# Agent Instructions

<!-- playbook:framework:start -->

## 规则优先级

1. 系统/开发者指令与安全约束
2. 仓库规则：`.agents/` 与本文件
3. `AGENT_RULES.md` - 执行流程
4. `TODO.md` - 任务队列

---

## 快速导航

<!-- playbook:agents:start -->

请以 `.agents/` 下的规则为准：

- 入口：`.agents/index.md`
- 语言规则：`.agents/{{MAIN_LANGUAGE}}/index.md`
<!-- playbook:agents:end -->

<!-- playbook:templates:start -->

### 核心规则

- **执行流程**：[AGENT_RULES.md](./AGENT_RULES.md)
- **AI 行为规范**：[docs/prompts/system/agent-behavior.md](docs/prompts/system/agent-behavior.md)

### 项目上下文

- **项目定位**：[memory-bank/project-brief.md](memory-bank/project-brief.md)
- **技术栈**：[memory-bank/tech-stack.md](memory-bank/tech-stack.md)
- **架构设计**：[memory-bank/architecture.md](memory-bank/architecture.md)
- **进度追踪**：[memory-bank/progress.md](memory-bank/progress.md)
- **架构决策**：[memory-bank/decisions.md](memory-bank/decisions.md)
- **实施计划**：[memory-bank/implementation-plan.md](memory-bank/implementation-plan.md)

### 工作流程

- **需求澄清**：[docs/prompts/coding/clarify.md](docs/prompts/coding/clarify.md)
- **验证检查**：[docs/prompts/coding/verify.md](docs/prompts/coding/verify.md)
<!-- playbook:templates:end -->

---

## 新会话开始时

**AI 应该做的**：

1. 读取 [AGENT_RULES.md](./AGENT_RULES.md)
2. 读取 [memory-bank/](memory-bank/) 核心文档
3. 读取 [docs/prompts/system/agent-behavior.md](docs/prompts/system/agent-behavior.md)
4. 查看 [TODO.md](./TODO.md) 和 [CONFIRM.md](./CONFIRM.md)
<!-- playbook:framework:end -->

---

**最后更新**：{{DATE}}