# openedclaude/claude-reviews-claude

Claude reads its own source code — 17-chapter architectural deep-dive  into Claude Code v2.1.88. EN/ZH bilingual.

Repository: https://github.com/openedclaude/claude-reviews-claude
Canonical: https://ross.abutalabs.com/products/claude-reviews-claude
Homepage: https://openedclaude.github.io/claude-reviews-claude/
License: MIT
License Family: permissive
Topics: agent, agentic-ai, ai, anthropic, architecture, claude, claude-code, deep-dive, documentation, llm, meta, reverse-engineering, source-code, typescript, vibe-coding
Last push: 2026-04-01T19:52:40+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
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1569, forks 698 (observed 2026-08-28T04:05:05.272882+00:00)

## What it is
A 17-chapter bilingual (EN/ZH) architectural deep-dive into Claude Code v2.1.88, written by Claude itself after reading its own 477K-line TypeScript source code. It is published as a static documentation site on GitHub Pages with architecture diagrams, code walkthroughs, and design-pattern analysis.

## Use cases
- understand how claude code's query engine and tool loop work internally
- learn multi-agent orchestration patterns from a production ai coding agent
- study how a cli agent implements permission and sandboxing layers
- find reference architecture for building my own coding agent
- learn how plugin and hook systems for ai agents are designed
- read an ai agent source code analysis in chinese or english

## When to choose
- you want a structured, chapter-by-chapter architectural analysis of Claude Code's internals
- you are building an agentic CLI tool and want transferable design patterns
- you prefer a searchable bilingual documentation site over raw source code

## When to avoid
- you need official, guaranteed-accurate documentation from Anthropic
- you need a runnable tool or library rather than reading material
- you need analysis of a version other than Claude Code v2.1.88

## Facets
- artifact type: learning-resource
- maturity: active
- function: documentation, reverse-engineering, developer-tools
- domain: artificial-intelligence, large-language-models, documentation, developer-tools, tutorials
- platform: cli
- tags: claude-code, architecture-analysis, bilingual, source-code-review, agentic-ai, meta, ai-agents, web

## Member repositories
- openedclaude/claude-reviews-claude (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:05.272882+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 2026-08-30T03:58:53.716645+00:00, confidence not recorded.
  - readme: https://github.com/openedclaude/claude-reviews-claude (fetched 2026-08-28T04:05:05.272882+00:00, sha 7ae1bb414360)
  - homepage: https://openedclaude.github.io/claude-reviews-claude/ (fetched 2026-08-29T11:28:41.893456+00:00, sha 7b9a507ce331)
- Data as of 2026-08-30T08:39:29.467469+00:00.