diff --git a/CHANGELOG.md b/CHANGELOG.md
index 884eb91e..847f4548 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -2,6 +2,15 @@
 
 Full release notes with details on each version: [GitHub Releases](https://github.com/safishamsi/graphify/releases)
 
+## 0.3.18 (2026-04-09)
+
+- Fix: `--watch` mode now respects `.graphifyignore` — `_rebuild_code` was calling `collect_files()` directly instead of `detect()`, bypassing ignore patterns (#120)
+- Fix: Codex PreToolUse hook now uses `systemMessage` instead of `additionalContext` — Codex does not support `additionalContext` and was returning an error (#121)
+- Fix: Trae link corrected from `trae.com` to `trae.ai` in README, README.zh-CN.md, README.ja-JP.md, README.ko-KR.md (#122)
+- Docs: Korean README added (README.ko-KR.md) (#112)
+- Refactor: `save_query_result` inline Python blocks in all 6 skill files replaced with `graphify save-result` CLI command — shorter, maintainable, less tokens for LLM (#114)
+- Add: `graphify save-result` CLI subcommand — saves Q&A results to memory dir without inline Python
+
 ## 0.3.17 (2026-04-08)
 
 - Add: Julia (.jl) support — modules, structs, abstract types, functions, short functions, using/import, call edges, inherits edges via tree-sitter-julia (#98)
diff --git a/graphify/__main__.py b/graphify/__main__.py
index 3dc8f7ac..093539d3 100644
--- a/graphify/__main__.py
+++ b/graphify/__main__.py
@@ -170,7 +170,7 @@ _CODEX_HOOK = {
                         "type": "command",
                         "command": (
                             "[ -f graphify-out/graph.json ] && "
-                            r"""echo '{"hookSpecificOutput":{"hookEventName":"PreToolUse","additionalContext":"graphify: Knowledge graph exists. Read graphify-out/GRAPH_REPORT.md for god nodes and community structure before searching raw files."}}' """
+                            r"""echo '{"hookSpecificOutput":{"hookEventName":"PreToolUse","permissionDecision":"allow","systemMessage":"graphify: Knowledge graph exists. Read graphify-out/GRAPH_REPORT.md for god nodes and community structure before searching raw files."}}' """
                             "|| true"
                         ),
                     }
@@ -388,6 +388,12 @@ def main() -> None:
         print("    --dfs                   use depth-first instead of breadth-first")
         print("    --budget N              cap output at N tokens (default 2000)")
         print("    --graph <path>          path to graph.json (default graphify-out/graph.json)")
+        print("  save-result             save a Q&A result to graphify-out/memory/ for graph feedback loop")
+        print("    --question Q            the question asked")
+        print("    --answer A              the answer to save")
+        print("    --type T                query type: query|path_query|explain (default: query)")
+        print("    --nodes N1 N2 ...       source node labels cited in the answer")
+        print("    --memory-dir DIR        memory directory (default: graphify-out/memory)")
         print("  benchmark [graph.json]  measure token reduction vs naive full-corpus approach")
         print("  hook install            install post-commit/post-checkout git hooks (all platforms)")
         print("  hook uninstall          remove git hooks")
@@ -518,6 +524,25 @@ def main() -> None:
         start = [nid for _, nid in scored[:5]]
         nodes, edges = (_dfs if use_dfs else _bfs)(G, start, depth=2)
         print(_subgraph_to_text(G, nodes, edges, token_budget=budget))
+    elif cmd == "save-result":
+        # graphify save-result --question Q --answer A --type T [--nodes N1 N2 ...]
+        import argparse as _ap
+        p = _ap.ArgumentParser(prog="graphify save-result")
+        p.add_argument("--question", required=True)
+        p.add_argument("--answer", required=True)
+        p.add_argument("--type", dest="query_type", default="query")
+        p.add_argument("--nodes", nargs="*", default=[])
+        p.add_argument("--memory-dir", default="graphify-out/memory")
+        opts = p.parse_args(sys.argv[2:])
+        from graphify.ingest import save_query_result as _sqr
+        out = _sqr(
+            question=opts.question,
+            answer=opts.answer,
+            memory_dir=Path(opts.memory_dir),
+            query_type=opts.query_type,
+            source_nodes=opts.nodes or None,
+        )
+        print(f"Saved to {out}")
     elif cmd == "benchmark":
         from graphify.benchmark import run_benchmark, print_benchmark
         graph_path = sys.argv[2] if len(sys.argv) > 2 else "graphify-out/graph.json"
diff --git a/graphify/skill-claw.md b/graphify/skill-claw.md
index c267a7df..ca353efd 100644
--- a/graphify/skill-claw.md
+++ b/graphify/skill-claw.md
@@ -894,18 +894,7 @@ Replace `QUESTION` with the user's actual question, `MODE` with `bfs` or `dfs`,
 After writing the answer, save it back into the graph so it improves future queries:
 
 ```bash
-$(cat .graphify_python) -c "
-from graphify.ingest import save_query_result
-from pathlib import Path
-save_query_result(
-    question='QUESTION',
-    answer='ANSWER',
-    memory_dir=Path('graphify-out/memory'),
-    query_type='query',
-    source_nodes=SOURCE_NODES,  # list of node labels cited, or []
-)
-print('Query result saved to graphify-out/memory/')
-"
+$(cat .graphify_python) -m graphify save-result --question "QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
 ```
 
