@nockdev/awf 6.2.2 → 6.2.4

package/.agent/templates/index.yaml

@@ -2,7 +2,7 @@
 # Template Index — HSA Semantic Template Matching
 # =============================================================================
 # DOMYH Awesome Code Agent — Template Registry for HSA
-# version: 6.2.2
+# version: 6.2.3
 # =============================================================================
 
 templates:
@@ -236,4 +236,4 @@ search:
 # =============================================================================
 # Footer
 # =============================================================================
-# _DOMYH Awesome Code • Template Index v6.2.2 • HSA Integration_
+# _DOMYH Awesome Code • Template Index v6.2.4 • HSA Integration_

package/.agent/templates/migrate-plan.md

@@ -1,6 +1,6 @@
 ---
 name: migrate-plan
-version: "6.2.2"
+version: "6.2.4"
 type: plan
 triggers: ["/migrate"]
 ---

package/.agent/templates/phase-template.md

@@ -1,4 +1,4 @@
-# 📋 Phase Template — DOMYH v6.2.2
+# 📋 Phase Template — DOMYH v6.2.4
 
 > **Mục đích**: Template chuẩn cho phase files khi sử dụng `/plan full`
 > **Tạo bởi**: Agent tự động tạo theo complexity detection

package/.agent/templates/tasks/audit.yaml

@@ -8,7 +8,7 @@
 
 ```yaml
 task_type: audit
-version: "6.2.2"
+version: "6.2.4"
 
 # Required fields
 scope: string              # What to audit

package/.agent/templates/tasks/bug_fix.yaml

@@ -8,7 +8,7 @@
 
 ```yaml
 task_type: bug_fix
-version: "6.2.2"
+version: "6.2.4"
 
 # Required fields
 symptom: string              # What's the visible problem

package/.agent/templates/tasks/code_implementation.yaml

@@ -8,7 +8,7 @@
 
 ```yaml
 task_type: code_implementation
-version: "6.2.2"
+version: "6.2.4"
 
 # Required fields
 description: string       # What to build

package/.agent/templates/tasks/refactor.yaml

@@ -8,7 +8,7 @@
 
 ```yaml
 task_type: refactor
-version: "6.2.2"
+version: "6.2.4"
 
 # Required fields
 target: string            # What to refactor

package/.agent/templates/test-report.md

@@ -1,6 +1,6 @@
 ---
 name: test-report
-version: "6.2.2"
+version: "6.2.4"
 type: report
 triggers: ["/test"]
 ---

package/.agent/workflows/ap.md

@@ -13,11 +13,11 @@ skills: { required: [security, audit-pro], contextual: [auto] }
 
 ## AUDIT FLOW
 
-1. **DISCOVERY** (Auto 30s) — Detect stack (`hsa_detect_stack`), count files, load audit-pro checklists via HSA (`hsa_get_context`), check audit history, **diff-aware**: if recent commits, focus on `git diff --name-only HEAD~5..HEAD`, **auto-activate** conditional experts based on detected project type
+1. **DISCOVERY** (Auto 30s) — Detect stack (`hsa_detect_stack`), project snapshot (`hsa_get_snapshot`), count files, load audit-pro checklists via HSA (`hsa_get_context`), check audit history, **diff-aware**: if recent commits, focus on `git diff --name-only HEAD~5..HEAD`, **auto-activate** conditional experts based on detected project type
 2. **SCOPE CONTRACT** — Display scope options (from scoring.yaml) → ⛔ STOP wait for user selection (1-5). Show **previous audit score** if available for delta comparison. Show **active experts** based on detection
 3. **EXECUTE** — Run active Expert Panels sequentially, collect findings with evidence. Show **progress**: `[Panel 2/8] Architecture — Checkpoint 12/20`
 4. **SELF-REVIEW** — Agent re-reads findings, removes duplicates, verifies evidence accuracy, assigns confidence (1-10) per finding
-5. **REPORT** — Production Readiness Score (0-10), findings by P0/P1/P2/P3, **delta** vs previous audit (↑↓), save to `.domyh/audit_YYYY-MM-DD.md`
+5. **REPORT** — Production Readiness Score (0-10), findings by P0/P1/P2/P3, **delta** vs previous audit (↑↓), save to `.domyh/audits/audit_YYYY-MM-DD.md`
 6. **MEMORY PERSIST** — Update `memory/audit_summary.json`, log decisions, update `memory/state.json` scores
 
