[CLAUDE] Docs: adopt Harness-9 — L2 archive dark-matter recovery (4 sub) + adap 2-workflow mandate (S70)

3-stage Workflow run-id evidence: investigate wf_be952f3c-97f / implement wf_a58e0d15-beb / audit wf_9520d8cd-4fe.

PART 1 (L2 recovery): 4 over-cap sub (cicd-monitor/investigator-codebase/reviewer/implementer-backend)
curated L1->L2 byte-exact + archive/_INDEX.md (substring sha-keyed pointers, no line-hints)
+ <period>.gist.md (4-field distill, distill-gen:1, verbatim frozen). All 4 MEMORY.md now < 25KB
auto-inject cap (closes P1 curate-debt). ~240KB archive no longer RAG-dark. 0-byte-loss git+sha
verified (Stage C audit + em-main self-gate on 2 reviewer StructuredOutput no-returns). Read-side
gap fixed (MEMORY.md L5 header -> _INDEX). + memory-budget.json (seed-by-measure) +
scripts/measure-agent-memory.ps1 + .ragignore guard.

PART 2/3 (process mandate): every adap = 2 separate workflows (implement + review) + report with
run-id; short-but-needs-confirm still requires review. Codified in .claude/commands/adap-apply.md
+ agents/README.md (Upgrade S70) + session-start.md (§2.1.2 budget-audit, pending-restart).

adap-report + email-back to AI_INFRA (body-hash 7c07b716e775).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

.claude/commands/session-start.md

@@ -71,6 +71,13 @@ Em main xác nhận **lead model resolve được** đầu session. Lead SE = **
 - **⬜ harvest-curator (H2):** spawn → báo **harvest-MD mới** (workflow-wave / sub-agent / agent-team kể từ last) + **delta mồ-côi chưa-APPEND** + wave-folder tồn-đọng. Bắt 0-byte memory (gotcha #53) + delta chưa thu-hoạch.
 - Cơ-chế = báo-lại-diff đầu session (FORM tự do trình bày). 2 monitor spawn parallel OK. **Light session / hỏi-đáp → có thể skip; bug/feature/multi-agent/wave session → nên chạy.**
 
+### 2.1.2 Memory L2 budget-audit (Harness-9 — 2026-06-17)
+
+> Read-side "vật-chất-tối": archive `agent-memory/<sub>/archive/*.md` KHÔNG vào RAG. Inject **mục-lục** (`archive/_INDEX.md`), nội dung verbatim + `.gist.md` đọc-theo-nhu-cầu. "Inject tấm bản-đồ, KHÔNG inject lãnh-thổ."
+
+- Đọc `.claude/agent-memory/memory-budget.json` → so kích-thước THẬT `_INDEX.md` mỗi sub vs cap. Nếu cắt-cho-vừa-ngân-sách đang rớt dấu-mốc quan trọng → **bump budget** (chốt-chặn chống "quên chỉnh ngân sách"). Đo lại bằng `scripts/measure-agent-memory.ps1` (seed-by-measure — KHÔNG đặt cap bằng số tưởng tượng).
+- L1 over-cap → curate L1→L2 (byte-exact additive) + build/refresh `_INDEX.md` (con-trỏ **substring** sha-keyed, fallback Ctrl-F) + `<period>.gist.md` (nén 4-field, `distill-gen` counter, verbatim FROZEN). Rollout đầu: 4 over-cap sub (S70).
+
 ### 2.2 Skill registry (6 skill)
 - Liệt kê: `contract-workflow` · `form-engine` · `permission-matrix` · `dependency-audit-erp` · `ef-core-migration` · `iis-deploy-runbook`
 - Dùng skill khi task khớp (KHÔNG tự suy luận lại). Phân bổ per agent: xem README skill matrix.