@ngocsangairvds/vsaf 3.0.0

package/.claude/skills/vsaf-ship/SKILL.md

@@ -0,0 +1,76 @@
+---
+name: vsaf-ship
+description: Review 3 lớp, ship code, và ghi lại toàn bộ knowledge vào bộ nhớ. Dùng sau /vsaf-test khi tất cả tests đã pass. Bước cuối cùng của mọi feature.
+---
+
+# VSAF Ship
+
+## Mục tiêu
+Đảm bảo code chất lượng, đóng gói feature, và ghi lại toàn bộ knowledge để các session sau kế thừa được.
+
+## Điều kiện tiên quyết
+- Đã chạy `/vsaf-test` và tất cả tests đã pass
+- Không có failing tests
+
+## Các bước thực hiện
+
+### Bước 1 — Review Layer 1: Methodology (Superpowers)
+- Dùng skill `superpowers:requesting-code-review`
+- Kiểm tra: code structure, naming, patterns, SOLID principles
+- Fix issues nếu có, commit lại
+
+### Bước 2 — Review Layer 2: Spec compliance (OpenSpec)
+- Dùng skill `opsx:verify` (hoặc `make verify`)
+- Kiểm tra: code có implement đúng tất cả FRs/NFRs trong spec không
+- Nếu fail: quay lại `/vsaf-build` để fix
+
+### Bước 3 — Review Layer 3: Security (ECC)
+- Chạy `npx ecc-agentshield scan`
+- Fix tất cả issues trước khi tiếp tục
+- Không skip warnings
+
+### Bước 4 — Re-index knowledge graph
+- Chạy `gitnexus analyze` để cập nhật call graph
+- Chạy `/graphify . --update` để cập nhật visual graph
+- Hoặc: `make index`
+
+### Bước 5 — Archive spec
+- Dùng skill `opsx:archive` để đóng spec proposal đã hoàn thành
+- Lưu vào `openspec/archived/`
+
+### Bước 6 — Ghi nhớ tự động (MemPalace)
+Thực hiện AUTO-WRITE từ `.claude/skills/vsaf-memory-protocol.md`.
+
+### Bước 9 — Push PR
+```bash
+git push origin feature/<name>
+```
+PR description phải bao gồm:
+- Link OpenSpec proposal
+- Impact summary (từ GitNexus)
+- Test results summary
+
+### Bước 10 — Output cho user
+```
+## Ship Complete: [feature]
+
+### Reviews
+- Layer 1 (Methodology): PASS
+- Layer 2 (Spec):         PASS
+- Layer 3 (Security):     PASS
+
+### Knowledge saved
+- Diary entry: ✓
+- Decisions: [X entries]
+- Reasoning chain: ✓
+
+### PR
+- Branch: feature/[name]
+- PR: [link]
+
+Workflow hoàn tất. Chạy /vsaf-plan <next-feature> cho task tiếp theo.
+```
+
+## Lưu ý
+- Không ship nếu bất kỳ layer review nào fail
+- `mempalace mine ~/chats/` — chạy weekly, không phải mỗi feature

package/.claude/skills/vsaf-test/SKILL.md

@@ -0,0 +1,70 @@
+---
+name: vsaf-test
+description: Viết tài liệu test từ spec, sau đó thực hiện test. Dùng sau /vsaf-build khi code đã implement xong. Test cases dựa trên spec, không phải dựa trên code.
+---
+
+# VSAF Test
+
+## Mục tiêu
+Tạo tài liệu test coverage đầy đủ từ spec, sau đó thực thi và verify kết quả.