 ---
@@ -113,7 +113,7 @@ scoring: skills/cross-cutting/audit-pro/data/scoring.yaml # 6 weight profiles, g
 📊 DOMYH AUDIT — [project] — [date] — Score: X.X/10 (↑0.3 from last)
 | Expert | Score | Issues | Δ vs Last |
 👥 Active Experts: 8/12 (Security, Architecture, Performance, Quality, DevOps, UX, Data, Reliability)
-📁 Full: .domyh/audit_YYYY-MM-DD.md
+📁 Full: .domyh/audits/audit_YYYY-MM-DD.md
 ⏱️ Duration: Xm Ys | Files: N | Changed: M
 ```
 

package/.agent/workflows/code.md

@@ -1,6 +1,6 @@
 ---
 description: "💻 Write production-ready code, fix/improve existing projects, with proper error handling, types, and documentation"
-skills: { required: [], contextual: [auto, domyh-design, tailwind] }
+skills: { required: [coding-rules], contextual: [auto, domyh-design, tailwind] }
 ---
 
 # 💻 /code — Code Pro
@@ -12,7 +12,7 @@ skills: { required: [], contextual: [auto, domyh-design, tailwind] }
 
 ## CODE FLOW
 
-1. **DETECT** (Auto) — Parse intent (feature/bugfix/refactor), detect stack via HSA (`hsa_detect_stack`), load language skill via HSA (`hsa_get_context`)
+1. **DETECT** (Auto) — Parse intent (feature/bugfix/refactor), detect stack via HSA (`hsa_detect_stack`), load language skill via HSA (`hsa_get_context`, `hsa_search_skills`)
    - **UI INTENT CHECK** (→ See FLOW.md §18.1):
      Classify intent into T1 (Create) / T2 (Modify) / T3 (Design):
      T1 (new UI, no existing ref) → Follow FLOW.md §18.2 Create Pipeline (12 steps)

package/.agent/workflows/debug.md

@@ -1,6 +1,6 @@
 ---
 description: "🐛 Systematic debugging: reproduce → isolate → analyze → fix → verify"
-skills: { required: [], contextual: [auto] }
+skills: { required: [error-handling], contextual: [auto] }
 ---
 
 # 🐛 /debug — Debug Pro
@@ -12,7 +12,7 @@ skills: { required: [], contextual: [auto] }
 
 ## DEBUG FLOW
 
-1. **CAPTURE** (Auto) — Auto-detect language via HSA (`hsa_detect_stack`), load skill via HSA (`hsa_get_context`), parse stack trace, identify affected files. Show: `[Step 1/7] Capturing error context...`
+1. **CAPTURE** (Auto) — Auto-detect language via HSA (`hsa_detect_stack`), load skill via HSA (`hsa_get_context`, `hsa_search_skills`), parse stack trace, identify affected files, `hsa_prefetch` suspected files. Show: `[Step 1/7] Capturing error context...`
 2. **TIMELINE** — Reconstruct event timeline: `git log --oneline -10`, check recent changes to affected files, correlate with error timestamps. Answer: "When did this start?"
 3. **REPRODUCE** — Create minimal reproduction, confirm error occurs consistently → ⛔ STOP if cannot reproduce: ask user 5 questions
 4. **ISOLATE** — Binary search / git bisect, add trace logging, narrow to exact location
@@ -24,7 +24,7 @@ skills: { required: [], contextual: [auto] }
    ```
 6. **ANALYZE** — 5 Whys on CONFIRMED root cause (not assumptions)
 7. **FIX** — Create FAILING test first, implement single fix → if 3+ fixes fail → question architecture. Add **prevention guard** to block similar bugs
-8. **VERIFY** — Run reproduction steps, run full test suite, show before/after evidence. Persist pattern to failure repository if novel
+8. **VERIFY** — Run reproduction steps, run full test suite, show before/after evidence. Persist pattern to `.domyh/debug/failures.yaml` if novel
 
 ---
 

package/.agent/workflows/deploy.md

@@ -16,7 +16,7 @@ skills:
 
 ## DEPLOYMENT FLOW
 
-1. **PRE-FLIGHT** (Auto) — Detect stack via HSA (`hsa_detect_stack`), load deploy context (`hsa_get_context`). Run pre-flight checklist:
+1. **PRE-FLIGHT** (Auto) — Detect stack via HSA (`hsa_detect_stack`), verify environment (`hsa_detect_environment`), load deploy context (`hsa_get_context`). Run pre-flight checklist:
    - [ ] Tests pass (`npm test` / `go test ./...`)
    - [ ] Security scan (no P0 vulnerabilities)
    - [ ] Dependencies up to date (no critical outdated)
@@ -36,6 +36,7 @@ skills:
    → Auto-rollback if: error_rate > 0.5% OR p99 > 1000ms OR CPU > 90%
    ```
 6. **FINALIZE** — Tag release in git, update changelog, document rollback point, release deploy lock
+7. **SYNC** — `hsa_check_changes` to update index after deployment config changes
 
 ---
 
@@ -67,7 +68,7 @@ pre_flight:
 ```yaml
 # Prevent concurrent deployments
 deploy_lock:
-  file: ".deploy.lock"
+  file: ".domyh/deploy.lock"
   content: |
     deployer: [user/agent]
     started: [ISO timestamp]