 Replace `QUESTION` with the question, `ANSWER` with your full answer text, `SOURCE_NODES` with the list of node labels you cited. This closes the feedback loop: the next `--update` will extract this Q&A as a node in the graph.
@@ -980,18 +969,7 @@ Replace `NODE_A` and `NODE_B` with the actual concept names from the user. Then
 After writing the explanation, save it back:
 
 ```bash
-$(cat .graphify_python) -c "
-from graphify.ingest import save_query_result
-from pathlib import Path
-save_query_result(
-    question='Path from NODE_A to NODE_B',
-    answer='ANSWER',
-    memory_dir=Path('graphify-out/memory'),
-    query_type='path_query',
-    source_nodes=PATH_NODES,  # list of node labels on the path
-)
-print('Path result saved to graphify-out/memory/')
-"
+$(cat .graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
 ```
 
 ---
@@ -1057,18 +1035,7 @@ Replace `NODE_NAME` with the concept the user asked about. Then write a 3-5 sent
 After writing the explanation, save it back:
 
 ```bash
-$(cat .graphify_python) -c "
-from graphify.ingest import save_query_result
-from pathlib import Path
-save_query_result(
-    question='Explain NODE_NAME',
-    answer='ANSWER',
-    memory_dir=Path('graphify-out/memory'),
-    query_type='explain',
-    source_nodes=['NODE_NAME'],
-)
-print('Explanation saved to graphify-out/memory/')
-"
+$(cat .graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
 ```
 
 ---
diff --git a/graphify/skill-codex.md b/graphify/skill-codex.md
index 33d82dfb..e94f2da4 100644
--- a/graphify/skill-codex.md
+++ b/graphify/skill-codex.md
@@ -950,18 +950,7 @@ Replace `QUESTION` with the user's actual question, `MODE` with `bfs` or `dfs`,
 After writing the answer, save it back into the graph so it improves future queries:
 
 ```bash
-$(cat .graphify_python) -c "
-from graphify.ingest import save_query_result
-from pathlib import Path
-save_query_result(
-    question='QUESTION',
-    answer='ANSWER',
-    memory_dir=Path('graphify-out/memory'),
-    query_type='query',
-    source_nodes=SOURCE_NODES,  # list of node labels cited, or []
-)
-print('Query result saved to graphify-out/memory/')
-"
+$(cat .graphify_python) -m graphify save-result --question "QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
 ```
 
 Replace `QUESTION` with the question, `ANSWER` with your full answer text, `SOURCE_NODES` with the list of node labels you cited. This closes the feedback loop: the next `--update` will extract this Q&A as a node in the graph.
@@ -1036,18 +1025,7 @@ Replace `NODE_A` and `NODE_B` with the actual concept names from the user. Then
 After writing the explanation, save it back:
 
 ```bash
-$(cat .graphify_python) -c "
-from graphify.ingest import save_query_result
-from pathlib import Path
-save_query_result(
-    question='Path from NODE_A to NODE_B',
-    answer='ANSWER',
-    memory_dir=Path('graphify-out/memory'),
-    query_type='path_query',
-    source_nodes=PATH_NODES,  # list of node labels on the path
-)
-print('Path result saved to graphify-out/memory/')
-"
+$(cat .graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
 ```
 
 ---
@@ -1113,18 +1091,7 @@ Replace `NODE_NAME` with the concept the user asked about. Then write a 3-5 sent
 After writing the explanation, save it back:
 
 ```bash
-$(cat .graphify_python) -c "
-from graphify.ingest import save_query_result
-from pathlib import Path
-save_query_result(
-    question='Explain NODE_NAME',
-    answer='ANSWER',
-    memory_dir=Path('graphify-out/memory'),
-    query_type='explain',
-    source_nodes=['NODE_NAME'],
-)
-print('Explanation saved to graphify-out/memory/')
-"
+$(cat .graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
 ```
 
