Add librarian Stage 1 oversize check

Third Stage 1 piece: scripts/librarian_check_oversize.py walks
non-archive markdown files and flags any over the 500-line soft cap
declared in AGENTS.md. Wired into scripts/librarian.sh.

Caught one real finding on first run: docs/performance.md at 914
lines. Splitting it into sub-topic notes is a separate cleanup task
— surfaced for the user, not auto-applied.

Updates docs/plans/librarian.md Progress + sets the next concrete
step to a stale-plan checker.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

docs/plans/librarian.md

@@ -134,6 +134,13 @@ operator applies the patch.
 - ✅ Stage 1 orchestrator: `scripts/librarian.sh`. Runs every Stage 1
   check in order, aggregates exit code, prints findings inline. Single
   entry point for users and (future) cron.
+- ✅ AGENTS.md mentions `scripts/librarian.sh` as the doc-lint entry
+  point in "Notes For Future Agents" (commit `0b363b5`).
+- ✅ Stage 1, piece 3: `scripts/librarian_check_oversize.py`. Flags
+  any non-archive markdown file over the 500-line soft cap declared
+  in AGENTS.md. Caught one real finding on first run:
+  `docs/performance.md` at 914 lines — split into sub-topics deferred
+  as a separate task.
 
 ## Stage 1 Remaining Checks
 
@@ -142,11 +149,10 @@ operator applies the patch.
   judgment is the open question).
 - MEMORY.md drift (index lines vs target file `description:` frontmatter).
 - Duplicate prose (high-overlap pairs across archive vs research).
-- Oversize files (>500-line soft cap from AGENTS.md).
 
 ## Next Concrete Step
 
-Mention `scripts/librarian.sh` in AGENTS.md so agents and humans know
-it exists as the canonical Stage 1 entry point. After that, pick one
-of the remaining checks above to add as the next checker (oversize
-files is the cheapest; stale plans is the most useful).
+Stale plan check (`scripts/librarian_check_stale_plans.py`). Walks
+`docs/plans/*.md` and flags files whose mtime is older than N days
+AND whose path hasn't appeared in `git log` over the same window.
+This catches plans that drift out of mind without being archived.

scripts/librarian.sh

@@ -21,6 +21,12 @@ if ! uv run python scripts/librarian_check_citations.py; then
 fi
 echo
 
+echo "→ File size (500-line soft cap from AGENTS.md)"
+if ! uv run python scripts/librarian_check_oversize.py; then
+    overall=1
+fi
+echo
+
 if [ "$overall" -eq 0 ]; then
     echo "All Stage 1 checks passed."
 else

scripts/librarian_check_oversize.py

@@ -0,0 +1,92 @@
+"""Oversize file check for librarian Stage 1.
+
+Walks markdown files and flags any whose line count exceeds the
+soft cap declared in AGENTS.md ("Docs & Experiment Workflow"
+section). Skips read-only archive doc directories — splitting them
+isn't an option.
+
+Usage:
+    uv run python scripts/librarian_check_oversize.py
+"""
+
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+SOFT_CAP_LINES = 500
+
+EXCLUDED_DIRS = {
+    ".git",
+    ".mypy_cache",
+    ".pytest_cache",
+    ".ruff_cache",
+    ".venv",
+    "__pycache__",
+    "build",
+    "dist",
+    "node_modules",
+    "runs",
+    "target",
+    "tools",
+    "wheels",
+}
+
+EXCLUDED_DOC_PREFIXES = (
+    Path("docs/archive"),
+    Path("docs/plans/archive"),
+)
+
+
+def _repo_root() -> Path:
+    current = Path(__file__).resolve()
+    for parent in current.parents:
+        if (parent / "pyproject.toml").is_file():
+            return parent
+    raise RuntimeError("pyproject.toml을 찾을 수 없어 repository root를 판정할 수 없습니다.")
+
+
+def _is_excluded(rel: Path) -> bool:
+    if any(part in EXCLUDED_DIRS for part in rel.parts):
+        return True
+    return any(prefix in rel.parents for prefix in EXCLUDED_DOC_PREFIXES)
+
+
+def _markdown_files(root: Path) -> list[Path]:
+    files: list[Path] = []
+    for path in root.rglob("*.md"):
+        rel = path.relative_to(root)
+        if not _is_excluded(rel):
+            files.append(path)
+    return sorted(set(files))
+
+
+def _line_count(path: Path) -> int:
+    with path.open(encoding="utf-8", errors="replace") as f:
+        return sum(1 for _ in f)
+
+
+def main() -> int:
+    root = _repo_root()
+    files = _markdown_files(root)
+    if not files:
+        print("검사할 Markdown 파일이 없습니다.", file=sys.stderr)
+        return 1
+
+    over = [(path, _line_count(path)) for path in files]
+    over = [(p, n) for p, n in over if n > SOFT_CAP_LINES]
+
+    if not over:
+        print(f"All markdown files under {SOFT_CAP_LINES}-line soft cap.")
+        return 0
+
+    over.sort(key=lambda item: -item[1])
+    print(f"Files over {SOFT_CAP_LINES}-line soft cap:")
+    for path, n in over:
+        rel = path.relative_to(root)
+        print(f"  {n:5d}  {rel}")
+    return 1
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())