# liuup/claude-code-analysis

🤖 The analysis of Claude Code

Repository: https://github.com/liuup/claude-code-analysis
Canonical: https://ross.abutalabs.com/products/claude-code-analysis
Language: TypeScript
License Family: other
Last push: 2026-04-02T00:39:09+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 75, release rhythm 35, longevity 11
- inputs: {"age_days": 155, "days_push": 154, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3853, forks 2050 (observed 2026-08-28T04:08:27.160752+00:00)

## What it is
A repository of static analysis documents for the leaked TypeScript source code of Anthropic's Claude Code CLI agent, covering architecture, security, memory, and extension mechanisms. It includes the recovered source tree alongside chaptered markdown analysis notes.

## Use cases
- understand how claude code works internally
- study agent memory and session compression design
- analyze security and privacy of a coding agent cli
- learn how mcp and skills extension mechanisms are implemented
- compare claude code with codex gemini cli and aider
- study sandbox and tool permission isolation in agent tools

## When to choose
- you want a deep architectural breakdown of Claude Code's internals
- you're researching security and data-collection behavior of coding agents
- you need source-level evidence for agent design patterns like memory and tool permissions

## When to avoid
- you want a maintained, production-ready tool or library
- you need a legally clean or officially supported codebase
- you just want to use Claude Code rather than study it

## Facets
- artifact type: learning-resource
- maturity: active
- function: documentation, security, reverse-engineering, developer-tools
- domain: developer-tools, large-language-models, security, documentation
- platform: cli
- tags: claude-code, source-analysis, leaked-source, static-analysis, agent-architecture, mcp, tui, typescript, ai-agents, nodejs

## Member repositories
- liuup/claude-code-analysis (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:27.160752+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:25:57.145353+00:00, confidence not recorded.
  - readme: https://github.com/liuup/claude-code-analysis (fetched 2026-08-28T04:08:27.160752+00:00, sha bae8b13b0ab9)
- Data as of 2026-08-30T08:39:29.467469+00:00.