where you cloned the repo.

Or as a single copy-paste block (clones, builds, and registers in one go):

git clone https://github.com/Atharvsinh-codez/claude-code.git ~/claude-code \
  && cd ~/claude-code/mcp-server \
  && npm install && npm run build \
  && claude mcp add claude-code-explorer -- node ~/claude-code/mcp-server/dist/index.js

What You Get

Once added, Claude has access to these tools for exploring the codebase:

Plus prompts for guided exploration:

• explain_tool - Deep-dive into how a specific tool works
• explain_command - Understand a slash command's implementation
• architecture_overview - Guided tour of the full architecture
• how_does_it_work - Explain any subsystem (permissions, MCP, bridge, etc.)
• compare_tools - Side-by-side comparison of two tools

Example Usage

After adding the MCP server, just ask Claude naturally:

"How does the BashTool work?" "Search for where permissions are checked" "Show me the /review command source" "Explain the MCP client integration"

Custom Source Path

If your src/ directory is in a non-standard location, set the environment variable:

claude mcp add claude-code-explorer -e CLAUDE_CODE_SRC_ROOT=/path/to/src -- node /path/to/mcp-server/dist/index.js

Remove It

claude mcp remove claude-code-explorer

Disclaimer

This repository archives source code that was leaked from Anthropic's npm registry on 2026-03-31. All original source code is the property of Anthropic.