+
+## Điều kiện tiên quyết
+- Đã chạy `/vsaf-build` và tất cả tasks đã commit
+- Có file spec trong `openspec/`
+
+## Các bước thực hiện
+
+### Bước 1 — Sinh test cases từ spec (BMAD qa)
+- Dùng skill `bmad-qa-generate-e2e-tests` với spec file làm input
+- Test cases phải cover: happy path, edge cases, error cases, NFRs
+- Nguồn gốc: từ FRs/NFRs trong spec — KHÔNG dựa trên implementation
+
+### Bước 2 — Đối chiếu coverage
+- So sánh test cases với task list trong spec
+- Mỗi task trong spec phải có ít nhất 1 test case tương ứng
+- Ghi nhận gaps nếu có
+
+### Bước 3 — Tạo task list test (Superpowers)
+- Dùng skill `superpowers:writing-plans` để tạo execution plan cho test
+- Mỗi test task có: input, expected output, pass/fail criteria
+
+### Bước 4 — Lưu tài liệu test
+- Lưu test plan vào `docs/test/[feature]-test-plan.md`
+- Format:
+
+```markdown
+## Test Plan: [feature]
+
+### Unit Tests
+| Test case | Input | Expected | Status |
+|-----------|-------|----------|--------|
+| ...       | ...   | ...      | [ ]    |
+
+### Integration Tests
+| ...       | ...   | ...      | [ ]    |
+
+### Edge Cases
+| ...       | ...   | ...      | [ ]    |
+```
+
+### Bước 5 — Thực thi test
+- Chạy toàn bộ test suite
+- Cập nhật status trong test plan
+- Nếu test fail: fix code, không sửa test để pass
+
+### Bước 6 — Output cho user
+```
+## Test Results: [feature]
+
+- Unit tests:        [X/Y passed]
+- Integration tests: [X/Y passed]
+- Edge cases:        [X/Y passed]
+
+Coverage: [X%]
+
+[PASS / FAIL — chi tiết nếu fail]
+```
+
+## Lưu ý
+- Nếu có test fail sau fix 2 lần: báo user, có thể cần quay lại `/vsaf-build`
+- Sau khi tất cả tests pass: chạy `/vsaf-ship`

package/README.md

@@ -0,0 +1,124 @@
+# VSAF — SDLC Agentic Framework
+
+A spec-driven development framework for Claude Code. Write specs first, let AI
+agents plan and execute, review in 3 layers, track every decision. 8 integrated
+tools, $20/month total.
+
+---
+
+## Architecture
+
+```
+┌──────────────────────────────────────────────────────────────────────┐
+│  PLANNING          BMAD (agents) ──▶ OpenSpec (specs, tasks, verify) │
+├──────────────────────────────────────────────────────────────────────┤
+│  CODE INTEL        GitNexus (MCP backbone) + Graphify (multimodal)   │
+├──────────────────────────────────────────────────────────────────────┤
+│  MEMORY            claude-mem (auto) + MemPalace (knowledge base)   │
+├──────────────────────────────────────────────────────────────────────┤
+│  IMPLEMENTATION    Claude Code + Superpowers + ECC cherry-pick       │
+└──────────────────────────────────────────────────────────────────────┘
+```
+
+See [1-setup-guide.md](docs/onboarding/1-setup-guide.md#2-how-the-tools-fit-together) for what each layer does and how the tools relate.
+
+## Quickstart
+
+Requires **Node.js ≥ 18**, **Python ≥ 3.10**, **Git**, **jq**, and a
+**Claude Code subscription** ($20/mo). Full prerequisites in
+[1-setup-guide.md](docs/onboarding/1-setup-guide.md#3-prerequisites).
+
+```bash
+git clone <this-repo> && cd vsaf
+make setup          # Install all 8 tools (idempotent — safe to re-run)
+make index          # Build knowledge graph
+make status         # Verify everything is working
+```
+
+One manual post-setup step (requires an interactive Claude Code session):
+
+```
+/plugin install superpowers@claude-plugins-official
+```
+
+Restart Claude Code after installing Superpowers.
+
+## Documentation
+
+All onboarding docs live in [`docs/onboarding/`](docs/onboarding/).