package/.agent/workflows/dev.md

@@ -12,7 +12,7 @@ skills: { required: [], contextual: [auto] }
 
 ## DEV FLOW
 
-1. **DETECT** — Identify stack via HSA (`hsa_detect_stack`), find dev commands, check monorepo (nx.json, turbo.json, pnpm-workspace.yaml, package.json workspaces). Show: `[Step 1/6] Detecting stack...`
+1. **DETECT** — Identify stack via HSA (`hsa_detect_stack`), verify environment (`hsa_detect_environment`), find dev commands, check monorepo (nx.json, turbo.json, pnpm-workspace.yaml, package.json workspaces). Show: `[Step 1/6] Detecting stack...`
 2. **DEPS CHECK** — Verify dependencies installed:
    - Node.js: `node_modules/` exists? → If not: auto-run `npm install` (or yarn/pnpm/bun)
    - Go: `go.sum` exists? → If not: `go mod download`

package/.agent/workflows/doc.md

@@ -17,6 +17,7 @@ skills: { required: [], contextual: [auto] }
 3. **GENERATE** — Create doc content, use language-specific format, add examples & diagrams
 4. **VALIDATE** — Check links/references, verify code examples compile, lint docs
 5. **OUTPUT** — Generate files (MD/HTML/PDF), update existing docs, show summary
+6. **SYNC** — `hsa_check_changes` to update index after documentation file changes
 
 ---
 

package/.agent/workflows/e2e.md

@@ -12,11 +12,12 @@ skills: { required: [testing, tdd-workflow], contextual: [auto] }
 
 ## E2E FLOW
 
-1. **DETECT** — Identify frontend framework, existing E2E setup, test runner. Show: `[Step 1/5] Detecting E2E framework...`
-2. **MAP** — Identify critical user flows from routes/pages. Show: `[Step 2/5] Mapping 8 critical user flows...`
-3. **GENERATE** — Write E2E tests for critical paths. Show: `[Step 3/5] Generating tests for Login → Dashboard → Checkout`
-4. **RUN** — Execute E2E tests, capture screenshots on failure. Show: `[Step 4/5] Running 12 E2E tests...`
-5. **REPORT** — Show results with pass/fail, timing, screenshots. Show: `[Step 5/5] ✅ 11/12 passed (1 flaky)`
+1. **DETECT** — Detect stack via HSA (`hsa_detect_stack`), verify environment (`hsa_detect_environment`), identify frontend framework, existing E2E setup, test runner. Show: `[Step 1/6] Detecting E2E framework...`
+2. **MAP** — Identify critical user flows from routes/pages. Show: `[Step 2/6] Mapping 8 critical user flows...`
+3. **GENERATE** — Write E2E tests for critical paths. Show: `[Step 3/6] Generating tests for Login → Dashboard → Checkout`
+4. **RUN** — Execute E2E tests, capture screenshots on failure. Show: `[Step 4/6] Running 12 E2E tests...`
+5. **REPORT** — Show results with pass/fail, timing, screenshots. Show: `[Step 5/6] ✅ 11/12 passed (1 flaky)`
+6. **SYNC** — `hsa_check_changes` to update index after test file creation
 
