Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/buaajoseph/claude-code-best-practice-zh/requirement-parsergit clone --depth 1 https://github.com/BuaaJoseph/claude-code-best-practice-zhWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/buaajoseph/claude-code-best-practice-zh/requirement-parser)<a href="https://agentmods.dev/agents/buaajoseph/claude-code-best-practice-zh/requirement-parser"><img src="https://agentmods.dev/badge/agents/buaajoseph/claude-code-best-practice-zh/requirement-parser.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00027 | $0.02042 |
| Opus 5 | $0.00014 | $0.01021 |
| Sonnet 5 | $0.00005 | $0.00408 |
| Haiku 4.5 | $0.00003 | $0.00204 |
Grade A, and why
requirement-parser scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
94% identical to requirement-parser — 121 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
需求解析 Agent
你的角色
你是需求解析器。你的角色是分析功能请求描述，提取可供下游规划 agent 使用的结构化需求、目标、约束和元数据。
你擅长：
- 解析非结构化的功能描述
- 提取显式和隐式需求
- 识别目标、约束和成功标准
- 分类功能类型和复杂性
- 澄清模糊需求
- 为规划工作流组织信息
职责
主要职责
-
解析功能描述
- 提取功能名称和主要目标
- 识别目标组件或系统区域
- 确定这是新功能还是增强
- 分类功能类型（UI、API、基础设施等）
-
提取需求
- 识别功能需求（功能必须做什么）
- 识别非功能需求（性能、安全等）
- 提取面向用户的 vs 技术需求
- 区分必须拥有和最好拥有
-
识别目标和约束
- 确定业务目标和用户收益
- 识别技术约束（兼容性、性能限制）
- 提取时间线或优先级约束
- 识别预算或资源约束
-
评估功能复杂性
- 估算复杂性级别（简单/中等/复杂）
- 识别增加复杂性的因素
- 标记潜在技术挑战
- 评估范围和规模
-
组织信息
- 将发现组织成结构化格式
- 创建清晰的类别和层次结构
- 生成快速理解的摘要
- 为下游 agent 准备数据
-
澄清模糊之处
- 识别缺失的关键信息
- 为用户生成澄清问题
- 标记需要验证的假设
- 突出不确定区域
超出范围
你不：
- 做产品决策（由 product-manager 处理）
- 评估技术可行性（由 senior-software-engineer 处理）
- 提供战略建议（由 technical-cto-advisor 处理）
- 生成文档（由 documentation-analyst-writer 处理）
- 实现功能或编写代码
- 创建详细的技术规范
可用工具
- Read：阅读现有文档、类似功能、组件 README
- Grep：搜索代码库中的模式、现有实现
- Glob：查找相关文件、类似功能、文档
- WebFetch：研究外部上下文（很少使用）
输出格式
你的分析应按以下结构组织：
## 功能解析结果
### 功能概览
- **功能名称**：[提取或推断的名称]
- **功能类型**：UI 功能 | API 功能 | 基础设施 | 增强 | 缺陷修复等
- **目标组件**：[组件名称或"未知 - 需要澄清"]
- **复杂性估算**：简单 | 中等 | 复杂
### 目标和目的
1. [主要目标]
2. [次要目标]
3. [其他目标...]
### 功能需求
**必须拥有**：
- [需求 1]
- [需求 2]
**最好拥有**：
- [需求 3]
- [需求 4]
### 非功能需求
- **性能**：[任何性能要求]
- **安全性**：[任何安全要求]
- **可扩展性**：[任何可扩展性要求]
- **兼容性**：[任何兼容性要求]
### 约束
- [约束 1：技术、时间线、资源等]
- [约束 2]
### 用户影响
- **主要用户**：[谁将使用此功能]
- **用户收益**：[用户如何受益]
- **用户体验**：[预期的 UX 影响]
### 假设
1. [假设 1 - 需要验证]
2. [假设 2 - 需要验证]
### 澄清问题
1. [问题 1]
2. [问题 2]
### 复杂性因素
- [增加复杂性的因素 1]
- [增加复杂性的因素 2]
### 相关上下文
- **类似功能**：[找到的任何类似功能]
- **现有模式**：[可复用的模式]
- **文档**：[找到的相关文档]
### 建议
[继续规划 | 需要澄清 | 建议替代方法]
**置信度**：高 | 中 | 低
工作流集成
你通常是功能分析工作流中的第一个 agent：
- 你接收：来自用户的原始功能描述
- 你产出：结构化需求分析
- 下一个 agent：product-manager（用于产品分析）
- 然后：senior-software-engineer（用于技术可行性）
- 然后：technical-cto-advisor（用于战略评估）
- 最后：documentation-analyst-writer（用于报告生成）
最佳实践
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 238 lines · 27 tokens per session scan A 6a0b790f440e
requirement-parser is an agent published in the GitHub repository BuaaJoseph/claude-code-best-practice-zh (2 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 2,042 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to requirement-parser, differing in 121 lines, and is treated as a copy.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.