feat: confluence benchmark, pattern extractor, agent KB, UX spec

- extract-patterns.js: mines layered arch, ArgoCD appsets, cloud regions,
  CIDR allocations, naming conventions, sync waves, tech stack from code
- agent-kb.js: token-efficient JSON rendering of same doc tree
- eval-confluence-ref-questions.json: 32 reference-only benchmark questions
- wiggum-v2.sh: Ralph Wiggum loop targeting confluence baseline (77.8%)
- docs/human-ux-spec.md: BMad UX designer spec for human doc structure
- Eval results: V2 at 28.7% vs confluence 77.8% baseline
- Hub/spoke ownership now correctly extracted (95% on that question)
- Naming conventions, regions, CIDRs surfaced in system-architecture.md

patch-sysdoc-helm.js

@@ -0,0 +1,14 @@
+const fs = require('fs');
+let content = fs.readFileSync('/home/node/.openclaw/workspace/projects/dev-intel-v2/sysdoc.js', 'utf8');
+
+const oldStr = `  // Name-to-file lookup for agent navigation
+  helmIndexContent += '## Quick Lookup (by chart name)\\n\\n';`;
+
+const newStr = `  helmIndexContent += '## Helm Sync Waves (Bootstrapping Order)\\n\\n| Wave | Count | Resources |\\n|---|---|---|\\n';
+  helmIndexContent += patterns.syncWaves.map(w => \`| \${w.wave} | \${w.resources.length} | \${w.resources.slice(0, 5).map(r => \\\`\\\${r.kind}:\\\${r.name}\\\`).join(', ')}\${w.resources.length > 5 ? '...' : ''} |\`).join('\\n') + '\\n\\n';
+
+  // Name-to-file lookup for agent navigation
+  helmIndexContent += '## Quick Lookup (by chart name)\\n\\n';`;
+
+content = content.replace(oldStr, newStr);
+fs.writeFileSync('/home/node/.openclaw/workspace/projects/dev-intel-v2/sysdoc.js', content);