 ---
 

package/.agent/workflows/env.md

@@ -16,6 +16,7 @@ skills: { required: [security], contextual: [auto] }
 2. **VALIDATE** — Validate format/types, detect missing/deprecated vars
 3. **SYNC** — Sync .env.example template, drift detection between envs
 4. **REPORT** — Security recommendations, next steps
+5. **INDEX** — `hsa_check_changes` to update index after environment file changes
 
 ---
 

package/.agent/workflows/fix.md

@@ -1,6 +1,6 @@
 ---
 description: "⚡ Quick-fix pipeline: capture error → identify → fix → verify (max 60s)"
-skills: { required: [], contextual: [auto] }
+skills: { required: [error-handling], contextual: [auto] }
 ---
 
 # ⚡ /fix — Fix Pro

package/.agent/workflows/init.md

@@ -12,7 +12,7 @@ skills: { required: [], contextual: [auto] }
 
 ## INITIALIZATION FLOW
 
-1. **DETECT** (Auto) — Parse user intent, detect existing project via HSA (`hsa_detect_stack`), infer stack from keywords
+1. **DETECT** (Auto) — Parse user intent, detect existing project via HSA (`hsa_detect_stack`), check installed tools (`hsa_detect_environment`), infer stack from keywords
 2. **CONFIGURE** — Select template, choose architecture → ⛔ STOP: confirm before scaffold
 3. **SCAFFOLD** — Run init commands, create folder structure, generate base files
 4. **CONFIGURE** — Setup linting/formatting, git hooks, create .env.example

package/.agent/workflows/monitor.md

@@ -1,6 +1,6 @@
 ---
 description: "📡 Setup observability: logging, tracing, metrics, and alerting configuration"
-skills: { required: [], contextual: [auto] }
+skills: { required: [observability, logging], contextual: [auto] }
 ---
 
 # 📡 /monitor — Monitor Pro
@@ -16,6 +16,7 @@ skills: { required: [], contextual: [auto] }
 2. **PLAN** — Recommend libraries & backends, setup OpenTelemetry → ⛔ STOP: confirm before install
 3. **EXECUTE** — Add logging, tracing (OpenTelemetry), metrics (Prometheus), configure alerts
 4. **VERIFY** — Verify data in backends, test alerts
+5. **SYNC** — `hsa_check_changes` to update index after observability config changes
 
 ---
 

package/.agent/workflows/onboard.md

@@ -12,12 +12,12 @@ skills: { required: [], contextual: [auto] }
 
 ## ONBOARD FLOW
 
-1. **DETECT** — Stack detection (`hsa_detect_stack`), count files/dirs, identify entry points & configs. Show: `[Step 1/6] Detecting stack...`
-2. **ANALYZE** — Parse architecture: folder structure, key modules, dependency graph, build system. Show: `[Step 2/6] Analyzing 342 files...`
+1. **DETECT** — Stack detection (`hsa_detect_stack`), project snapshot (`hsa_get_snapshot`), count files/dirs, identify entry points & configs. Show: `[Step 1/6] Detecting stack...`
+2. **ANALYZE** — Parse architecture: folder structure, key modules, dependency graph, build system. Use `hsa_get_repo_map` for file importance ranking. Show: `[Step 2/6] Analyzing 342 files...`
 3. **MAP** — Generate Mermaid architecture diagram + module dependency graph. Show: `[Step 3/6] Mapping architecture...`
 4. **ASSESS** — Identify code health: test coverage, lint score, outdated deps, known issues. Show: `[Step 4/6] Assessing code health...`
 5. **GUIDE** — Create "Getting Started" guide: setup steps, key files, conventions, common tasks. Show: `[Step 5/6] Generating guide...`
-6. **SYNC** — Save onboard report to `.domyh/onboard_YYYY-MM-DD.md`. Show: `[Step 6/6] Saving report...`
+6. **SYNC** — Save onboard report to `.domyh/onboard/onboard_YYYY-MM-DD.md`. `hsa_check_changes` to update index after generating onboarding docs. Show: `[Step 6/6] Saving report...`
 