+
+| # | Doc | Covers |
+|---|-----|--------|
+| 1 | [1-setup-guide.md](docs/onboarding/1-setup-guide.md) | Install, tool overview, first walkthrough, glossary |
+| 2 | [2-workflow-guide.md](docs/onboarding/2-workflow-guide.md) | Deep dives, coordination playbooks, JWT demo, troubleshooting |
+| 3 | [3-cheatsheet.md](docs/onboarding/3-cheatsheet.md) | 1-page command reference — print and pin |
+| 4 | [4-milestones.md](docs/onboarding/4-milestones.md) | Day 1 / Week 1 / Month 1 ramp-up path |
+| 5 | [5-faq.md](docs/onboarding/5-faq.md) | Mindset questions every new dev asks |
+| — | [2-workflow-guide.vi.md](docs/onboarding/2-workflow-guide.vi.md) | Bản tiếng Việt của workflow guide |
+
+**New here?** Start with **1-setup-guide** → then **4-milestones** for your
+first 30 days.
+
+## Directory Layout
+
+```
+.
+├── .claude/
+│   ├── settings.json       # ECC hooks: block secrets, protect config files
+│   └── skills/              # Coding standards for Go, Rust, Python
+├── docs/
+│   ├── architecture/        # Architecture documents (from BMAD Architect)
+│   └── onboarding/          # Developer onboarding (see table above)
+├── githooks/                # Git hooks (pre-push runs verify + security scan)
+├── graphify-out/            # Graphify output (gitignored, regenerated by make index)
+├── openspec/                # OpenSpec workspace (proposals, specs, designs, tasks)
+├── scripts/
+│   └── setup-vsaf.sh       # Full setup automation (called by make setup)
+├── CLAUDE.md                # Claude Code system prompt — workflow rules
+└── Makefile                 # All day-to-day operations
+```
+
+## Daily Operations
+
+Run `make help` for the full list. Highlights:
+
+| Command | What It Does |
+|---|---|
+| `make setup` | Install or update all tools |
+| `make index` | Re-index codebase (GitNexus + Graphify) — run after every merge |
+| `make verify` | Check implementation against OpenSpec specs |
+| `make review` | Full 3-layer review coordinator |
+| `make status` | Show status of all installed tools |
+
+All commands — including BMAD agents, OpenSpec, Superpowers, and GitNexus — are
+listed in [3-cheatsheet.md](docs/onboarding/3-cheatsheet.md).
+
+## Workflow
+
+Every feature follows a **10-step cycle**: scope → plan → spec → impact
+analysis → brainstorm → TDD execute → 3-layer review → push → archive.
+Bug fixes ("Quick Flow") skip planning steps and go straight to brainstorm.
+
+See [1-setup-guide.md § Your First Project](docs/onboarding/1-setup-guide.md#5-your-first-project--a-walkthrough)
+for a walkthrough, or [2-workflow-guide.md § JWT Demo](docs/onboarding/2-workflow-guide.md#4-full-sdlc-demo)
+for a full command-by-command example.
+
+## Tools
+
+| Tool | What It Does | Cost |
+|---|---|---|
+| **Claude Code** | AI coding agent — everything else plugs into it | $20/mo |
+| **BMAD Method** | AI agents for planning: Analyst, PM, Architect, Product Owner | Free |
+| **OpenSpec** | Spec-driven development: proposals, specs, designs, task lists, verification | Free |
+| **Superpowers** | Methodology engine: brainstorm, plan, TDD execution, code review | Free |
+| **ECC (cherry-pick)** | Security scanner (AgentShield) + git hooks (block secrets) + coding standards | Free |
+| **GitNexus** | Code knowledge graph via MCP — impact analysis, dependency queries | Free |
+| **Graphify** | Multimodal knowledge graph — visual dependency maps, path tracing | Free |
+| **claude-mem** | Auto-pilot memory — captures sessions, re-injects context next time | Free |
+| **MemPalace** | Knowledge base — verbatim storage of decisions, temporal knowledge graph | Free |
+
+---
+
+**Core principles:** Spec before code. Context is king. Git is source of truth.
+3-layer review before every PR. Re-index after every merge. Mine decisions
+weekly.

