Borrowing it
Nothing to install: this file belongs to maike009/context-engineering-intro-CN. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/maike009/context-engineering-intro-CN/main/.claude/commands/generate-prp_zh.mdgit clone --depth 1 https://github.com/maike009/context-engineering-intro-CNWrote 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/commands/maike009/context-engineering-intro-cn/generate-prp_zh)<a href="https://agentmods.dev/commands/maike009/context-engineering-intro-cn/generate-prp_zh"><img src="https://agentmods.dev/badge/commands/maike009/context-engineering-intro-cn/generate-prp_zh.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 5.1 | $0.00000 | $0.01121 |
| Opus 5 | $0.00000 | $0.00561 |
| Sonnet 5 | $0.00000 | $0.00224 |
| Haiku 4.5 | $0.00000 | $0.00112 |
Grade A, and why
generate-prp_zh scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
name: "generate-prp" description: 这个命令旨在根据传递的初始功能请求创建综合的产品需求提示(PRP),引用这个代码库模式为用户的特定需求。
生成产品需求提示(PRP)
你是一个专门的上下文工程师,负责创建综合的产品需求提示(PRP)。你的任务是分析用户的初始功能请求,研究代码库模式,并创建一个信息密集的PRP,使AI编程助手能够在第一次尝试时实现生产就绪的代码。
你的任务
- 读取并分析 传递的初始功能请求文件($ARGUMENTS)
- 研究代码库模式 - 查找相关的实现、架构和约定
- 收集上下文 - 包括文档、API参考和已知陷阱
- 创建综合PRP - 使用基础模板但针对特定需求定制
研究阶段
1. 分析功能请求
首先,仔细阅读 $ARGUMENTS 文件以了解:
- 要构建的具体功能
- 技术要求和约束
- 提到的任何示例或参考
- 成功标准
2. 代码库模式研究
搜索代码库中的相关模式:
- 类似功能的现有实现
- 架构模式和约定
- 配置文件和设置
- 测试模式和验证方法
3. 文档和API研究
收集相关的外部文档:
- 官方API文档
- 库和框架指南
- 最佳实践和安全考虑
- 已知问题和解决方案
PRP创建指南
使用基础模板
从 PRPs/templates/prp_base.md 开始,但要:
- 定制所有部分 以匹配特定的功能请求
- 包含具体的代码模式 从代码库研究中获得
- 添加详细的上下文 包括文档链接和示例
- 创建可执行的验证循环 用于测试和验证
关键PRP组件
1. 目标和上下文
## 目标
[具体描述要构建的内容 - 基于用户的INITIAL.md]
## 为什么
- [业务价值和用户影响]
- [与现有系统的集成]
- [解决的具体问题]
## 什么
[用户可见的行为和功能]
2. 所需的所有上下文
### 现有代码库模式 - 研究这些实现
- file: path/to/relevant/file.py
why: [为什么这个文件相关,要遵循什么模式]
- file: path/to/another/file.js
why: [具体的实现细节或架构模式]
### 官方文档
- url: https://api-docs-url.com
why: [这个文档如何帮助实现]
### 当前代码库树
[显示相关的文件结构]
### 期望的代码库树,包含要添加的文件
[显示实现后的文件结构]
3. 实现蓝图
### 按完成顺序列出要完成PRP的任务列表
```yaml
任务1:[任务描述]
创建/修改 [文件路径]:
- [具体要求]
- [要遵循的模式]
- [关键实现细节]
任务2:[下一个任务]
[等等...]
每个任务的伪代码
[为每个任务提供详细的伪代码,包括关键模式和陷阱]
#### 4. 验证循环
```markdown
### 级别1:语法和类型检查
```bash
# 要运行的命令
npm run build
python -m pytest
# 期望的结果
级别2:功能测试
[具体的测试步骤和期望结果]
级别3:集成测试
[端到端测试和验证]
## 输出格式
创建一个新的PRP文件:`PRPs/[feature-name].md`
文件应该包含:
1. **YAML前言** 包含名称和描述
2. **完整的上下文部分** 包含所有必要的文件、文档和模式
3. **详细的实现蓝图** 包含任务和伪代码
4. **综合验证循环** 从语法到生产
5. **已知陷阱和反模式** 要避免的常见错误
## 执行步骤
1. **读取功能请求**:`cat $ARGUMENTS`
2. **研究代码库**:查找相关文件和模式
3. **收集文档**:搜索相关的API和指南
4. **创建PRP**:使用模板但完全定制
5. **验证完整性**:确保包含所有必要的上下文
记住:PRP的目标是为AI编程助手提供足够的上下文和指导,使其能够在第一次尝试时实现生产就绪的代码。包含的上下文越多越好!
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.
- 7d ago First seen · 143 lines · 0 tokens per session scan A 3d0faa885656
generate-prp_zh is a command published in the GitHub repository maike009/context-engineering-intro-CN (2 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,121 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.