memory: bundle accumulated 04-17/26 + lock ARC about-page architecture

Safety checkpoint before deep-audit Phase 0 of the ARC repo. Steward-authorized
commit-everything for rollback safety.

ARC architectural locks (2026-04-26 evening):
- Path 1 enfilade structure (separate Colophon and Lex items)
- 8-door enfilade locked: Colophon · Lex · Framework · Vignette · Attention ·
  Chamber · Tools · Now (+ Bio quiet link)
- Adsum and threshold-hic as two distinct texts on the reflowed About page
  (steward verbatim: "They are certainly not the same text")

ARC consolidation pass (canonical tracker project-arc-rework.md, +~700 lines):
fold 04-23 evening (Norris read), 04-24 (lex-method authored, posture cluster,
§XII Sidenotes, ARC CLAUDE.md cleanup), 04-25 (marks cluster, colophon-at-scale,
full Vico/Harrison lex-chain), 04-26 (chamber-library walk, cluster scaffolds,
canonical-tracker discipline surfaced).

Sibling-file integration: four 2026-04-26 frame files folded into the canonical
tracker (Integrations A/B/C/D) with INTEGRATED redirect notices retained as
audit trail.

New durable feedback memories:
- feedback-canonical-workstream-tracker-discipline (umbrella drift surfaced
  2026-04-26 by steward; proposes /wake-up + /wrap-up amendments)
- feedback-catalogues-stale-walk-trees (steward feedback on chamber-library
  catalogue currency)

Implementation plan drafted for the coming week: Phase 0 deep audit → Phase 5
cleanup, with steward additions on second pass (deep audit; Chamber v1 as own
browsable archive; clean rebuild of cluster sources rather than moving test
artifacts as canon).

Also bundled (untracked accumulation since 04-17):
- ~24 session memory + ledger files for 04-17 through 04-26 work
- ~10 feedback memories (BMF + ARC + working-method)
- 5 project memories (lex-as-method, strunk-white queue, plus today's four)
- 4 user memories (duality-rules, formation-practice, foundation-work, humic-layer)

Steward-side modifications also in this commit: ~/CLAUDE.md, bin/bmf-start.sh,
open-tasks.md, project-focus-april-may.md, session-2026-04-17 — all
pre-existing, not from today's session.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

claude/memory/open-tasks.md

@@ -2,8 +2,8 @@
 name: Open Tasks
 description: Centralized list of pending tasks across all projects, updated as items are completed or added
 type: project
+originSessionId: e55939da-2fa7-4e18-a2e5-8f8fd3a8c607
 ---
-
 # Open Tasks — Centralized
 
 **Last updated:** 2026-04-08
@@ -63,6 +63,16 @@ Two open inquiries. Exploratory, unsettled, explicitly non-blocking. Executor ac
 - [ ] `residual_risk` schema field
 - [ ] P-AC-2 (Host-Agent Constitutional Status)
 
+### When L2 resumes — directions from 2026-04-18 governance-substrate exchange
+
+Context: steward + Claude Code exchange on whether to build a ground-up model vs. apply governance substrate. Surfaced directions for L2 that draw on insights from parallel work accumulated while L2 was parked (L1 silent-degradation audit, Symmetria drift-pattern KG, wake/wrap ritualized pauses, ARC inherit-without-solve versioning regime). Full reasoning and verbatim exchange filed in MemPalace under `capablemind-thinking / seeds` as waterings of `ground-up-model-horizon`.
+
+- [ ] **Governance silent-degradation audit** — apply L1's 43-finding audit method to L2 decisions since parked. Examine every PENDING item that was deferred, every design note that went to FRAMING without advancing to INVARIANT, every review finding "acknowledged" but not acted on. Ask: is there a pattern? Method proven at L1 scale.
+- [ ] **Governance pattern KG** — a pattern layer over PENDING/REVIEWED making drift across decisions queryable. KG predicates like `<decision> → declined-frame → <frame>` or `<decision> → deferred-question → <question>`. Uses MemPalace infrastructure already running. Small technical effort.
+- [ ] **Exercise CD-03 against one recent L2 decision** — session-sized. Pick one pending or recent L2 decision, re-examine through CD-03's lens (infrastructure-toward-honest-inheritance, not toward-solution). If nothing changes, CD-03 is declared but not operational. Either outcome is informative.
+
+Not added here — held as horizon in seed: **counterfactual instance of L1+L2 running on an open-weight substrate** (Qwen/Llama locally). Substantial work, not near-term. Surfaced in seed kg_query; promote to open-tasks when readiness conditions allow.
+
 ---
 
 ## Priority 2 — Chamber