package/assets/templates/.claude/settings.json

@@ -0,0 +1,82 @@
+{
+  "hooks": {
+    "PreToolUse": [
+      {
+        "matcher": "Edit|Write|Create|MultiEdit",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "FILE=\"$TOOL_INPUT_FILE\"; if [ -n \"$FILE\" ]; then if echo \"$FILE\" | grep -qE '\\.env$|\\.env\\.|\\.pem$|\\.key$|id_rsa|id_ed25519|\\.claude/settings\\.json'; then echo 'BLOCK: Protected file. Manual edit required for secrets/config files.'; exit 2; fi; fi"
+          }
+        ]
+      },
+      {
+        "matcher": "Edit|Write|Create|Bash",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "INPUT=\"$TOOL_INPUT\"; if [ -n \"$INPUT\" ]; then if echo \"$INPUT\" | grep -qE 'AKIA[0-9A-Z]{16}|ASIA[0-9A-Z]{16}|ghp_[a-zA-Z0-9]{36}|sk-[a-zA-Z0-9]{48}|xox[bpoas]-[a-zA-Z0-9-]+|eyJ[a-zA-Z0-9_-]*\\.[a-zA-Z0-9_-]*\\.[a-zA-Z0-9_-]*'; then echo 'BLOCK: Hardcoded secret/token detected. Use environment variables.'; exit 2; fi; fi"
+          }
+        ]
+      }
+    ],
+    "Stop": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "bash scripts/session-end-check.sh"
+          }
+        ]
+      }
+    ]
+  },
+  "permissions": {
+    "allow": [
+      "Read",
+      "Edit",
+      "MultiEdit",
+      "Bash(cat:*)",
+      "Bash(ls:*)",
+      "Bash(find:*)",
+      "Bash(grep:*)",
+      "Bash(rg:*)",
+      "Bash(head:*)",
+      "Bash(tail:*)",
+      "Bash(wc:*)",
+      "Bash(git status:*)",
+      "Bash(git diff:*)",
+      "Bash(git log:*)",
+      "Bash(git branch:*)",
+      "Bash(git show:*)",
+      "Bash(npm test:*)",
+      "Bash(npm run:*)",
+      "Bash(npx:*)",
+      "Bash(make:*)",
+      "Bash(python:*)",
+      "Bash(node:*)"
+    ],
+    "deny": [
+      "Bash(rm -rf:*)",
+      "Bash(rm -r /:*)",
+      "Bash(git push --force:*)",
+      "Bash(git push -f:*)",
+      "Bash(git reset --hard:*)",
+      "Bash(git clean -fd:*)",
+      "Bash(chmod 777:*)",
+      "Bash(curl * | bash:*)",
+      "Bash(wget * | bash:*)",
+      "Bash(eval:*)",
+      "Bash(DROP TABLE:*)",
+      "Bash(DROP DATABASE:*)",
+      "Bash(mkfs:*)",
+      "Bash(dd if=:*)",
+      "Bash(sudo:*)",
+      "Bash(ssh :*)",
+      "Bash(ssh -:*)",
+      "Bash(> /dev/:*)"
+    ]
+  },
+  "enabledPlugins": {}
+}

package/assets/templates/CLAUDE.md

@@ -0,0 +1,248 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+> VSAF v3 — Agentic AI SDLC Framework. Spec-driven development. 3-layer review. 7 integrated tools.
+
+---
+
+## Prerequisites
+
+Node.js ≥18, Python ≥3.10, Git, jq, Claude Code subscription. Run `npx vsaf init` (idempotent) to install all tools.
+
+---
+
+## Architecture
+
+VSAF is a meta-framework for AI-driven SDLC — not an application. It has no source code to compile. The 4-layer stack:
+
+| Layer | Tools | Purpose |
+|-------|-------|---------|
+| Planning | BMAD Method, OpenSpec | PRD, architecture docs, spec proposals |
+| Code Intelligence | GitNexus (MCP), Graphify | Impact analysis, dependency graphs, path tracing |
+| Memory | claude-mem, MemPalace | Session continuity (auto), architecture decisions (manual) |
+| Implementation | Superpowers, Claude Code | TDD execution, code review |
+
+Key directories: `.claude/` (settings + skills), `openspec/` (spec proposals), `scripts/` (helper scripts), `.gitnexus/` (knowledge graph index).