 ---
 

package/.agent/workflows/orchestrate.md

@@ -13,8 +13,8 @@ skills: { required: [], contextual: [] }
 ## ORCHESTRATE FLOW
 
 1. **DECOMPOSE** — Break complex task into sub-tasks, identify dependencies, build DAG (Directed Acyclic Graph). Show: `[Step 1/5] Decomposing into 4 parallel tasks...`
-2. **ASSIGN** — Map sub-tasks to specialist personas, define interfaces between agents
-3. **PLAN** — Define execution order, checkpoints, rollback points → ⛔ STOP for user approval. Show task DAG visualization
+2. **ASSIGN** — Map sub-tasks to specialist personas, define interfaces between agents. Use `hsa_prepare_handoff` per sub-task for context injection
+3. **PLAN** — Define execution order, checkpoints, rollback points. Use `hsa_filter_tools` per sub-agent to reduce prompt bloat → ⛔ STOP for user approval. Show task DAG visualization
 4. **EXECUTE** — Run parallel tasks, monitor progress, handle failures. Show: `[Task 2/4] Backend API ████████░░ 80%`
 5. **SYNTHESIZE** — Merge results, resolve conflicts, verify integration. Run cross-task tests
 

package/.agent/workflows/perf.md

@@ -1,6 +1,6 @@
 ---
 description: "⚡ Performance profiling: CPU, memory, benchmarks, and optimization recommendations"
-skills: { required: [], contextual: [auto] }
+skills: { required: [web-perf], contextual: [auto] }
 ---
 
 # ⚡ /perf — Perf Pro
@@ -16,7 +16,8 @@ skills: { required: [], contextual: [auto] }
 2. **PROFILE** — CPU/memory profiling, flamegraphs
 3. **ANALYZE** — Identify hotspots, bottlenecks
 4. **OPTIMIZE** — Apply fixes, verify improvement
-5. **REPORT** — Before/after comparison
+5. **REPORT** — Before/after comparison. Save to `.domyh/perf/benchmark_YYYY-MM-DD.md`
+6. **SYNC** — `hsa_check_changes` to update index after performance optimization edits
 
 ---
 

package/.agent/workflows/plan.md

@@ -13,26 +13,49 @@ skills: { required: [], contextual: [auto] }
 ## PLAN FLOW
 
 1. **PHASE 0: DEEP INTERVIEW** — Thu thập context (skip if clear) → ⛔ STOP if info missing
-2. **PHASE 1: UNDERSTAND** — Parse request, detect stack via HSA (`hsa_detect_stack`), load context (`hsa_get_context`), clarify scope
-3. **PHASE 2: ANALYZE** — Impact assessment, risk analysis, dependencies
+2. **PHASE 1: UNDERSTAND** — Parse request, detect stack via HSA (`hsa_detect_stack`), load context (`hsa_get_context`), use `hsa_get_repo_map` for codebase overview, clarify scope
+3. **PHASE 2: ANALYZE** — Impact assessment, risk analysis, dependencies. `hsa_prefetch` target files for deep analysis
 4. **PHASE 3: DESIGN** — Technical design, architecture, API contracts
 5. **PHASE 4: BREAKDOWN** — Task decomposition, effort estimation → ⛔ STOP for user approval
 6. **PHASE 5: VALIDATE** — Review with user, finalize plan
+7. **PHASE 6: PERSIST** — Save to `.domyh/plans/YYYY-MM-DD_{feature-slug}/plan.md`. If scope ≥ L, also save `impact.md` and `tasks.md`. Update `memory/state.json` → `phase_progress.active_plan`. Show: `📁 Saved: .domyh/plans/2026-02-12_payment-gateway/`
 
