[CLAUDE] Docs: S107 +office-document 12th sub (anh giao — Sub chính Office) — agent OD1-OD10 + skill nạp docx·xlsx·pptx·pdf + form-engine + MEMORY seed 2161B + wire 14-file (roster 11→12, VALID_ROLES hmw.js 9→10) — spawn-test pending CLI-restart

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

.claude/commands/session-start.md

@@ -1,5 +1,5 @@
 ---
-description: Bootstrap session SOLUTION_ERP — load context, audit state (11-agent + RAG + tests + monitor RE-REPORT), report plan. Run đầu mỗi session.
+description: Bootstrap session SOLUTION_ERP — load context, audit state (12-agent + RAG + tests + monitor RE-REPORT), report plan. Run đầu mỗi session.
 ---
 
 # /session-start — Session bootstrap (READ + AUDIT + REPORT)
@@ -46,21 +46,22 @@ Em main xác nhận **lead model resolve được** đầu session. Lead SE = **
 4. **`docs/PROJECT-MAP.md`** — bản đồ tổng quan module
 5. **`docs/changelog/migration-todos.md`** — atomic tasks theo phase (Phase 11 polish hiện tại)
 6. **`docs/workflow-contract.md`** — state machine 9 phase HĐ (base pattern cho PE/Proposal workflow V2)
-7. **`.claude/agents/README.md`** — 11-agent decision tree + skill matrix + split boundary
+7. **`.claude/agents/README.md`** — 12-agent decision tree + skill matrix + split boundary
 8. **`.claude/agent-memory/{spawned-agent}/MEMORY.md`** — L1 HOT auto-inject (Tiered Memory v1 ~30KB) + L2 `archive/` Read-on-demand + L3 RAG `search_memory` just-in-time
 9. **User auto-memory `MEMORY.md`** — auto-loaded bởi harness (index feedback_* entries)
 10. **Liên quan task hiện tại:** `docs/rules.md`, `docs/architecture.md`, `docs/gotchas.md` (số hiện tại → `docs/STATUS.md`), `docs/database/schema-diagram.md`, `docs/flows/`
 
 ## Phase 2 — AUDIT (state check)
 
-### 2.1 Sub-agent state (11-agent topology — 9 product/quality + 2 monitor INFORM-only)
-- Check 11 sub-agent đã spawn chưa:
+### 2.1 Sub-agent state (12-agent topology — 10 product/quality + 2 monitor INFORM-only)
+- Check 12 sub-agent đã spawn chưa:
   - 🟦 **investigator-codebase** — internal SQL/EF/grep/reference mirror audit
   - 🟦 **investigator-api** — external docs/CVE/lib/cross-project reference
   - 🟨 **implementer-backend** — .NET Domain+App+Infra+Api scaffold
   - 🟧 **implementer-frontend** — FE 2 app cookie-cutter SHA256 mirror
   - 🩷 **frontend-designer** — FE design/redesign visual-verification loop (FD1–FD10)
   - 🔵 **database-agent** — read-advisory DB lens (DB1–DB11: schema/migration-review/perf/concurrency)
+  - 📄 **office-document** — Office document WRITE (docx·xlsx·pptx·pdf + form-engine — template/spec-extract/report/screenshot→docx, OD1–OD10)
   - 🟪 **test-specialist** — tests/ xUnit dedicated
   - 🟥 **reviewer** — adversarial pre-commit + live curl prod
   - 🟩 **cicd-monitor** — post-deploy Gitea + bundle hash + smoke
@@ -181,7 +182,7 @@ Plan cha: [tên]
 ```
 
 ### SOLUTION_ERP report
-- Trạng thái spawn 11 sub-agent (idle/working) + agentId reuse-able trong session
+- Trạng thái spawn 12 sub-agent (idle/working) + agentId reuse-able trong session
 - Plan progress: ✅ Phase 10 COMPLETE 11/11 · ⬜ Phase 11 polish (wire ApproveV2 skeleton) · 🚫 Phase 9 Ops (anh main coordinate)
 - Critical signal: state counts (mig/table/endpoint/page/menu/test/gotcha) + bundle hash prod + RAG health
 - (SE KHÔNG copy phần "6 sister report" của AI_INFRA — đó là vai trò host)