diff --git a/CLAUDE.md b/CLAUDE.md
deleted file mode 100644
index 7935796..0000000
--- a/CLAUDE.md
+++ /dev/null
@@ -1,38 +0,0 @@
-# CLAUDE.md
-
-This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
-
-## Project Overview
-
-**Musiksammlung** is a Python CLI tool that automates digitizing physical CD collections for use with Jellyfin. It orchestrates: CD ripping (via `abcde`), OCR of cover/back images (via Tesseract), LLM-based tracklist extraction, file renaming/tagging, and M3U playlist generation.
-
-## Build & Development Commands
-
-```bash
-pip install -e ".[dev]"          # Install in editable mode with dev deps
-pytest tests/ -v                 # Run all tests
-pytest tests/test_models.py -v   # Run a single test module
-ruff check src/ tests/           # Lint
-musiksammlung --help             # CLI entry point
-```
-
-## Architecture
-
-The pipeline flows: **OCR → LLM → Organize → Tag → Playlist**
-
-- `models.py` — Pydantic models (`Album`, `Disc`, `Track`) shared across all modules; the LLM JSON output validates directly into `Album`
-- `cli.py` — Typer CLI with three commands: `scan` (OCR+LLM→JSON), `apply` (JSON→files), `process` (full pipeline)
-- `ocr.py` — Tesseract wrapper with Pillow-based image preprocessing
-- `llm_parser.py` — Sends OCR text to LLM (Ollama or OpenAI-compatible), enforces JSON output, retries on parse failure
-- `organizer.py` — Builds source→target file mapping, handles single-disc and multi-disc layouts
-- `tagger.py` — Sets audio tags via mutagen (format-agnostic), optional cover embedding for FLAC/MP3
-- `playlist.py` — Generates M3U playlists with relative paths
-- `ripper.py` — Drives `abcde` via subprocess for CD ripping
-- `cover.py` — Resizes/converts cover images to JPEG for Jellyfin
-
-## Conventions
-
-- Python 3.11+, German variable names and comments are acceptable
-- Pydantic for data models, Typer for CLI, mutagen for audio tagging
-- External tools required at runtime: `tesseract`, `abcde`
-- The two-step workflow (`scan` → review JSON → `apply`) is the recommended default over the one-shot `process` command