feat: geometric graph topology + module pages + phantom link cleanup

Graph topology (Metatron's Cube pattern — 1 center + 12 outer nodes):
- index: now links to ALL 12 other nodes (complete hub)
- Inner ring cycle: hot→log→overview→dashboard→concepts/_index→entities/_index
  - Added: hot↔WikiMap, log↔sources/_index, dashboard↔concepts/_index
  - Added: entities/_index↔hot, entities/_index↔LLM Wiki Pattern
  - Added: sources/_index↔log, sources/_index↔entities/_index
- Outer ring: concepts connected in triangle + Karpathy/sources cross-linked
  - Added: dashboard↔Compounding, entities/_index↔LLM Wiki Pattern

graph.json physics for geometric arrangement:
- repelStrength: 80 (strong push-apart for uniform spacing)
- linkStrength: 3.0 (locks ring geometry)
- linkDistance: 80 (tighter rings)
- centerStrength: 0.25 (moderate center pull)
- nodeSizeMultiplier: 2.0 (hub nodes visually dominant)
- Added colors: questions=yellow, comparisons=red, nav=teal

Phantom links removed from Hot Cache.md:
- Removed [[Page A]], [[Page B]], [[New Page 1]], [[Existing Page]]

New module pages:
- wiki/questions/How does the LLM Wiki pattern work.md
- wiki/comparisons/Wiki vs RAG.md
- Adds questions/ and comparisons/ domains to the graph (yellow + red nodes)

wiki/comparisons/Wiki vs RAG.md

@@ -0,0 +1,56 @@
+---
+type: comparison
+title: "Wiki vs RAG"
+subjects:
+  - "[[LLM Wiki Pattern]]"
+  - "RAG (Retrieval-Augmented Generation)"
+dimensions:
+  - "How knowledge is stored"
+  - "Query cost"
+  - "Infrastructure"
+  - "Maintenance"
+  - "Scale limit"
+verdict: "Wiki wins at <1000 pages. RAG wins at enterprise scale."
+created: 2026-04-07
+updated: 2026-04-07
+tags:
+  - comparison
+  - llm-wiki
+  - knowledge-management
+status: mature
+related:
+  - "[[LLM Wiki Pattern]]"
+  - "[[Compounding Knowledge]]"
+  - "[[index]]"
+  - "[[How does the LLM Wiki pattern work]]"
+sources: []
+---
+
+# Wiki vs RAG
+
+## Overview
+
+Both approaches let you query a large document collection. They differ fundamentally in when synthesis happens.
+
+## Comparison
+
+| Dimension | LLM Wiki | Semantic RAG |
+|-----------|----------|-------------|
+| **How knowledge is stored** | Pre-compiled markdown pages with cross-references already built | Raw chunks in a vector database |
+| **Finding answers** | Read index → follow links → synthesize | Embed query → similarity search → assemble |
+| **Query cost** | Low — synthesis already done | Higher — re-derives on every query |
+| **Infrastructure** | Just markdown files | Embedding model + vector DB + chunking pipeline |
+| **Maintenance** | Run a lint pass | Re-embed when content changes |
+| **Scale limit** | ~hundreds of pages (index file navigation) | Millions of documents |
+| **Setup time** | 5 minutes | Hours to days |
+| **Contradiction detection** | Built in — LLM flags on ingest | Manual |
+
+## Verdict
+
+**Under 1000 pages → LLM Wiki.** The index file is sufficient for navigation, token cost is low, setup is minimal, and the pre-compiled synthesis means every query benefits from everything ever read.
+
+**Over 100K pages → RAG.** The index file becomes too large to read, and embedding-based retrieval becomes more efficient than full-index scanning.
+
+The sweet spot: run the wiki pattern for active research (where things are being added, synthesized, and connected), then export to a vector store if the collection grows beyond the index threshold.
+
+(Source: [[LLM Wiki Pattern]], [[Compounding Knowledge]])

wiki/concepts/Hot Cache.md

@@ -60,9 +60,9 @@ YYYY-MM-DD — [what happened]
 - [Second]
 
 ## Recent Changes
-- Created: [[New Page 1]]
-- Updated: [[Existing Page]] (added section on X)
-- Flagged: Contradiction between [[Page A]] and [[Page B]]
+- Created: new wiki pages from this ingest
+- Updated: existing pages with new connections
+- Flagged: contradictions between sources where found
 