 ---
diff --git a/graphify/skill-droid.md b/graphify/skill-droid.md
index 7dfb7381..915dc784 100644
--- a/graphify/skill-droid.md
+++ b/graphify/skill-droid.md
@@ -947,18 +947,7 @@ Replace `QUESTION` with the user's actual question, `MODE` with `bfs` or `dfs`,
 After writing the answer, save it back into the graph so it improves future queries:
 
 ```bash
-$(cat .graphify_python) -c "
-from graphify.ingest import save_query_result
-from pathlib import Path
-save_query_result(
-    question='QUESTION',
-    answer='ANSWER',
-    memory_dir=Path('graphify-out/memory'),
-    query_type='query',
-    source_nodes=SOURCE_NODES,  # list of node labels cited, or []
-)
-print('Query result saved to graphify-out/memory/')
-"
+$(cat .graphify_python) -m graphify save-result --question "QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
 ```
 
 Replace `QUESTION` with the question, `ANSWER` with your full answer text, `SOURCE_NODES` with the list of node labels you cited. This closes the feedback loop: the next `--update` will extract this Q&A as a node in the graph.
@@ -1033,18 +1022,7 @@ Replace `NODE_A` and `NODE_B` with the actual concept names from the user. Then
 After writing the explanation, save it back:
 
 ```bash
-$(cat .graphify_python) -c "
-from graphify.ingest import save_query_result
-from pathlib import Path
-save_query_result(
-    question='Path from NODE_A to NODE_B',
-    answer='ANSWER',
-    memory_dir=Path('graphify-out/memory'),
-    query_type='path_query',
-    source_nodes=PATH_NODES,  # list of node labels on the path
-)
-print('Path result saved to graphify-out/memory/')
-"
+$(cat .graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
 ```
 
 ---
@@ -1110,18 +1088,7 @@ Replace `NODE_NAME` with the concept the user asked about. Then write a 3-5 sent
 After writing the explanation, save it back:
 
 ```bash
-$(cat .graphify_python) -c "
-from graphify.ingest import save_query_result
-from pathlib import Path
-save_query_result(
-    question='Explain NODE_NAME',
-    answer='ANSWER',
-    memory_dir=Path('graphify-out/memory'),
-    query_type='explain',
-    source_nodes=['NODE_NAME'],
-)
-print('Explanation saved to graphify-out/memory/')
-"
+$(cat .graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
 ```
 
 ---
diff --git a/graphify/skill-opencode.md b/graphify/skill-opencode.md
index e03db2b7..9ced2a61 100644
--- a/graphify/skill-opencode.md
+++ b/graphify/skill-opencode.md
@@ -946,18 +946,7 @@ Replace `QUESTION` with the user's actual question, `MODE` with `bfs` or `dfs`,
 After writing the answer, save it back into the graph so it improves future queries:
 
 ```bash
-$(cat .graphify_python) -c "
-from graphify.ingest import save_query_result
-from pathlib import Path
-save_query_result(
-    question='QUESTION',
-    answer='ANSWER',
-    memory_dir=Path('graphify-out/memory'),
-    query_type='query',
-    source_nodes=SOURCE_NODES,  # list of node labels cited, or []
-)
-print('Query result saved to graphify-out/memory/')
-"
+$(cat .graphify_python) -m graphify save-result --question "QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
 ```
 
 Replace `QUESTION` with the question, `ANSWER` with your full answer text, `SOURCE_NODES` with the list of node labels you cited. This closes the feedback loop: the next `--update` will extract this Q&A as a node in the graph.
@@ -1032,18 +1021,7 @@ Replace `NODE_A` and `NODE_B` with the actual concept names from the user. Then
 After writing the explanation, save it back:
 
 ```bash
-$(cat .graphify_python) -c "
-from graphify.ingest import save_query_result
-from pathlib import Path
-save_query_result(
-    question='Path from NODE_A to NODE_B',
-    answer='ANSWER',
-    memory_dir=Path('graphify-out/memory'),
-    query_type='path_query',
-    source_nodes=PATH_NODES,  # list of node labels on the path
-)
-print('Path result saved to graphify-out/memory/')
-"
+$(cat .graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
 ```
 