+
+---
+
+## Make Commands
+
+```bash
+npx vsaf init    # Install all tools (one-time, idempotent)
+make index       # Re-index: gitnexus analyze + graphify update
+make verify      # Check implementation against OpenSpec specs
+make review      # Full 3-layer review coordinator
+make archive     # Archive specs + re-index (post-merge)
+make mine        # Mine conversations into MemPalace
+make status      # Show status of all tools
+make clean       # Clean GitNexus index
+```
+
+---
+
+## Identity
+
+This project uses the **VSAF v3 (Agentic AI SDLC Framework)**. All development
+follows the 10-step workflow below. No code ships without spec compliance and
+3-layer review.
+
+---
+
+## Memory Management
+
+### claude-mem (auto-pilot)
+- claude-mem handles session continuity automatically. **Do not duplicate** its work.
+- Session context is auto-injected on start. No manual action needed.
+- Web viewer: http://localhost:37777
+
+### MemPalace (knowledge base)
+- Call `mempalace_search` **BEFORE** answering about past decisions, architecture
+  rationale, or "why did we choose X" questions.
+- Use `mempalace_add_drawer` for important decisions worth preserving verbatim.
+- Write `mempalace_diary_write` at end of meaningful sessions.
+- Run `mempalace mine ~/chats/ --mode convos` weekly to capture decision history.
+
+### Separation of Concerns
+| claude-mem | MemPalace |
+|---|---|
+| Session recall, debug history | Architecture decisions, team knowledge |
+| Auto-compressed summaries | Verbatim lossless storage |
+| "What file did I change yesterday?" | "Why did we choose Patroni over Stolon?" |
+| Lossy — may lose reasoning chain | Temporal KG with stale fact invalidation |
+
+**Anti-pattern:** Do not use MemPalace for session recall. Do not use claude-mem
+for architecture decisions. Do not dump knowledge into CLAUDE.md.
+
+---
+
+## Knowledge Graph
+
+### GitNexus (MCP backbone)
+- Use GitNexus MCP tools for impact analysis before any code change.
+- Query: "What breaks if I change X?" before touching cross-module code.
+- Re-index after every merge: `gitnexus analyze`
+
+### Graphify (multimodal KG)
+- Read `graphify-out/GRAPH_REPORT.md` **before** answering architecture questions.
+- Use `/graphify query "question"` for structural queries.
+- Use `/graphify path ServiceA ServiceB` to trace dependency paths.
+- Re-build after merge: `/graphify . --update`
+
+### Mandatory Re-indexing
+After every merge or significant change:
+```
+gitnexus analyze && /graphify . --update
+```
+Or: `make index`
+
+---
+
+## 10-Step Workflow
+
+### Step 0: Setup (one-time)
+```bash
+npx vsaf init
+```
+
+### Step 1: Understand Codebase
+- Read `graphify-out/GRAPH_REPORT.md` first.
+- Run `gitnexus serve` for web UI exploration.
+- Query MemPalace for past team decisions.
+- Do not modify code on day one.
+
+### Step 2: Scope
+```
+*agent analyst          # BMAD: clarify scope
+*workflow-init          # Quick/Standard/Enterprise
+bmad-help               # What's next?
+```
+Quick Flow (bug fix) --> skip to Step 6.
+
+### Step 3: Planning (skip for Quick Flow)
+```
+*agent pm               # PRD: FRs, NFRs, Epics
+*agent architect         # Architecture doc
+*agent po               # Sprint stories
+git add docs/ && git commit -m "feat: PRD + arch for <feature>"
+```
+
+### Step 4: Specs (skip for Quick Flow)
+```
+/opsx:propose <feature>
+/opsx:ff                # Fast-forward all docs
+git add openspec/ && git commit -m "spec: <feature>"
+```
+Tasks must be atomic (2-5 min). Include edge cases.