 ---
 
 ## COMMANDS
 
-| Command                    | Description                |
-| -------------------------- | -------------------------- |
-| `/plan [feature]`          | Full planning flow         |
-| `/plan quick [feature]`    | Rapid plan (skip Phase 0)  |
-| `/plan estimate [feature]` | Effort estimation only     |
-| `/plan flow [sprint]`      | Flow metrics for sprint    |
-| `/plan forecast [n]`       | Forecast n items           |
-| `/plan specify [feature]`  | Spec-driven (DoR + INVEST) |
-| `/plan sprint`             | Sprint planning (DoD/DoR)  |
-| `/plan uat [feature]`      | UAT scenario planning      |
+| Command                    | Description                         |
+| -------------------------- | ----------------------------------- |
+| `/plan [feature]`          | Full planning flow                  |
+| `/plan quick [feature]`    | Rapid plan (skip Phase 0)           |
+| `/plan estimate [feature]` | Effort estimation only              |
+| `/plan flow [sprint]`      | Flow metrics for sprint             |
+| `/plan forecast [n]`       | Forecast n items                    |
+| `/plan specify [feature]`  | Spec-driven (DoR + INVEST)          |
+| `/plan sprint`             | Sprint planning (DoD/DoR)           |
+| `/plan uat [feature]`      | UAT scenario planning               |
+| `/plan list`               | List saved plans in `.domyh/plans/` |
+| `/plan open [slug]`        | Open a saved plan                   |
+| `/plan compare [a] [b]`    | Compare two plan versions           |
+
+---
+
+## PLAN OUTPUT
+
+```yaml
+output:
+  base: ".domyh/plans/"
+  structure: "YYYY-MM-DD_{feature-slug}/"
+  files:
+    plan.md: "Main plan (always created)"
+    impact.md: "Impact analysis (when scope ≥ L)"
+    tasks.md: "Task breakdown (when scope ≥ L)"
+  naming:
+    slug: "kebab-case from plan title, max 30 chars"
+    example: ".domyh/plans/2026-02-12_payment-gateway/"
+  active_ref: "Update memory/state.json → phase_progress.active_plan"
+  memory_sync: "Update memory/state.json with plan metadata"
+```
 
 ---
 

package/.agent/workflows/prompt.md

@@ -12,11 +12,12 @@ skills: { required: [prompt-engineering], contextual: [domyh-design] }
 
 ## PROMPT FLOW
 
-1. **ANALYZE** — Parse user request, detect prompt type (image/project/modify/system/general). Extract: mục đích, target tool/model, ngôn ngữ, constraints. Show: `[Step 1/5] Analyzing: "{request}" → Type: image`
+1. **ANALYZE** — Parse user request, detect prompt type (image/project/modify/system/general). If project-related: load context via HSA (`hsa_get_context`). Extract: mục đích, target tool/model, ngôn ngữ, constraints. Show: `[Step 1/5] Analyzing: "{request}" → Type: image`
 2. **RESEARCH** — Online research về domain, best practices, reference examples. Tìm kiếm: cấu trúc prompt tối ưu cho target tool, industry standards, trending patterns. Show: `[Step 2/5] Researching: "midjourney v6 architecture prompts"...`
 3. **STRUCTURE** — Apply RCTO Framework (Role-Context-Task-Output). Map research → sections phù hợp. Choose template theo prompt type. Show: `[Step 3/5] Structuring prompt with 6 sections...`
 4. **GENERATE** — Tạo structured markdown prompt. Viết bằng ngôn ngữ người dùng yêu cầu. Apply prompt-engineering patterns (CoT, few-shot, role-play). Show: `[Step 4/5] Generating prompt...`
 5. **REFINE** — Present output → ⛔ **STOP — user review**. Iterate nếu cần: thêm chi tiết, đổi style, adjust parameters.
+6. **SAVE** (Optional) — If user confirms, save to `.domyh/prompts/prompt_YYYY-MM-DD_{type}.md`
 