 ---
@@ -1109,18 +1087,7 @@ Replace `NODE_NAME` with the concept the user asked about. Then write a 3-5 sent
 After writing the explanation, save it back:
 
 ```bash
-$(cat .graphify_python) -c "
-from graphify.ingest import save_query_result
-from pathlib import Path
-save_query_result(
-    question='Explain NODE_NAME',
-    answer='ANSWER',
-    memory_dir=Path('graphify-out/memory'),
-    query_type='explain',
-    source_nodes=['NODE_NAME'],
-)
-print('Explanation saved to graphify-out/memory/')
-"
+$(cat .graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
 ```
 
 ---
diff --git a/graphify/skill-trae.md b/graphify/skill-trae.md
index 8b2e1ef8..73d2979e 100644
--- a/graphify/skill-trae.md
+++ b/graphify/skill-trae.md
@@ -915,18 +915,7 @@ Replace `QUESTION` with the user's actual question, `MODE` with `bfs` or `dfs`,
 After writing the answer, save it back into the graph so it improves future queries:
 
 ```bash
-$(cat .graphify_python) -c "
-from graphify.ingest import save_query_result
-from pathlib import Path
-save_query_result(
-    question='QUESTION',
-    answer='ANSWER',
-    memory_dir=Path('graphify-out/memory'),
-    query_type='query',
-    source_nodes=SOURCE_NODES,
-)
-print('Query result saved to graphify-out/memory/')
-"
+$(cat .graphify_python) -m graphify save-result --question "QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
 ```
 
 Replace `QUESTION` with the question, `ANSWER` with your full answer text, `SOURCE_NODES` with the list of node labels you cited. This closes the feedback loop: the next `--update` will extract this Q&A as a node in the graph.
@@ -1001,18 +990,7 @@ Replace `NODE_A` and `NODE_B` with the actual concept names from the user. Then
 After writing the explanation, save it back:
 
 ```bash
-$(cat .graphify_python) -c "
-from graphify.ingest import save_query_result
-from pathlib import Path
-save_query_result(
-    question='Path from NODE_A to NODE_B',
-    answer='ANSWER',
-    memory_dir=Path('graphify-out/memory'),
-    query_type='path_query',
-    source_nodes=PATH_NODES,
-)
-print('Path result saved to graphify-out/memory/')
-"
+$(cat .graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
 ```
 
 ---
@@ -1077,18 +1055,7 @@ Replace `NODE_NAME` with the concept the user asked about. Then write a 3-5 sent
 After writing the explanation, save it back:
 
 ```bash
-$(cat .graphify_python) -c "
-from graphify.ingest import save_query_result
-from pathlib import Path
-save_query_result(
-    question='Explain NODE_NAME',
-    answer='ANSWER',
-    memory_dir=Path('graphify-out/memory'),
-    query_type='explain',
-    source_nodes=['NODE_NAME'],
-)
-print('Explanation saved to graphify-out/memory/')
-"
+$(cat .graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
 ```
 
 ---
diff --git a/graphify/skill-windows.md b/graphify/skill-windows.md
index e8f9c9de..e635c020 100644
--- a/graphify/skill-windows.md
+++ b/graphify/skill-windows.md
@@ -937,18 +937,7 @@ Replace `QUESTION` with the user's actual question, `MODE` with `bfs` or `dfs`,
 After writing the answer, save it back into the graph so it improves future queries:
 
 ```powershell
-python -c "
-from graphify.ingest import save_query_result
-from pathlib import Path
-save_query_result(
-    question='QUESTION',
-    answer='ANSWER',
-    memory_dir=Path('graphify-out/memory'),
-    query_type='query',
-    source_nodes=SOURCE_NODES,  # list of node labels cited, or []
-)
-print('Query result saved to graphify-out/memory/')
-"
+python -m graphify save-result --question "QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
 ```
 
 Replace `QUESTION` with the question, `ANSWER` with your full answer text, `SOURCE_NODES` with the list of node labels you cited. This closes the feedback loop: the next `--update` will extract this Q&A as a node in the graph.
@@ -1023,18 +1012,7 @@ Replace `NODE_A` and `NODE_B` with the actual concept names from the user. Then
 After writing the explanation, save it back:
 
 ```powershell
-python -c "
-from graphify.ingest import save_query_result
-from pathlib import Path
-save_query_result(
-    question='Path from NODE_A to NODE_B',
-    answer='ANSWER',
-    memory_dir=Path('graphify-out/memory'),
-    query_type='path_query',
-    source_nodes=PATH_NODES,  # list of node labels on the path
-)
-print('Path result saved to graphify-out/memory/')
-"
+python -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
 ```
 
