Claude Code Source Snapshot for Security Research

This repository mirrors a publicly exposed Claude Code source snapshot that became accessible on March 31, 2026 through a source map exposure in the npm distribution. It is maintained for educational, defensive security research, and software supply-chain analysis.

Research Context

This repository is maintained by a university student studying:

• software supply-chain exposure and build artifact leaks
• secure software engineering practices
• agentic developer tooling architecture
• defensive analysis of real-world CLI systems

This archive is intended to support:

• educational study
• security research practice
• architecture review
• discussion of packaging and release-process failures

It does not claim ownership of the original code, and it should not be interpreted as an official Anthropic repository.

How the Public Snapshot Became Accessible

Chaofan Shou (@Fried_rice) publicly noted that Claude Code source material was reachable through a .map file exposed in the npm package:

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

— @Fried_rice, March 31, 2026

The published source map referenced unobfuscated TypeScript sources hosted in Anthropic's R2 storage bucket, which made the src/ snapshot publicly downloadable.

Repository Scope

Claude Code is Anthropic's CLI for interacting with Claude from the terminal to perform software engineering tasks such as editing files, running commands, searching codebases, and coordinating workflows.

This repository contains a mirrored src/ snapshot for research and analysis.

• Public exposure identified on: 2026-03-31
• Language: TypeScript
• Runtime: Bun
• Terminal UI: React + Ink
• Scale: ~1,900 files, 512,000+ lines of code

Directory Structure

src/
├── main.tsx                 # Entrypoint orchestration (Commander.js-based CLI path)
├── commands.ts              # Command registry
├── tools.ts                 # Tool registry
├── Tool.ts                  # Tool type definitions
├── QueryEngine.ts           # LLM query engine
├── 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 and remote-control bridge
├── 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/                  # Persistent memory directory
├── tasks/                   # Task management
├── state/                   # State management
├── migrations/              # Config migrations
├── schemas/                 # Config schemas (Zod)
├── entrypoints/             # Initialization logic
├── ink/                     # Ink renderer wrapper
├── buddy/                   # Companion sprite
├── native-ts/               # Native TypeScript utilities
├── outputStyles/            # Output styling
├── query/                   # Query pipeline
└── upstreamproxy/           # Proxy configuration

Architecture Summary

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 and React/Ink renderer initialization. At startup, it overlaps 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, gRPC, analytics, and some feature-gated subsystems) 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/ are executed through SkillTool. Users can add custom skills.

Plugin Architecture

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

Research / Ownership Disclaimer

• This repository is an educational and defensive security research archive maintained by a university student.
• It exists to study source exposure, packaging failures, and the architecture of modern agentic CLI systems.
• The original Claude Code source remains the property of Anthropic.
• This repository is not affiliated with, endorsed by, or maintained by Anthropic.