 ## Active Threads
 - User is researching [topic]

wiki/concepts/_index.md

@@ -10,6 +10,11 @@ domain: knowledge-management
 status: evergreen
 related:
   - "[[index]]"
+  - "[[dashboard]]"
+  - "[[Wiki Map]]"
+  - "[[Hot Cache]]"
+  - "[[LLM Wiki Pattern]]"
+  - "[[Compounding Knowledge]]"
   - "[[LLM Wiki Pattern]]"
   - "[[Hot Cache]]"
   - "[[Compounding Knowledge]]"

wiki/entities/_index.md

@@ -10,6 +10,8 @@ status: evergreen
 related:
   - "[[index]]"
   - "[[Andrej Karpathy]]"
+  - "[[hot]]"
+  - "[[LLM Wiki Pattern]]"
 ---
 
 # Entities Index

wiki/hot.md

@@ -9,6 +9,8 @@ status: evergreen
 related:
   - "[[index]]"
   - "[[log]]"
+  - "[[Wiki Map]]"
+  - "[[entities/_index]]"
 ---
 
 # Recent Context

wiki/index.md

@@ -10,6 +10,15 @@ related:
   - "[[overview]]"
   - "[[log]]"
   - "[[hot]]"
+  - "[[dashboard]]"
+  - "[[Wiki Map]]"
+  - "[[concepts/_index]]"
+  - "[[entities/_index]]"
+  - "[[sources/_index]]"
+  - "[[LLM Wiki Pattern]]"
+  - "[[Hot Cache]]"
+  - "[[Compounding Knowledge]]"
+  - "[[Andrej Karpathy]]"
 ---
 
 # Wiki Index

wiki/log.md

@@ -9,6 +9,8 @@ status: evergreen
 related:
   - "[[index]]"
   - "[[hot]]"
+  - "[[overview]]"
+  - "[[sources/_index]]"
 ---
 
 # Operation Log

wiki/meta/dashboard.md

@@ -10,6 +10,8 @@ related:
   - "[[index]]"
   - "[[overview]]"
   - "[[log]]"
+  - "[[concepts/_index]]"
+  - "[[Compounding Knowledge]]"
 ---
 
 # Wiki Dashboard

wiki/questions/How does the LLM Wiki pattern work.md

@@ -0,0 +1,52 @@
+---
+type: question
+title: "How does the LLM Wiki pattern work?"
+question: "How does the LLM Wiki pattern work and why is it better than RAG?"
+answer_quality: definitive
+created: 2026-04-07
+updated: 2026-04-07
+tags:
+  - question
+  - llm-wiki
+  - knowledge-management
+status: developing
+related:
+  - "[[LLM Wiki Pattern]]"
+  - "[[Compounding Knowledge]]"
+  - "[[Hot Cache]]"
+  - "[[index]]"
+  - "[[Wiki vs RAG]]"
+sources: []
+---
+
+# How does the LLM Wiki pattern work?
+
+**Question:** How does the LLM Wiki pattern work and why is it better than RAG?
+
+## Answer
+
+The [[LLM Wiki Pattern]] turns an LLM into a knowledge architect rather than a search engine.
+
+**Standard RAG** (Retrieval-Augmented Generation): every query searches raw documents, retrieves chunks, and assembles an answer from scratch. Nothing is built up. Ask the same question twice — it does the same work twice.
+
+**The wiki pattern** is different. When a source arrives, the LLM reads it and integrates it: updating entity pages, noting contradictions, adding cross-references. The synthesis is done once and persists. Every query benefits from all previous ingests.
+
+### The three layers
+
+1. **`.raw/`** — your source documents. Immutable. Claude reads, never modifies.
+2. **`wiki/`** — Claude-generated knowledge. Summaries, entities, concepts, synthesis.
+3. **`CLAUDE.md`** — the schema. Tells Claude how the wiki is structured and what to do.
+
+### Why it compounds
+
+See [[Compounding Knowledge]] for the full argument. The short version: each new source doesn't just add one page — it enriches 8-15 existing pages. The connections between pages are where the value lives, not the raw content itself.
+
+### The hot cache shortcut
+
+[[Hot Cache]] (wiki/hot.md) is a ~500-word summary of recent context. New sessions read it first. Cross-project references read it first. It prevents re-reading the whole wiki just to answer "where were we?"
+
+(Source: [[LLM Wiki Pattern]])
+
+## Confidence
+
+definitive — this is the core concept the entire vault demonstrates.

wiki/sources/_index.md

@@ -9,6 +9,9 @@ tags:
 status: evergreen
 related:
   - "[[index]]"
+  - "[[log]]"
+  - "[[entities/_index]]"
+  - "[[Andrej Karpathy]]"
 ---
 
 # Sources Index