claude-code-source
mimran-khan/claude-code-source
This repository provides access to the extracted TypeScript source code of Anthropic's Claude Code assistant for educational analysis and research.
Overview
Claude Code Source is an archive containing the reverse-engineered and extracted TypeScript codebase of Anthropic's AI coding assistant, originating from an accidental source map leak in their npm package. It outlines the internal architecture, command structure, agent tools, and UI components used by the proprietary assistant, enabling developers and researchers to examine how modern agentic workflows are implemented.
Capabilities
- ▸Examine core LLM query engines and task orchestration loops
- ▸Review implementations of custom agent tools and slash commands
- ▸Study React-based terminal UI components and state management
Best for
Studying the internal architecture of advanced AI coding assistants, Analyzing tool execution patterns and agentic loop designs, Researching how MCP and external service integrations are structured
Works with
実タスクにどれだけ役立つか(機能の豊富さ・用途の明確さ)。 — AIによるcapabilities/use-cases解析
実装・指示の品質。 — AIによるSKILL.md/README解析
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
ありふれたラッパーではない独自性。 — AIによる独自性判定
コミュニティの採用度。 — GitHub Stars/Forks(対数スケール)
対応AIエージェントの広さ。 — AIによる対応エージェント判定
ライセンス不明/制限あり(Red)のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
Contains leaked proprietary source code which may present legal and compliance risks if used commercially or outside strict educational bounds.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.