🚀 Open source Claude Code CLI source code. Advanced AI Agent for developers. Includes TypeScript codebase for LLM tool-calling, agentic workflows, and terminal UI. Remember this is just the skeleton not the brain itself. Found by Chaofan Shou.
This repository is a mirror and breakdown of Anthropic's Claude Code CLI source code, which was inadvertently exposed on the npm registry when Bun's default build behavior included source map files containing the full original TypeScript in their `sourcesContent` fields. The leak was discovered by Chaofan Shou on March 31st, 2026. The codebase centers on a 785KB `main.tsx` entry point built with React/Ink for terminal rendering and contains over 40 agent tools covering Bash execution, file operations, LSP integration, and web access. Notable internal systems include KAIROS, a proactive background assistant that acts on logs without user prompts; ULTRAPLAN, which delegates complex planning to a remote Opus 4.6 session for up to 30 minutes; an autoDream memory consolidation service; an Undercover Mode that blocks disclosure of internal model codenames like Tengu and Capybara; and a Tamagotchi companion system called BUDDY with 18 species and Claude-authored personality descriptions. The repository also bundles an MCP server called `claude-code-explorer-mcp` that allows browsing the source through Claude Desktop. Researchers, reverse engineers, and developers studying agentic CLI architecture are the primary audience, though the code remains proprietary to Anthropic.
- ✓Recently active
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
- !No standard license detected
git clone https://github.com/yasasbanukaofficial/claude-code && cp claude-code/*.md ~/.claude/agents/Subagents overview
What people ask about claude-code
What is yasasbanukaofficial/claude-code?
+
yasasbanukaofficial/claude-code is subagents for the Claude AI ecosystem. 🚀 Open source Claude Code CLI source code. Advanced AI Agent for developers. Includes TypeScript codebase for LLM tool-calling, agentic workflows, and terminal UI. Remember this is just the skeleton not the brain itself. Found by Chaofan Shou. It has 3.5k GitHub stars and was last updated 2mo ago.
How do I install claude-code?
+
You can install claude-code by cloning the repository (https://github.com/yasasbanukaofficial/claude-code) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is yasasbanukaofficial/claude-code safe to use?
+
Our security agent has analyzed yasasbanukaofficial/claude-code and assigned a Trust Score of 75/100 (tier: Trusted). See the full breakdown of passed checks and flags on this page.
Who maintains yasasbanukaofficial/claude-code?
+
yasasbanukaofficial/claude-code is maintained by yasasbanukaofficial. The last recorded GitHub activity is from 2mo ago, with 4 open issues.
Are there alternatives to claude-code?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy claude-code to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/yasasbanukaofficial-claude-code)<a href="https://claudewave.com/repo/yasasbanukaofficial-claude-code"><img src="https://claudewave.com/api/badge/yasasbanukaofficial-claude-code" alt="Featured on ClaudeWave: yasasbanukaofficial/claude-code" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Production-ready platform for agentic workflow development.
The agent engineering platform.
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.