docs: factual audit + reference sync — 260 findings corrected

Parallel 6-agent audit against official Anthropic docs (llms-full.txt).
Key corrections applied across permissions, hooks, MCP, security, privacy, reference.yaml.

Highlights:
- Fix MCP config path (~/.claude.json), mcpServers key, variable substitution syntax
- Fix permission modes (5 not 3), :* syntax (×6), Stop event description
- Fix hook JSON field names (hook_event_name, tool_name, tool_input, session_id)
- Fix filesystem restriction docs (permission rules, not settings.json keys)
- Fix data-privacy: 4-tier retention, /bug 5yr warning, ZDR conditions, 5 telemetry opt-out vars
- Add official llms.txt/llms-full.txt references to CLAUDE.md + machine-readable/llms.txt
- Reference.yaml: 375 entries re-synced (92% had wrong line numbers — guide grew 15K→21K lines)
- New script: scripts/resync-reference-yaml.py for automated line number sync
- Quiz: corrected answers for hooks (07), memory settings (03), MCP servers (08)

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

examples/hooks/README.md

@@ -54,7 +54,7 @@ Hooks are scripts that execute automatically on Claude Code events. They enable
 | `Notification` | When Claude sends a notification | Sound alerts, external notifications |
 | `SessionStart` | At session start | Initialization, environment setup |
 | `SessionEnd` | At session end | Cleanup, session summary |
-| `Stop` | User interrupts operation | State saving, graceful shutdown |
+| `Stop` | Claude finishes responding | Post-response actions, state saving |
 
 ## Advanced Guardrails (NEW in v3.3.0)