chore: initial commit — portable agent memory & skill scaffold

Extracted and cleaned up from a prior WSL/Windows agent-memory setup.
Contains only project-agnostic content:

- Claude_Memory/: feedback rules, user profile, reusable reference docs,
  session scratch space (claude_info/, claude_log/), mirrored skill defs
- caveman/: ultra-compressed communication mode skill + subcommands
- html-slide-deck/: self-contained HTML slide deck builder skill

Project-specific knowledge (previously mixed in) was moved out to each
project's own repository as part of this cleanup.

caveman/caveman-stats/SKILL.md

@@ -0,0 +1,10 @@
+---
+name: caveman-stats
+description: >
+  Show real token usage and estimated savings for the current session.
+  Reads directly from the Claude Code session log — no AI estimation.
+  Triggers on /caveman-stats. Output is injected by the mode-tracker hook;
+  the model itself does not compute the numbers.
+---
+
+This skill is delivered by `hooks/caveman-stats.js` (read by `hooks/caveman-mode-tracker.js` on `/caveman-stats`). The model does not need to do anything when this skill fires — the hook returns `decision: "block"` with the formatted stats as the reason. The user sees the numbers immediately.