+
+### Step 5: Impact Analysis
+```
+"What breaks if I change PaymentService?"    # GitNexus MCP
+/graphify path PaymentService NotificationService
+mempalace search "PaymentService refactor"   # Past attempts
+```
+Impact > 3 modules --> split PRs. Update specs if new edge cases found.
+
+### Step 6: Brainstorm + Plan
+```
+/superpowers:brainstorm       # Socratic Q&A, explore alternatives
+/superpowers:write-plan       # Bite-sized tasks + verification steps
+```
+Do not approve until every task has a verification step.
+
+### Step 7: Execute
+```
+/superpowers:execute-plan     # RED -> GREEN -> REFACTOR per task
+```
+- 1 commit per task.
+- Tests after EVERY task.
+- Fail 3x on same task --> stop, do architectural review.
+
+### Step 8: Self-Review (3-layer -- MANDATORY)
+```bash
+# Layer 1: Methodology compliance
+/superpowers:code-review
+
+# Layer 2: Spec compliance
+/opsx:verify               # or: make verify
+
+# Layer 3: Knowledge graph sync
+make index                  # gitnexus analyze + graphify update
+```
+If Layer 2 fails --> return to Step 7.
+
+### Step 9: Push PR
+```bash
+git push origin feature/<name>
+```
+PR description must include: OpenSpec proposal link, impact summary, test results.
+
+### Step 10: Archive + Ship
+```bash
+make archive                # openspec archive + re-index
+mempalace mine ~/chats/ --mode convos   # Mine decisions
+git tag v<version> && git push --tags
+```
+
+---
+
+## Tool Commands — Quick Reference
+
+| Action | Command |
+|---|---|
+| BMAD analyst | `*agent analyst` |
+| BMAD PRD | `*agent pm` |
+| BMAD architect | `*agent architect` |
+| BMAD next step | `bmad-help` |
+| OpenSpec propose | `/opsx:propose <feature>` |
+| OpenSpec fast-forward | `/opsx:ff` |
+| OpenSpec verify | `/opsx:verify` |
+| OpenSpec archive | `/opsx:archive` |
+| Superpowers brainstorm | `/superpowers:brainstorm` |
+| Superpowers plan | `/superpowers:write-plan` |
+| Superpowers execute | `/superpowers:execute-plan` |
+| Superpowers review | `/superpowers:code-review` |
+| GitNexus index | `gitnexus analyze` |
+| GitNexus web | `gitnexus serve` |
+| Graphify build | `/graphify .` |
+| Graphify query | `/graphify query "question"` |
+| Graphify update | `/graphify . --update` |
+| MemPalace search | `mempalace search "query"` |
+| MemPalace mine | `mempalace mine ~/chats/ --mode convos` |
+| MemPalace status | `mempalace status` |
+| claude-mem viewer | `http://localhost:37777` |
+
+---
+
+## Anti-Patterns
+
+| Do Not | Instead |
+|---|---|
+| Write code before specs | Spec first, code second: `/opsx:propose` |
+| Skip brainstorm | `/superpowers:brainstorm` before planning |
+| Push without review | 3-layer: Superpowers + OpenSpec verify + re-index |
+| Forget to re-index | `make index` after every merge |
+| Create PRs > 400 lines | Split into smaller PRs |
+| Trust AI output blindly | AI writes -> Superpowers reviews -> human approves |
+| Skip impact analysis | GitNexus + Graphify + MemPalace BEFORE coding |
+| Dump knowledge into CLAUDE.md | CLAUDE.md = rules. claude-mem = sessions. MemPalace = decisions |
+| Use MemPalace for session recall | claude-mem auto-handles session continuity |
+| Use claude-mem for architecture decisions | MemPalace verbatim + temporal KG for decisions |
+| Skip MemPalace mining | `mempalace mine` weekly for architecture decisions |
+
+---
+
+## Commit Discipline
+
+- 1 commit per task from the plan.
