HitCC banner
hitmux hitmux

HitCC

Documentation community

Description

Complete reverse-engineering documentation of the full logic of Claude Code CLI Node.js version v2.1.84

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

**English** | [中文](./README_zh.md)

HitCC

Complete reverse-engineering documentation of the full logic of Claude Code CLI Node.js version v2.1.84

HitCC is not a source code repository. It is a documentation knowledge base for learning, analysis, and rewrite work. The goal of this project is not to reconstruct the original file tree, but to recover Claude Code CLI's core runtime logic, module boundaries, configuration system, and surrounding ecosystem as faithfully as possible, so it can serve as a stable reference for a runnable alternative or a high-similarity rewrite.

This project is not affiliated with Anthropic PBC. The repository does not contain Claude Code original source code, cracking content, or implementations intended to bypass product policies or permission mechanisms.

Notes

To obtain the Claude Code CLI package analyzed by this repository:

npm pack @anthropic-ai/claude-code@2.1.84

The Python scripts under `recovery_tools/` can perform an initial round of cleanup on obfuscated or encrypted source code.

This repository is based only on static analysis of Claude Code CLI v2.1.84 obtained through the method above. It does not include runtime dynamic analysis, and it did not use any Anthropic PBC network services, including LLM inference services.

The documentation content in this repository may be quite extensive. The current statistics for the `docs/` directory (the following data may not be updated in real time):

TOTAL
  Files: 81
  Lines: 27170
  Chars: 698707
  Bytes: 953399

What This Repository Provides

  • Structured reverse-engineering documentation for the main Claude Code CLI execution chain
  • Topic-oriented analysis from startup entry to the Agent Loop, Tool Use, prompt assembly, and session persistence
  • Split-out explanations of surrounding systems such as MCP, Plugin, Skill, TUI, Remote Persistence, and Bridge
  • Candidate architecture, known boundaries, and open questions for rewrite-oriented engineerin