create-claude-cabinet 0.8.3 → 0.8.4

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/package.json +1 -1
  2. package/templates/rules/memory-capture.md +12 -4
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "create-claude-cabinet",
3
- "version": "0.8.3",
3
+ "version": "0.8.4",
4
4
  "description": "Claude Cabinet — opinionated process scaffolding for Claude Code projects",
5
5
  "bin": {
6
6
  "create-claude-cabinet": "bin/create-claude-cabinet.js"
package/templates/rules/memory-capture.md CHANGED
@@ -51,7 +51,15 @@ Memory types: `decision`, `lesson`, `preference`, `constraint`, `pattern`
51
51
 
52
52
  Do NOT capture after every interaction. Capture when something worth
53
53
  remembering actually happens. Most messages in a session produce nothing
54
- worth storing. A typical session might generate 0-3 memories.
55
-
56
- Over-capturing degrades retrieval quality. When in doubt, don't capture.
57
- The debrief sweep catches anything important that was missed.
54
+ worth storing.
55
+
56
+ Cadence scales with session length and discovery density. A short
57
+ focused session might produce 0-1 memories. A long session with
58
+ multiple discoveries, corrections, and decisions could produce 5-10+.
59
+ The right number is however many genuinely worth-remembering things
60
+ happened — no artificial cap.
61
+
62
+ Over-capturing degrades retrieval quality. The test: *"Would a future
63
+ session benefit from knowing this?"* If yes, capture it. If it's just
64
+ noise or ephemera, skip it. The debrief sweep catches anything
65
+ important that was missed during the session.