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

foxtrot-docs-v3/reference/subsystems/network-common.md

@@ -0,0 +1,10 @@
+# Subsystem: network-common
+
+**Kind:** domain
+**Files:** 24
+**Functions:** 0, **Classes:** 0
+
+## Structural Notes
+- Zero functions despite 24 files — likely a configuration-only or IaC subsystem
+- Isolated subsystem with no cross-subsystem dependencies — may be self-contained tooling or unused
+