diff --git a/serato_doctor/cli.py b/serato_doctor/cli.py
index e69de29..8ba0026 100644
--- a/serato_doctor/cli.py
+++ b/serato_doctor/cli.py
@@ -0,0 +1,46 @@
+from pathlib import Path
+import argparse
+import csv
+
+from serato_doctor.crate_parser import parse_crates
+from serato_doctor.scanner import scan_audio
+
+
+def main():
+    parser = argparse.ArgumentParser(prog="serato-doctor")
+    parser.add_argument("--serato", default=str(Path.home() / "Music/_Serato_"))
+    parser.add_argument("--music", default=str(Path.home() / "Library/CloudStorage/OneDrive-Personal/Jukebox"))
+    parser.add_argument("--out", default=str(Path.home() / "Desktop/serato_doctor_scan.csv"))
+    args = parser.parse_args()
+
+    serato = Path(args.serato)
+    music = Path(args.music)
+    out = Path(args.out)
+
+    refs = parse_crates(serato / "Subcrates")
+    disk = scan_audio(music)
+
+    disk_names = {t.filename for t in disk}
+
+    rows = []
+    for ref in refs:
+        rows.append({
+            "crate": str(ref.source),
+            "serato_path": str(ref.path),
+            "filename": ref.filename,
+            "exists_by_filename": ref.filename in disk_names,
+        })
+
+    with out.open("w", newline="", encoding="utf-8") as f:
+        writer = csv.DictWriter(f, fieldnames=["crate", "serato_path", "filename", "exists_by_filename"])
+        writer.writeheader()
+        writer.writerows(rows)
+
+    print(f"Crate references: {len(refs)}")
+    print(f"Disk tracks: {len(disk)}")
+    print(f"Missing by filename: {sum(1 for r in rows if not r['exists_by_filename'])}")
+    print(f"Wrote: {out}")
+
+
+if __name__ == "__main__":
+    main()
diff --git a/serato_doctor/crate_parser.py b/serato_doctor/crate_parser.py
index e69de29..947a538 100644
--- a/serato_doctor/crate_parser.py
+++ b/serato_doctor/crate_parser.py
@@ -0,0 +1,47 @@
+from pathlib import Path
+import re
+
+from serato_doctor.models import TrackReference
+
+AUDIO_EXTS = "mp3|m4a|wav|aif|aiff|flac|MP3|M4A|WAV|AIF|AIFF|FLAC"
+
+
+def read_crate_text(crate_path: Path) -> str:
+    raw = crate_path.read_bytes()
+    for enc in ("utf-16-be", "utf-16-le", "utf-8", "latin1"):
+        text = raw.decode(enc, errors="ignore")
+        if "Users" in text or "Jukebox" in text:
+            return text
+    return raw.decode("latin1", errors="ignore")
+
+
+def parse_crate(crate_path: Path) -> list[TrackReference]:
+    text = read_crate_text(crate_path)
+
+    # Serato crate files often decode with weird spacing/null-ish characters.
+    # This finds paths from /Users/... through the audio extension without
+    # greedily scanning the entire file.
+    pattern = rf"/?Users/[^\r\n]+?\.(?:{AUDIO_EXTS})"
+
+    refs = []
+    for match in re.finditer(pattern, text):
+        raw_path = "/" + match.group(0).lstrip("/")
+        raw_path = raw_path.replace("\x00", "")
+        path = Path(raw_path)
+
+        refs.append(
+            TrackReference(
+                source=crate_path,
+                path=path,
+                filename=path.name,
+            )
+        )
+
+    return refs
+
+
+def parse_crates(root: Path) -> list[TrackReference]:
+    refs = []
+    for crate in root.rglob("*.crate"):
+        refs.extend(parse_crate(crate))
+    return refs
diff --git a/serato_doctor/models.py b/serato_doctor/models.py
new file mode 100644
index 0000000..22466b9
--- /dev/null
+++ b/serato_doctor/models.py
@@ -0,0 +1,17 @@
+from dataclasses import dataclass
+from pathlib import Path
+
+
+@dataclass(frozen=True)
+class TrackReference:
+    source: Path
+    path: Path
+    filename: str
+
+
+@dataclass(frozen=True)
+class DiskTrack:
+    path: Path
+    filename: str
+    size: int
+    suffix: str
diff --git a/serato_doctor/scanner.py b/serato_doctor/scanner.py
index e69de29..d12ee0e 100644
--- a/serato_doctor/scanner.py
+++ b/serato_doctor/scanner.py
@@ -0,0 +1,31 @@
+from pathlib import Path
+
+from serato_doctor.models import DiskTrack
+
+AUDIO_SUFFIXES = {".mp3", ".m4a", ".wav", ".aif", ".aiff", ".flac"}
+
+
+def scan_audio(folder: Path) -> list[DiskTrack]:
+    tracks = []
+
+    for path in folder.rglob("*"):
+        if not path.is_file():
+            continue
+        if path.suffix.lower() not in AUDIO_SUFFIXES:
+            continue
+
+        try:
+            stat = path.stat()
+        except OSError:
+            continue
+
+        tracks.append(
+            DiskTrack(
+                path=path,
+                filename=path.name,
+                size=stat.st_size,
+                suffix=path.suffix.lower(),
+            )
+        )
+
+    return tracks