AI Engineering Harness：把 AI 代码放进可验证的工程闭环

Idea → PRD → Issue → Agent 认领 → Worktree → 实施计划
     → 实现 → 自测 → Draft PR → CI → 对抗式审查 → 修 → 再审
     → 证据闸门 → 人工审批 → 合并 → 阶段总结 → 记忆沉淀 → 下一轮

PR 合进去 → Done ✅

PR → CI 绿 → 2+ 审查员 Approved → 证据齐全 → Done ✅

Coordinator
├── Frontend Agent
├── Backend Agent
├── Database Agent
├── Bug Hunter
├── Behavior Reviewer
├── Architecture Reviewer
├── Security Reviewer
├── UI Reviewer
├── QA Agent
├── Evidence Aggregator
└── ... (共 18 类)

主仓库: main
  ├── worktree/feature-17-auth → Issue #17 (Backend Agent)
  ├── worktree/feature-18-ui   → Issue #18 (Frontend Agent)
  └── worktree/feature-19-db   → Issue #19 (Database Agent)

L0: AGENTS.md + ENGINEERING.md 摘要（始终加载）
L1: 当前 Issue + 模块架构 + ADR（任务级）
L2: 相邻模块 + 最近阶段总结（按需）
L3: PDF/图片/长报告（显式需要时才加载）

docs/evidence/17/
├── change-summary.md
├── verification.md
├── screenshots/
│   ├── desktop.png
│   ├── tablet.png
│   ├── mobile.png
│   ├── empty-state.png
│   ├── error-state.png
│   └── loading-state.png
├── playwright-trace.zip
└── review-frontend.md

docs/evidence/17/
├── api-trace.json
├── error-coverage.md
├── auth-negative-cases.md
└── performance-baseline.json

docs/
├── product/
│   ├── vision.md
│   └── roadmap.md
├── architecture/
│   └── system-design.md
├── design/
│   └── ui-guidelines.md
├── decisions/
│   └── ADR-001.md
memory/
├── project-memory.md
└── decisions.md
PROJECT_STATUS.md
AGENTS.md

Context / Goal / Scope / Non-Goal / Related Docs / Implementation Plan /
Acceptance Criteria / Evidence Requirements / Reviewer Requirements /
Owner / Estimate

# 为 Issue #17 创建独立 worktree
git worktree add ../myproject-worktree-17 -b feature/17-user-auth main

cd ../myproject-worktree-17

# Owner Agent 在这里工作
# Frontend Agent 实现 UI
# Backend Agent 实现 API
# Database Agent 实现 schema

# .github/workflows/test.yml
on: [push, pull_request]
jobs:
  test:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v3
      - run: npm install
      - run: npm test
      - run: npm run lint

# 自动检查
- [ ] docs/evidence/17/change-summary.md
- [ ] docs/evidence/17/verification.md
- [ ] docs/evidence/17/screenshots/ (6 张)
- [ ] docs/evidence/17/review-bug-hunter.md ✅
- [ ] docs/evidence/17/review-behavior.md ✅
- [ ] docs/evidence/17/fix-tasks.md ✅
- [ ] CI 绿

workflows/06-phase-summary.md
→ 沉淀到 memory/phase-17-summary.md

workflows/08-memory-evolution.md
→ 更新 memory/project-memory.md
→ 更新 memory/decisions.md

PR 合进去 → Done ✅
"我觉得可以" → 合并 ✅
"本地跑通了" → 合并 ✅

PR → CI 绿 + 2+ 审查员 Approved + 证据齐全 → Done ✅

# 一行安装
npx -y skills add lora-sys/ai-engineering-harness -g --all --full-depth

# 干跑：只打印草稿
bash skills/dashboard/scripts/scan-to-issues.sh

# 真的建 Issue
bash skills/dashboard/scripts/scan-to-issues.sh --create

✅ 硬编码密钥 (HIGH) → Issue #1
✅ 缺失错误处理 (MEDIUM) → Issue #2
✅ 重复逻辑 (MEDIUM) → Issue #3
✅ 风格漂移 (LOW) → Issue #4
✅ 缺少测试 (MEDIUM) → Issue #5
⚠️ TODO 无 Issue 链接 (LOW) → Issue #6

# 在你的仓库里说
Use $ai-engineering-harness to take over this repo. Inventory the gap
between current state and harness layout; file Issues for the missing
pieces; do not edit code yet.

📊 盘点完成
- ✅ 发现 23 个问题
- ✅ 创建 15 个 Issue
- ✅ 优先级排序

前 3 件事：
1. 硬编码密钥 → 移到环境变量
2. 缺少测试 → Quick Scan 检测到 5 个模块无测试
3. 没有 CI → 配置 GitHub Actions

# 推 Issue #1 到 Done
Use $ai-engineering-harness to take Issue #1 from Planning to Done.

1. 写 Plan → Issue #1 的 Implementation Plan
2. Worktree → git worktree add ../proj-issue-1
3. 分派 → Backend Agent 修密钥
4. 实现 → 移到环境变量
5. 自测 → 跑测试，通过
6. Draft PR → 自动创建 PR
7. CI → 通过 ✅
8. Bug Hunter → 冷启动审查，Approved
9. Behavior Reviewer → 冷启动审查，Approved
10. Evidence → 证据齐全 ✅
11. Merge → Coordinator 自动合并
12. Memory → 阶段总结 + 记忆沉淀

# 检查证据
ls docs/evidence/1/
# ✅ change-summary.md
# ✅ verification.md
# ✅ screenshots/ (6 张)
# ✅ review-bug-hunter.md
# ✅ review-behavior.md
# ✅ fix-tasks.md

# 检查 CI
gh pr view 1 --json state,statusCheckRollup
# ✅ state: MERGED
# ✅ statusCheckRollup: SUCCESS

npx -y skills add lora-sys/ai-engineering-harness -g --all --full-depth

# 只装这一个 skill
npx -y skills add lora-sys/ai-engineering-harness -g -s ai-engineering-harness

# 只装到指定 agent
npx -y skills add lora-sys/ai-engineering-harness -g -a claude-code codex grok

# Claude 工作到一半，切到 Grok
Use $ai-engineering-harness. I'm continuing from another agent.
Read memory/project-memory.md and sessions/<last-id>/summary.md, then continue.

# 分派 3 个 Issue 并行开发
Use $ai-engineering-harness to spawn parallel Owners
for Issue #20 (frontend), #21 (backend), #22 (database).

# CI 红了，让它自愈
CI is red on PR #23. Use $ai-engineering-harness to recover.

# 创建项目
mkdir my-saas && cd my-saas
git init
echo "# My SaaS" > README.md
git add . && git commit -m "feat: init"

# 进入任意 CLI
# Use $ai-engineering-harness to bootstrap this repo from PRD.md

npx -y skills add lora-sys/ai-engineering-harness -g --all --full-depth
bash skills/dashboard/scripts/scan-to-issues.sh --create
# 选择一个真实 Issue，跑完实现、CI、审查和证据检查