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

session 2026-06-13 (post-clear): L1 /health PR #174 + Studium Steps 5-7 + the dilution correction; chamber 23-source graduation

Browse Source
This commit is contained in:
David F Glidden
2026-06-13 16:20:17 +02:00
parent d31831b6db
commit 0845c7b43f
3 changed files with 79 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
claude/memory/skill-harvest-register.md
+9
View File
@@ -152,3 +152,12 @@ The single place proposed skills live so they don't evaporate between sessions.
| **Symmetria §3 flag: census-through-a-pattern** | Symmetria §3 flag (refines census-through-truncation) | A filter/regex used to *count* or *partition* a set can silently mis-match and the count reads as authoritative. Today `grep -iE 'LOG'` for meta-files matched "episteme**LOG**y"/"pheno­meno­**log**y"/"eco**log**y" → 49 false "meta" files (real = 4). Antidote: verify the pattern against known positives AND a known negative before trusting the partition; anchor patterns (`_LOG\.md$` not `LOG`). One step more specific than census-through-truncation (which is about *coverage* of the scan; this is about *correctness* of the matcher). | Symmetria §3 | **PROPOSED** |
*(Both genuine, both recurring-shaped. The first will pay off the next bulk corpus move — the 237 dirty files graduate incrementally, each a potential bulk op. The second caught a real false-count today and is a clean refinement of an existing flag.)*
## New proposals (2026-06-13 post-clear — L1 /health PR + Studium Steps 5-7 + the dilution correction)
| Element | Kind | One-line | Where it lands | Status |
|---|---|---|---|---|
| **Symmetria §3 flag: solve-the-constraint-by-discarding-the-value** | Symmetria §3 flag | A "fix" that satisfies a stated constraint by **removing the thing the constraint was protecting** is contamination shape — it optimizes away the value to avoid a failure. Caught HARD today: the steward's dilution memory → my first Step-7 verdict bounded vector to voice-scope-only ("never a global semantic index"), which *solved* dilution by discarding the engine's core value (whole-corpus depth+breadth). The steward caught it; correction restored depth-WITH-breadth (dilution = engineering problem, not a reason to forbid the capability). Antidote: when a constraint forces a fix, check the fix **preserves the value the constraint was guarding**, not merely satisfies the constraint. Kin to the executor-bias-to-satisfy-the-interlocutor, one level up (satisfy the *constraint* over the *truth*). | Symmetria §3 | **PROPOSED** |
| **verification-ladder: re-verify a workflow/sub-agent's per-item dispositions on the real apply** | verification-ladder entry | A sub-agent or background workflow that reports a per-item verdict from a **dry-run on a temp copy** can be wrong on the real apply — the agent's own audit can differ. Caught today: the cleaning-triage workflow classified `la-terre-…-Bachelard` as "cleanable to 0" (dry-run on a temp copy); the real `strip_cruft` run left **460 cruft** (7 passes). 23/25, not 25, graduated. Antidote: treat a workflow's dispositions as *candidates*; re-run the gate on the **real mutation** before trusting/committing. Kin to `/symmetria audit-agent` (calibration/convenience checks on a return), specialized to workflow per-item verdicts + the real-vs-dry-run gap. | `reference-verification-ladder.md` | **PROPOSED** |
*(Both earned in use today. The first is the load-bearing one — a clean name for a contamination shape the steward caught live, and a genuine addition to the §3 catalogue. The second is a concrete guardrail for the now-standard workflow-fan-out pattern.)*