diff --git a/README.md b/README.md
index 7b47b37..93935bf 100644
--- a/README.md
+++ b/README.md
@@ -153,6 +153,6 @@ See [`problem_statement.md`](problem_statement.md) for the official participant
 
 ## Submission
 
-Build `code.zip` with `python3 code/package_submission.py`, submit the root `output.csv`, and upload `log.txt` as the chat transcript. The challenge submission page is:
+Build `code.zip` with `python3 code/package_submission.py`, submit the root `output.csv`, and upload `log.txt` as the chat transcript. The archive includes the required reports at the exact paths `evaluation/evaluation_report.md` and `evaluation/usage_report.md`; their source-of-truth copies remain beside the evaluator under `code/evaluation/`. The challenge submission page is:
 
 https://www.hackerrank.com/contests/hackerrank-orchestrate-october26/challenges/ghost-data-still-exists
diff --git a/code/package_submission.py b/code/package_submission.py
index 8336eb6..ecce120 100644
--- a/code/package_submission.py
+++ b/code/package_submission.py
@@ -12,6 +12,14 @@
 EXCLUDED_PARTS = {"__pycache__", ".venv", "venv", "node_modules", ".git"}
 EXCLUDED_SUFFIXES = {".pyc", ".pyo", ".zip", ".tar", ".gz", ".tgz", ".7z", ".rar"}
 FIXED_ZIP_TIMESTAMP = (1980, 1, 1, 0, 0, 0)
+REPORT_ALIASES = {
+    ROOT / "code" / "evaluation" / "evaluation_report.md": (
+        "evaluation/evaluation_report.md"
+    ),
+    ROOT / "code" / "evaluation" / "usage_report.md": (
+        "evaluation/usage_report.md"
+    ),
+}
 
 
 def included_files() -> list[Path]:
@@ -25,13 +33,27 @@ def included_files() -> list[Path]:
     )
 
 
-def build_archive(output: Path = OUTPUT) -> list[Path]:
+def archive_entries() -> list[tuple[Path, str]]:
+    """Return source files and their contract-compliant archive paths."""
+    entries = [
+        (path, path.relative_to(ROOT).as_posix())
+        for path in included_files()
+    ]
+    entries.extend(REPORT_ALIASES.items())
+    entries = sorted(entries, key=lambda item: item[1])
+    names = [name for _path, name in entries]
+    if len(names) != len(set(names)):
+        raise ValueError("Submission archive contains duplicate paths")
+    return entries
+
+
+def build_archive(output: Path = OUTPUT) -> list[tuple[Path, str]]:
     """Write a byte-reproducible archive independent of checkout timestamps."""
-    files = included_files()
+    entries = archive_entries()
     with zipfile.ZipFile(output, "w") as archive:
-        for path in files:
+        for path, archive_path in entries:
             info = zipfile.ZipInfo(
-                path.relative_to(ROOT).as_posix(),
+                archive_path,
                 date_time=FIXED_ZIP_TIMESTAMP,
             )
             info.compress_type = zipfile.ZIP_DEFLATED
@@ -43,12 +65,12 @@ def build_archive(output: Path = OUTPUT) -> list[Path]:
                 compress_type=zipfile.ZIP_DEFLATED,
                 compresslevel=9,
             )
-    return files
+    return entries
 
 
 def main() -> int:
-    files = build_archive()
-    print(f"Created {OUTPUT} with {len(files)} files")
+    entries = build_archive()
+    print(f"Created {OUTPUT} with {len(entries)} files")
     return 0
 
 
diff --git a/code/tests/test_engine.py b/code/tests/test_engine.py
index 1239d88..ad36cbf 100644
--- a/code/tests/test_engine.py
+++ b/code/tests/test_engine.py
@@ -298,6 +298,24 @@ def test_submission_archive_is_reproducible_and_dataset_free(self) -> None:
             with zipfile.ZipFile(first) as archive:
                 names = archive.namelist()
                 self.assertEqual(archive.testzip(), None)
+                self.assertEqual(len(names), len(set(names)))
+                required_reports = {
+                    "evaluation/evaluation_report.md": (
+                        REPO_ROOT
+                        / "code"
+                        / "evaluation"
+                        / "evaluation_report.md"
+                    ),
+                    "evaluation/usage_report.md": (
+                        REPO_ROOT / "code" / "evaluation" / "usage_report.md"
+                    ),
+                }
+                self.assertTrue(required_reports.keys() <= set(names))
+                for archive_path, source_path in required_reports.items():
+                    self.assertEqual(
+                        archive.read(archive_path),
+                        source_path.read_bytes(),
+                    )
                 self.assertFalse(
                     any(
                         name == "log.txt"