fix: address code review findings — version sync, CLAUDE.md, install.py gaps

CLAUDE.md

@@ -0,0 +1,43 @@
+# CLAUDE.md
+
+## Entry Point
+
+This project uses **Skill workflow documents → manual Agent calls** pattern. Slash commands like `/smoke-test` are **not registered** as Claude Code commands — they are workflow documents in `skills/` that describe step-by-step processes. The main thread reads the Skill doc, then calls `Agent(subagent_type="xxx")` sequentially.
+
+There is **no auto-orchestration engine**. The main thread reads Skill docs and calls Agents sequentially. Agents may invoke utils but often implement equivalent logic themselves.
+
+## Directory Map
+
+| What | Where |
+|------|-------|
+| Agent definitions | `agents/` (16 agents) |
+| Skill workflow docs | `skills/` (35 skills) |
+| Python utils | `utils/` (78 modules) |
+| Config templates | `config/` (incl. `.env.example`) |
+| Test outputs | `workspace/` |
+| Runtime / MCP | `runtime/` |
+| CI pipelines | `ci/` |
+| Docs | `docs/` |
+| Marketplace | `marketplace/` |
+
+## How to Run
+
+1. Copy `config/.env.example` to `.env` and fill in required values
+2. Read the relevant Skill doc in `skills/` to understand the workflow
+3. Call agents manually via `Agent(subagent_type="xxx")` following the Skill flow
+4. Outputs land in `workspace/`
+
+## Architecture
+
+```
+Skill docs (skills/*.md)  →  define workflows
+Agent defs (agents/*.md)  →  define roles + tool access
+Utils (utils/*.py)        →  executable implementations
+```
+
+## Design Limitations
+
+- `/smoke-test` etc. are **not** registered slash commands. They are workflow documents.
+- Agent definitions contain Python import hints (e.g. `from utils.prd_loader import load_prd`) as prompts for AI agents, not actual executable code.
+- `test-lead` cannot recursively spawn sub-agents (Claude Code architecture limitation).
+- Pentest workflows require `tagent.yml` with `pentest.authorized: true` — see `tagent.yml.example`.

README.md

@@ -48,7 +48,7 @@ python install.py ~/test-agent-project       # macOS / Linux example, any folder
 
 After deployment, outputs under `workspace/`: test cases (Excel + xmind + markmap + opml) + Word report + decision logs.
 
-**Next**: edit `.env` → `claude /login` → `cd project-dir && claude` → `/smoke-test`
+**Next**: `cp config/.env.example .env` → edit `.env` → `cd project-dir && claude` → read `skills/smoke-test.md` workflow, run agents per the flow
 
 ## 🖥 Desktop App
 

ROADMAP.md

@@ -1,7 +1,7 @@
 # Test-Agent V1.x ROADMAP
 
 > 项目终态目标:每个 expert / skill 真 LLM-driven / script-backed 实装,**绝不输出 mock 数据**。
-> 当前状态:V1.42.0 (**expert rollout 收尾 + skill rollout 完成（16/16）+ Phase 3 完成 + Phase 4 完成 + Phase 5 完成**)
+> 当前状态:V1.43.0 (**expert rollout 收尾 + skill rollout 完成（16/16）+ Phase 3 完成 + Phase 4 完成 + Phase 5 完成**)
 > - **expert 16/16 active**(11 production + 5 script);0 rollout。
 > - **skill 30/32 active**(23 production + 7 script);0 rollout;2 暂为 V2 vision 方法论参考。
 > - 3 meta-skill(nuwa-skill / darwin-skill / karpathy-guidelines)独立,工具属性,不在 32 业务 skill 数内。

install.py

@@ -299,6 +299,7 @@ def create_dirs(project_root):
         os.path.join("workspace", "执行日志", "baselines"),
         os.path.join("workspace", "执行日志", "history"),
         os.path.join("workspace", "执行日志", "截图"),
+        "memory",
     ]
     for d in dirs:
         os.makedirs(os.path.join(project_root, d), exist_ok=True)
@@ -409,7 +410,7 @@ def copy_top_level_docs(template_dir, project_root):
     docs = [
         "LICENSE", "NOTICE.md", "SECURITY.md", "CONTRIBUTING.md",
         "CODE_OF_CONDUCT.md", "ROADMAP.md", "README.md", "README.zh-CN.md",
-        "CHANGELOG.md", "VERSION",
+        "CHANGELOG.md", "VERSION", "FULL_GUIDE.md", "tagent.yml.example",
     ]
     for f in docs:
         src = os.path.join(template_dir, f)
@@ -503,7 +504,8 @@ def finish(project_root):
  2. 安装 Java JRE 17 + JMeter 5.6.3 + Allure CLI（详见 部署说明.md）
  3. claude /login                           # 首次登录 Claude Code
  4. cd {project_root} && claude              # 启动
- 5. 在 Claude 提示符内: > /smoke-test       # 第一次冒烟验证
+ 5. cd {project_root} && claude              # 进入项目
+ 6. 阅读 skills/smoke-test.md 工作流        # 第一次冒烟验证
 
 {'=' * 50}
 """