A recent source‑code leak of Claude Code exposed over 1900 files and 510,000 lines, uncovering hidden features like an electronic pet, long‑term memory, advanced planning tools, and a multi‑layer security model, while also highlighting Anthropic’s recurring operational oversights.
A recent leak of the @anthropic-ai/claude-code npm package exposed full TypeScript source maps, allowing researchers to reconstruct the entire Claude Code CLI, publish it on GitHub, and analyze its architecture, components, and potential security implications.
The accidental exposure of Claude Code’s TypeScript source via an npm source‑map mishap sparked a rapid community deep‑dive that uncovered anti‑distillation safeguards, a hidden Buddy pet, extensive prompt‑caching logic, undercover mode, auto‑compaction thresholds, and broader engineering trade‑offs, while Anthropic and its founder responded to the slip.
A massive source‑map mishap exposed over 1,900 files and 510,000 lines of Claude Code’s TypeScript implementation, revealing its React‑Ink UI, Bun runtime, a 40‑module toolbox, a 46k‑line QueryEngine, multi‑agent coordinator, hidden Kairos mode, Undercover mode, and even an embedded virtual pet system.