 ---
 

package/.agent/workflows/recap.md

@@ -12,7 +12,7 @@ skills: { required: [], contextual: [] }
 
 ## RECAP FLOW
 
-1. **COLLECT** — Git changes (`git log --oneline -20`), task list, decisions from memory, file system changes
+1. **COLLECT** — Git changes (`git log --oneline -20`), engine data (`hsa_export`), task list, decisions from memory, file system changes
 2. **ANALYZE** — Categorize changes (features, fixes, refactors, docs), calculate metrics (files changed, lines added/removed)
 3. **SUMMARIZE** — Group by category, generate structured report. Show: `Session: 2h 15m | 8 tasks | 23 files changed`
 4. **PERSIST** — Save key decisions and context to `memory/state.json` for next session continuity

package/.agent/workflows/refactor.md

@@ -1,6 +1,6 @@
 ---
 description: "🔧 Code refactoring & cleanup: identify smells, clean dead code, organize imports, restructure — verify tests pass"
-skills: { required: [], contextual: [auto] }
+skills: { required: [coding-rules], contextual: [auto] }
 ---
 
 # 🔧 /refactor — Refactor Pro

package/.agent/workflows/review.md

@@ -12,12 +12,13 @@ skills: { required: [security], contextual: [auto] }
 
 ## REVIEW FLOW
 
-1. **CONTEXT** — Detect stack via HSA (`hsa_detect_stack`), load review context (`hsa_get_context`), read changed files. Auto-detect review scope: staged changes, uncommitted, or PR
+1. **CONTEXT** — Detect stack via HSA (`hsa_detect_stack`), load review context (`hsa_get_context`), `hsa_prefetch` changed files. Auto-detect review scope: staged changes, uncommitted, or PR
 2. **DIFF ANALYSIS** — Parse `git diff --staged` or PR diff, classify change types, identify high-risk areas (auth, payments, data). Show: `[Analyzing] 12 files changed, 3 high-risk`
 3. **REVIEW** — Apply 5-category checklist on changed code, inline comments with severity
 4. **SELF-REVIEW** — Agent re-reads own findings, removes false positives, verifies evidence accuracy
 5. **REPORT** — Structured feedback with severity, approve/comment/request changes decision
-6. **SYNC** — `hsa_check_changes` to update index
+6. **PERSIST** — Save review findings to `.domyh/reviews/review_YYYY-MM-DD.md`
+7. **SYNC** — `hsa_check_changes` to update index
 
 ---
 

package/.agent/workflows/scaffold.md

@@ -1,6 +1,6 @@
 ---
 description: "🏗️ Unified scaffolding & code generation: components, pages, services, models, APIs from project patterns"
-skills: { required: [], contextual: [auto] }
+skills: { required: [coding-rules], contextual: [auto] }
 ---
 
 # 🏗️ /scaffold — Scaffold Pro

package/.agent/workflows/security.md

@@ -156,7 +156,7 @@ Scan Types: SAST ✅ | SCA ✅ | Secrets ✅ | Container ⏭️ | License ✅
 | Low      |     7 |            7 |
 