+- Each commit message: `<type>: <description>` (feat, fix, refactor, spec, docs, test).
+- Tests must pass after every commit.
+- If a task fails 3 times, stop and trigger an architectural review.
+
+---
+
+## Security
+
+- Never hardcode credentials. Use environment variables.
+- Review `.claude/settings.json` hook rules if a block triggers unexpectedly.

package/assets/templates/Makefile

@@ -0,0 +1,77 @@
+# VSAF v3 — Agentic AI SDLC Framework
+# Day-to-day operations via Make targets.
+# Run `make help` for available commands.
+
+.PHONY: help index verify review archive status mine clean
+
+SHELL := /bin/bash
+
+# ── Help ───────────────────────────────────────────────────────────────────────
+
+help: ## Show this help
+	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | \
+		awk 'BEGIN {FS = ":.*?## "}; {printf "  \033[36m%-14s\033[0m %s\n", $$1, $$2}'
+
+# ── Knowledge Graph ────────────────────────────────────────────────────────────
+
+index: ## Re-index codebase (GitNexus + Graphify)
+	@echo "==> Re-indexing codebase..."
+	gitnexus analyze
+	@if command -v graphify &>/dev/null; then \
+		graphify . --update 2>/dev/null || echo "[WARN] graphify update failed — run '/graphify . --update' in Claude Code"; \
+	fi
+	@echo "==> Index complete"
+
+# ── Review (3-layer) ──────────────────────────────────────────────────────────
+
+verify: ## Layer 2: Check implementation against OpenSpec specs
+	openspec validate --all
+
+review: ## Run 3-layer review (methodology + spec + re-index)
+	@echo "==> Layer 1: Methodology review"
+	@echo "    Run in Claude Code: /superpowers:code-review"
+	@echo ""
+	@echo "==> Layer 2: Spec compliance"
+	openspec validate --all
+	@echo ""
+	@echo "==> Layer 3: Re-index knowledge graph"
+	$(MAKE) index
+	@echo ""
+	@echo "==> 3-layer review complete"
+
+# ── Spec Lifecycle ─────────────────────────────────────────────────────────────
+
+archive: ## Archive specs + re-index (post-merge)
+	openspec archive
+	$(MAKE) index
+	@echo "==> Archived and re-indexed"
+
+# ── Memory ─────────────────────────────────────────────────────────────────────
+
+mine: ## Mine conversations into MemPalace knowledge base
+	@export PATH="$$HOME/.local/bin:$$PATH"; mempalace mine ~/chats/ --mode convos --extract general
+
+# ── Status ─────────────────────────────────────────────────────────────────────
+
+status: ## Show status of all tools
+	@export PATH="$$HOME/.local/bin:$$PATH"; \
+	echo "==> GitNexus"; \
+	gitnexus status 2>/dev/null || echo "    [not indexed]"; \
+	echo ""; \
+	echo "==> MemPalace"; \
+	mempalace status 2>/dev/null || echo "    [not initialized]"; \
+	echo ""; \
+	echo "==> OpenSpec"; \
+	openspec list 2>/dev/null || echo "    [no active changes]"; \
+	echo ""; \
+	echo "==> Graphify output"; \
+	ls graphify-out/ 2>/dev/null || echo "    [no output — run '/graphify .' in Claude Code]"; \
+	echo ""; \
+	echo "==> claude-mem"; \
+	curl -sf http://localhost:37777 >/dev/null 2>&1 && echo "    Web viewer: http://localhost:37777" || echo "    [web viewer not running]"
+
+# ── Maintenance ────────────────────────────────────────────────────────────────
+
+clean: ## Clean GitNexus index (requires confirmation)
+	@read -p "This will remove the GitNexus index. Continue? [y/N] " confirm && \
+		[ "$$confirm" = "y" ] && gitnexus clean || echo "Aborted."