David/dotfiles
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore(memory): Basic Memory trial begins — sync normalization baseline (283 files)

Browse Source 
Basic Memory v0.21.6 first sync over the live memory dir (steward-authorized
live-dir trial, Option A 2026-06-06): adds permalink: to frontmatter, refolds
long YAML description lines, strips final newlines. Bodies untouched —
verified via full diff classification. From this commit forward, any diff in
claude/memory shows only what Basic Memory or the session writes.

Trial design: MemPalace untouched as incumbent; git status check on this dir
at every wrap; end-of-day evaluation (recall quality, sync robustness,
rebuild-from-files, malformed-file behavior).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
David F Glidden
2026-06-06 09:52:17 +02:00
co-authored by Claude Opus 4.8
parent 161fad7ae2
commit 3f9a89b00c
283 changed files with 2055 additions and 620 deletions
Download Patch File Download Diff File Expand all files Collapse all files
claude/memory/feedback-skill-success-is-reexplanation-reduction.md
+7 -3
View File
@@ -1,10 +1,14 @@
---
name: feedback-skill-success-is-reexplanation-reduction
description: The measure of success for skill / discipline / framework improvements is whether the steward stops having to reexplain himself — not whether the skills become more sophisticated. Sophistication that does not reduce reexplanation cost is decoration.
metadata:
description: The measure of success for skill / discipline / framework improvements
is whether the steward stops having to reexplain himself — not whether the skills
become more sophisticated. Sophistication that does not reduce reexplanation cost
is decoration.
metadata:
node_type: memory
type: feedback
originSessionId: 13bd65a2-634d-4ec4-a92c-d3d6fe0ee4db
permalink: claude-memory/feedback-skill-success-is-reexplanation-reduction
---
**Rule:** When evaluating a proposed change to the continuity-skill framework (wake-up, wrap-up, symmetria), to CLAUDE.md, to MemPalace skill substrate, or to any discipline-layer artifact: measure success by whether the change reduces the number of moments the steward has to reexplain himself to future Claude. *Skill sophistication is not the criterion; reduction of steward overhead is.* A change that adds capability without absorbing a recurring steward correction is decorative, regardless of how architecturally well-shaped it is.
@@ -16,4 +20,4 @@ metadata:
2. When evaluating *implementations* of authorized PENDING items (S0–S10 and successors), the acceptance test is not "does the procedure read well" but "does the next session need the steward to intervene at the moment this change addresses?" Test against live wake-ups and wrap-ups, not against the skill file in the abstract.
3. The criterion applies to this audit's own authorization sequence: if Phase 2 (Directive elaboration) lands but the executor still requires three corrections in a day to hold the time-the-task-requires principle, the elaboration has not yet absorbed its overhead. The work continues until the steward stops being the principle's carrier.
4. Related: [[feedback-load-bearing-not-by-immediate-weight]] — the audit principle that catches *which* small structural marks are worth adding. This criterion catches *whether* the marks (once added) have actually reduced the cost they were added to reduce. The two work together: load-bearing-by-future-prevention identifies candidates; reexplanation-reduction validates outcomes.
5. The criterion is also a Symmetria pulse question to hold: *"Is this change actually absorbing a recurring steward correction, or am I adding structure that looks disciplined but doesn't shift the load?"*
5. The criterion is also a Symmetria pulse question to hold: *"Is this change actually absorbing a recurring steward correction, or am I adding structure that looks disciplined but doesn't shift the load?"*