Skip to content
Back to search

Anthropic-Leaked-Source-Code

CLAUDE LEAK - Full Claude Leaked Source Code

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/austin1serb--anthropic-leaked-source-code/badge.svg)](/listings/austin1serb--anthropic-leaked-source-code)

HTML

<a href="/listings/austin1serb--anthropic-leaked-source-code"><img src="/api/listings/austin1serb--anthropic-leaked-source-code/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 55 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Claude Code Source Code Leak — Anthropic Code Leak Archive
  2. This repository contains an unmodified archive of the leaked source code for [Claude Code](https://github.com/anthropics/claude-code), Anthropic's AI-powered coding agent.
  3. Also known as the **Claude Code leak**, **Anthropic source code leak**, or **Claude Code source code leak**, this archive is intended for research, education, and technical analysis.
  4. Nothing has been added besides this README. Nothing has been removed or changed. This is the raw source as leaked.
  5. ## What's included
  6. - Agent orchestration and query engine
  7. - Tool implementations for Bash, FileEdit, FileRead, FileWrite, Glob, Grep, WebSearch, WebFetch, Notebook, and related developer tools
  8. - API service layer and model provider integrations
  9. - MCP, or Model Context Protocol, server management
  10. - Permission system and sandboxing logic
  11. - CLI transport layers, including SSE, WebSocket, and hybrid transports
  12. - Prompt construction and system prompt logic
  13. ## Claude Code leak overview
  14. Claude Code is Anthropic's AI coding agent. This repository exists as a public archive for developers, researchers, and security-minded engineers who want to study how a modern AI coding agent is structured.
  15. Common search terms for this topic include:
  16. - Claude Code GitHub
  17. - Claude Code leak
  18. - Claude Code source code
  19. - Anthropic code leak
  20. - Anthropic source code leak
  21. - Anthropic leaked source code
  22. - Claude Code source map
  23. - Claude Code repo
  24. ## Why this exists
  25. This repository is for educational and research purposes. It may be useful for studying:
  26. - AI coding agent architecture
  27. - Tool-calling systems
  28. - Prompt construction
  29. - Local development workflows
  30. - Sandboxing and permission models
  31. - MCP server integration
  32. - CLI-based AI agent design
  33. ## Disclaimer
  34. This repository is provided for educational and research purposes only.
  35. No affiliation with Anthropic AI. Claude Code is a product of Anthropic AI.
  36. ## Reverse Engineered by Serbyte Development
  37. Reverse engineered using JavaScript source maps by [Serbyte Web Design & Development](https://www.serbyte.net), a software development firm creating custom software, AI automations, and open-source developer tools.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.