feat(docs): add architecture deep-dive documentation v3.4.0

Add comprehensive technical documentation explaining Claude Code internals:

- NEW: guide/architecture.md (~800 lines) - Complete architecture deep-dive
  - Master Loop (while tool_call), Tool Arsenal, Context Management
  - Sub-Agent Architecture, Permission System, MCP Integration
  - Edit Tool mechanics, Session persistence, Philosophy comparison
  - 5 ASCII diagrams, source confidence tiers (Tier 1/2/3)

- guide/ultimate-guide.md: Add Section 2.7 "Under the Hood" summary
- guide/cheatsheet.md: Add "Under the Hood (Quick Facts)" section
- machine-readable/reference.yaml: Add architecture index + deep_dive refs
- Update all navigation links across repository

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

guide/cheatsheet.md

@@ -6,7 +6,7 @@
 
 **Written with**: Claude (Anthropic)
 
-**Version**: 3.3.1 | **Last Updated**: January 2026
+**Version**: 3.4.0 | **Last Updated**: January 2026
 
 ---
 
@@ -153,6 +153,20 @@ Model: Sonnet | Ctx: 89.5k | Cost: $2.11 | Ctx(u): 56.0%
 
 ---
 
+## Under the Hood (Quick Facts)
+
+| Concept | Key Point |
+|---------|-----------|
+| **Master Loop** | Simple `while(tool_call)` — no DAGs, no classifiers |
+| **Tools** | 8 core: Bash, Read, Edit, Write, Grep, Glob, Task, TodoWrite |
+| **Context** | ~200K tokens, auto-compacts at 75-92% |
+| **Sub-agents** | Isolated context, max depth=1 |
+| **Philosophy** | "Less scaffolding, more model" — trust Claude's reasoning |
+
+**Deep dive**: [Architecture & Internals](./architecture.md)
+
+---
+
 ## Plan Mode & Think Levels
 
 | Feature | Activation | Usage |