chore: add graphify hooks, CLAUDE.md, and gitignore updates

- .claude/settings.json: PreToolUse hooks redirecting grep/file reads
  to graphify query when graph.json exists
- CLAUDE.md: graphify knowledge graph instructions for Claude Code sessions
- .gitignore: exclude graphify-out/ and .claude/settings.local.json
- .vscode/extensions.json: add comments header

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

.claude/settings.json

@@ -0,0 +1,24 @@
+{
+  "hooks": {
+    "PreToolUse": [
+      {
+        "matcher": "Bash",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "CMD=$(python3 -c \"import json,sys; d=json.load(sys.stdin); print(d.get('tool_input',d).get('command',''))\" 2>/dev/null || true); case \"$CMD\" in *grep*|*rg\\ *|*ripgrep*|*find\\ *|*fd\\ *|*ack\\ *|*ag\\ *)   [ -f graphify-out/graph.json ] &&   echo '{\"hookSpecificOutput\":{\"hookEventName\":\"PreToolUse\",\"additionalContext\":\"graphify: knowledge graph at graphify-out/. For focused questions, run `graphify query \\\"<question>\\\"` (scoped subgraph, usually much smaller than GRAPH_REPORT.md) instead of grepping raw files. Read GRAPH_REPORT.md only for broad architecture context.\"}}'   || true ;; esac"
+          }
+        ]
+      },
+      {
+        "matcher": "Read|Glob",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "HIT=$(python3 -c \"import json,sys;d=json.load(sys.stdin);t=d.get('tool_input',d);s=(str(t.get('file_path') or '')+' '+str(t.get('pattern') or '')+' '+str(t.get('path') or '')).lower().replace(chr(92),'/');exts=('.py','.js','.ts','.tsx','.jsx','.go','.rs','.java','.rb','.c','.h','.cpp','.hpp','.cc','.cs','.kt','.swift','.php','.scala','.lua','.sh','.md','.rst','.txt','.mdx');sys.stdout.write('1' if 'graphify-out/' not in s and any(e in s for e in exts) else '')\" 2>/dev/null || true); if [ \"$HIT\" = 1 ] && [ -f graphify-out/graph.json ]; then echo '{\"hookSpecificOutput\":{\"hookEventName\":\"PreToolUse\",\"additionalContext\":\"graphify: knowledge graph at graphify-out/. For codebase questions, run `graphify query \\\"<question>\\\"` (scoped subgraph, usually much smaller than reading files one by one), `graphify explain \\\"<concept>\\\"`, or `graphify path \\\"<A>\\\" \\\"<B>\\\"`, instead of reading source files to answer. Read raw files to modify or debug specific code, or when the graph lacks the detail.\"}}'; fi || true"
+          }
+        ]
+      }
+    ]
+  }
+}

.gitignore

@@ -20,3 +20,7 @@ platformio.local.ini
 CODE_REVIEW.md
 tools/pngs/
 tools/gpx/
+
+# graphify
+graphify-out/
+.claude/settings.local.json

.vscode/extensions.json

@@ -1,4 +1,6 @@
 {
+    // See http://go.microsoft.com/fwlink/?LinkId=827846
+    // for the documentation about the extensions.json format
     "recommendations": [
         "pioarduino.pioarduino-ide",
         "platformio.platformio-ide"

CLAUDE.md

@@ -0,0 +1,9 @@
+## graphify
+
+This project has a knowledge graph at graphify-out/ with god nodes, community structure, and cross-file relationships.
+
+Rules:
+- For codebase questions, first run `graphify query "<question>"` when graphify-out/graph.json exists. Use `graphify path "<A>" "<B>"` for relationships and `graphify explain "<concept>"` for focused concepts. These return a scoped subgraph, usually much smaller than GRAPH_REPORT.md or raw grep output.
+- If graphify-out/wiki/index.md exists, use it for broad navigation instead of raw source browsing.
+- Read graphify-out/GRAPH_REPORT.md only for broad architecture review or when query/path/explain do not surface enough context.
+- After modifying code, run `graphify update .` to keep the graph current (AST-only, no API cost).