 ⏱️ Duration: 45s | Files: 128 | Dependencies: 47
-📁 Full: .domyh/security_YYYY-MM-DD.json
+📁 Full: .domyh/security/scan_YYYY-MM-DD.json
 ```
 
 ---
@@ -183,4 +183,4 @@ Scan Types: SAST ✅ | SCA ✅ | Secrets ✅ | Container ⏭️ | License ✅
 - Never expose actual secret values in reports (mask to `sk-****...****`)
 - Warn before scanning large directories (> 10,000 files)
 - Skip scanning `node_modules/`, `vendor/`, `.git/` by default
-- Output findings to `.domyh/` (gitignored) for sensitive content
+- Output findings to `.domyh/security/` (gitignored) for sensitive content

package/.agent/workflows/status.md

@@ -14,7 +14,7 @@ skills: { required: [], contextual: [auto] }
 
 1. **DETECT** — Identify project stack via HSA (`hsa_detect_stack`), config files. Show: `[Step 1/3] Detected: Go + TypeScript monorepo`
 2. **COLLECT** — Run build, tests, coverage, lint, dep check, `hsa_status` (engine health). Show: `[Step 2/3] Running 6 checks...`
-3. **REPORT** — Calculate health score, identify issues, compare with previous
+3. **REPORT** — Calculate health score, identify issues, compare with previous. Use `hsa_export` for structured data. Save snapshot to `.domyh/status/health_YYYY-MM-DD.md`
 
 ---
 

package/.agent/workflows/tdd.md

@@ -12,11 +12,12 @@ skills: { required: [tdd-workflow, testing], contextual: [auto] }
 
 ## TDD FLOW
 
-1. **SETUP** — Detect stack, load TDD skill, identify test framework. Show: `[Step 1/5] Detecting stack and test framework...`
-2. **RED** — Write a failing test that defines the expected behavior. Run tests to confirm it fails. Show: `[Step 2/5] 🔴 RED — Writing failing test: test_[feature]`
-3. **GREEN** — Write the SIMPLEST production code that makes the test pass. Show: `[Step 3/5] 🟢 GREEN — Implementing minimal code to pass`
-4. **REFACTOR** — Clean up code and tests without changing behavior. Re-run tests. Show: `[Step 4/5] 🔵 REFACTOR — Cleaning up (all tests still green)`
-5. **VERIFY** — Run full test suite, check coverage delta. Show: `[Step 5/5] ✅ Coverage: 75% → 83% (+8%)`
+1. **SETUP** — Detect stack via HSA (`hsa_detect_stack`), load TDD skill, load test context (`hsa_get_context`), identify test framework. Show: `[Step 1/6] Detecting stack and test framework...`
+2. **RED** — Write a failing test that defines the expected behavior. Run tests to confirm it fails. Show: `[Step 2/6] 🔴 RED — Writing failing test: test_[feature]`
+3. **GREEN** — Write the SIMPLEST production code that makes the test pass. Show: `[Step 3/6] 🟢 GREEN — Implementing minimal code to pass`
+4. **REFACTOR** — Clean up code and tests without changing behavior. Re-run tests. Show: `[Step 4/6] 🔵 REFACTOR — Cleaning up (all tests still green)`
+5. **VERIFY** — Run full test suite, check coverage delta. Show: `[Step 5/6] ✅ Coverage: 75% → 83% (+8%)`
+6. **SYNC** — `hsa_check_changes` to update index after test/code creation
 
 ---
 

package/.agent/workflows/verify.md

@@ -12,10 +12,11 @@ skills: { required: [testing], contextual: [auto] }
 
 ## VERIFY FLOW
 
-1. **DETECT** — Identify build system, linter, test runner. Show: `[Step 1/4] Detecting verification pipeline...`
-2. **RUN** — Execute verification pipeline sequentially. Show: `[Step 2/4] Running 4-stage pipeline...`
-3. **FIX** — Auto-fix what's possible (lint, format). Show: `[Step 3/4] Auto-fixing 3 lint issues...`
-4. **RE-RUN** — Loop until all pass or max iterations. Show: `[Step 4/4] Iteration 2/3 — All checks passed ✅`
+1. **DETECT** — Detect stack via HSA (`hsa_detect_stack`), identify build system, linter, test runner. Show: `[Step 1/5] Detecting verification pipeline...`
+2. **RUN** — Execute verification pipeline sequentially. Show: `[Step 2/5] Running 4-stage pipeline...`
+3. **FIX** — Auto-fix what's possible (lint, format). Show: `[Step 3/5] Auto-fixing 3 lint issues...`
+4. **RE-RUN** — Loop until all pass or max iterations. Show: `[Step 4/5] Iteration 2/3 — All checks passed ✅`
+5. **SYNC** — `hsa_check_changes` to update index after auto-fixes
 
 ---