 ---
@@ -1100,18 +1078,7 @@ Replace `NODE_NAME` with the concept the user asked about. Then write a 3-5 sent
 After writing the explanation, save it back:
 
 ```powershell
-python -c "
-from graphify.ingest import save_query_result
-from pathlib import Path
-save_query_result(
-    question='Explain NODE_NAME',
-    answer='ANSWER',
-    memory_dir=Path('graphify-out/memory'),
-    query_type='explain',
-    source_nodes=['NODE_NAME'],
-)
-print('Explanation saved to graphify-out/memory/')
-"
+python -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
 ```
 
 ---
diff --git a/graphify/skill.md b/graphify/skill.md
index bd744e78..ec09523d 100644
--- a/graphify/skill.md
+++ b/graphify/skill.md
@@ -958,18 +958,7 @@ Replace `QUESTION` with the user's actual question, `MODE` with `bfs` or `dfs`,
 After writing the answer, save it back into the graph so it improves future queries:
 
 ```bash
-$(cat graphify-out/.graphify_python) -c "
-from graphify.ingest import save_query_result
-from pathlib import Path
-save_query_result(
-    question='QUESTION',
-    answer='ANSWER',
-    memory_dir=Path('graphify-out/memory'),
-    query_type='query',
-    source_nodes=SOURCE_NODES,  # list of node labels cited, or []
-)
-print('Query result saved to graphify-out/memory/')
-"
+$(cat graphify-out/.graphify_python) -m graphify save-result --question "QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
 ```
 
 Replace `QUESTION` with the question, `ANSWER` with your full answer text, `SOURCE_NODES` with the list of node labels you cited. This closes the feedback loop: the next `--update` will extract this Q&A as a node in the graph.
@@ -1044,18 +1033,7 @@ Replace `NODE_A` and `NODE_B` with the actual concept names from the user. Then
 After writing the explanation, save it back:
 
 ```bash
-$(cat graphify-out/.graphify_python) -c "
-from graphify.ingest import save_query_result
-from pathlib import Path
-save_query_result(
-    question='Path from NODE_A to NODE_B',
-    answer='ANSWER',
-    memory_dir=Path('graphify-out/memory'),
-    query_type='path_query',
-    source_nodes=PATH_NODES,  # list of node labels on the path
-)
-print('Path result saved to graphify-out/memory/')
-"
+$(cat graphify-out/.graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
 ```
 
 ---
@@ -1121,18 +1099,7 @@ Replace `NODE_NAME` with the concept the user asked about. Then write a 3-5 sent
 After writing the explanation, save it back:
 
 ```bash
-$(cat graphify-out/.graphify_python) -c "
-from graphify.ingest import save_query_result
-from pathlib import Path
-save_query_result(
-    question='Explain NODE_NAME',
-    answer='ANSWER',
-    memory_dir=Path('graphify-out/memory'),
-    query_type='explain',
-    source_nodes=['NODE_NAME'],
-)
-print('Explanation saved to graphify-out/memory/')
-"
+$(cat graphify-out/.graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
 ```
 
 ---
diff --git a/graphify/watch.py b/graphify/watch.py
index c0cabdde..0d92bd6c 100644
--- a/graphify/watch.py
+++ b/graphify/watch.py
@@ -24,19 +24,16 @@ def _rebuild_code(watch_path: Path, *, follow_symlinks: bool = False) -> bool:
     Returns True on success, False on error.
     """
     try:
-        from graphify.extract import collect_files, extract
+        from graphify.extract import extract
+        from graphify.detect import detect, FileType
         from graphify.build import build_from_json
         from graphify.cluster import cluster, score_all
         from graphify.analyze import god_nodes, surprising_connections, suggest_questions
         from graphify.report import generate
         from graphify.export import to_json
 
-        code_files = collect_files(watch_path, follow_symlinks=follow_symlinks)
-        code_files = [
-            f for f in code_files
-            if "graphify-out" not in f.parts
-            and "__pycache__" not in f.parts
-        ]
+        detected = detect(watch_path, follow_symlinks=follow_symlinks)
+        code_files = [Path(f) for f in detected[FileType.CODE]]
 
         if not code_files:
             print("[graphify watch] No code files found - nothing to rebuild.")
@@ -47,7 +44,7 @@ def _rebuild_code(watch_path: Path, *, follow_symlinks: bool = False) -> bool:
         detection = {
             "files": {"code": [str(f) for f in code_files], "document": [], "paper": [], "image": []},
             "total_files": len(code_files),
-            "total_words": 0,  # not needed during watch rebuild
+            "total_words": detected.get("total_words", 0),
         }
 
         G = build_from_json(result)