[CLAUDE] Docs: S152 closeout — bookend hình B trọn 2 đầu + owner (30)(31)(32) + queue memory-ops TRỌN (squash 20 wal:)

- Owner 3-quyết: (30) JUMP để-nguyên-theo-nhịp · (31) 4 persona +NEVER-block (restart ĐÃ THOẢ) · (32) vòng 1→5 AUTO — lô consent gỡ 9 site (5 H1 + ring1-tự-bắt + 3 trio; E-013 EXT)
- Memory-ops TRỌN: A1-A4/D1/D2/R1/B-series — A7 392/392 · mfe 20/20-100% lần đầu · lead-gap drain 24.728→16.485B · strike-ledger + WARN-latch (-Ack = owner-action)
- V4 sleep AUTO đầu: 1 shard thật/16 KÊU · ring4 đầu-đời TRƯỢT-4/5 → 4 fix gist (scribe sub-ring4-close vì return-only)
- Thư model re-stamp: 59ce1d0f → 9c909007 published (G-024a) — adap-report Đính-chính @S152 + sweep 13 bề-mặt LIVE
- Bookend @close: stale 6 FLAG + gap 2 FLAG → vá 8/8; ring2 8/8 ĐẠT (4-A pin-bản-cắt → slot 33) · ring1 48Đ/5T/59-claim
- M9 13 đơn-vị diary (3 S151-deep hồi-tố) · #53 ×10-chắc → tally 60-cận-dưới + errata subject-1b85713
- Session-log 2 run= + completeness-gate 5-vòng ĐẠT · HANDOFF segment S152 (carry 3-đóng/3-mới/23-giữ; slot 33/34)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

eval/mfe/README.md

@@ -22,8 +22,16 @@ powershell.exe -ExecutionPolicy Bypass -File scripts\mfe-eval.ps1            # a
 powershell.exe -ExecutionPolicy Bypass -File scripts\mfe-eval.ps1 -Tier lead
 powershell.exe -ExecutionPolicy Bypass -File scripts\mfe-eval.ps1 -Tier sub
 powershell.exe -ExecutionPolicy Bypass -File scripts\mfe-eval.ps1 -Judge     # show judge scaffold (no scoring)
+powershell.exe -ExecutionPolicy Bypass -File scripts\mfe-eval.ps1 -Detail    # +per-item MISS list (which denominator items unmatched)
+powershell.exe -ExecutionPolicy Bypass -File scripts\mfe-eval.ps1 -Ack      # 🔴 OWNER-ACTION ONLY — acknowledge GOODHART-WARN, move warn_baseline
 ```
 
+### `-Detail` / `-Ack` (B4 @S152)
+
+- **`-Detail`** — read-only diagnostic: prints one `MISS: <item>` line per unmatched denominator item, so a coverage drop is traceable to the exact item instead of a bare percentage. Safe to run any time.
+- **GOODHART-WARN is LATCHED** — when strikes rise vs the persisted `warn_baseline` (stored in `.mfe-state.json`), the warning repeats on **every** run until acknowledged. It does NOT self-clear on a later good run (self-clearing would let one lucky run bury a real regression).
+- **`-Ack`** — the ONLY thing that moves `warn_baseline` (and appends the ack to `history[]`). 🔴 **Owner-action:** lead/agents may run `-Detail` freely but MUST NOT run `-Ack` on their own — acknowledging a Goodhart warning = accepting the new strike level as the reference point, and that acceptance belongs to anh (same rule as every threshold/number in `memory-budget.json`). Lead surfaces the WARN; anh decides to ack.
+
 Opt-in at session ends: `/session-start … eval` (baseline) and `/session-end … eval` (retention) — see `session-start.md §2.1.6` / `session-end.md §L.b(c)`. Default (no `eval`) = unchanged behaviour.
 
 ## Operational decision (the point)