A command that reads a product requirements prompt (PRP) and uses it as a detailed plan for building a software feature. It follows the prompt’s code context, implementation steps, security guidance, and checks.

Use it to implement a feature from a PRP file, including researching referenced code and documents, planning file changes, writing code, handling errors and input validation, and running the specified verification commands.

It gives a coding agent the background and sequence needed to implement a feature consistently. It also provides repeated checks for syntax, types, tests, integration, and deployment.

execute-prp — Command for Claude Code by maike009: A command that reads a product requirements prompt (PRP)…

Install

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.

agentmods

npx agentmods add commands/maike009/context-engineering-intro-cn/execute-prp_zh

Clone the repo

git clone --depth 1 https://github.com/maike009/context-engineering-intro-CN

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/maike009/context-engineering-intro-cn/execute-prp_zh.svg)](https://agentmods.dev/commands/maike009/context-engineering-intro-cn/execute-prp_zh)

Your own site

<a href="https://agentmods.dev/commands/maike009/context-engineering-intro-cn/execute-prp_zh"><img src="https://agentmods.dev/badge/commands/maike009/context-engineering-intro-cn/execute-prp_zh.svg" alt="Measured on agentmods" height="20"></a>

Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,447 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin 92% copy Near-identical to another mod in the catalogue.

Token cost

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	$0.00036	$0.01447
Opus 5	$0.00018	$0.00724
Sonnet 5	$0.00007	$0.00289
Haiku 4.5	$0.00004	$0.00145

Measured 5d ago against content hash cab13e370265, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

execute-prp 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 5d 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.

Origin

This is a copy

92% identical to execute-prp — 184 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.

.claude/commands/execute-prp_zh.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

执行产品需求提示（PRP）

你是一个专门的AI编程助手，负责执行产品需求提示（PRP）来实现生产就绪的功能。你的任务是读取PRP文件，加载所有上下文，并按照详细的实现蓝图逐步完成功能。

你的任务

读取并分析 传递的PRP文件（$ARGUMENTS）
加载所有上下文 - 研究引用的文件、文档和模式
创建实现计划 - 基于PRP中的任务列表
逐步实现 - 遵循模式和最佳实践
运行验证循环 - 确保每个级别都通过

执行阶段

1. PRP分析和上下文加载

首先，仔细阅读 $ARGUMENTS PRP文件以了解：

功能目标和要求
所有引用的代码库文件和模式
外部文档和API参考
实现任务和验证循环

2. 上下文研究

对于PRP中引用的每个文件：

读取并理解 现有的实现模式
识别关键架构 和设计决策
注意安全模式 和最佳实践
理解错误处理 和边缘情况

3. 实现计划

基于PRP的任务列表创建详细计划：

任务依赖关系 - 确定正确的执行顺序
文件修改 - 计划哪些文件需要创建/修改
测试策略 - 如何验证每个组件
回滚计划 - 如果出现问题如何恢复

实现指南

遵循PRP模式

严格遵循PRP中指定的模式：

使用相同的架构 如引用的文件
复制安全模式 用于认证和验证
遵循命名约定 和代码风格
实现相同的错误处理 模式

代码质量要求

每个实现必须包括：

详细的中文注释 解释功能和设计决策
适当的错误处理 包括用户友好的错误消息
输入验证 防止安全漏洞
日志记录 用于调试和监控

安全考虑

始终实现：

输入清理 防止注入攻击
权限检查 确保适当的访问控制
数据验证 使用架构和类型检查
安全默认值 最小权限原则

验证循环执行

级别1：语法和类型检查

# 运行PRP中指定的检查
[从PRP复制具体命令]

# 如果失败：
# 1. 阅读错误消息
# 2. 修复语法/类型问题
# 3. 重新运行直到通过

级别2：单元测试

# 运行功能测试
[从PRP复制测试命令]

# 如果失败：
# 1. 分析测试失败
# 2. 修复实现问题
# 3. 重新测试

级别3：集成测试

# 运行端到端测试
[从PRP复制集成测试]

# 验证：
# 1. 所有组件正确集成
# 2. 用户工作流程正常
# 3. 错误情况得到处理

级别4：生产验证

# 部署和生产检查
[从PRP复制部署命令]

# 确认：
# 1. 部署成功
# 2. 生产环境功能正常
# 3. 监控和日志工作

实现策略

渐进式实现

从最简单的组件开始 - 构建基础功能
逐步添加复杂性 - 一次添加一个功能
在每个步骤验证 - 确保稳定性
处理边缘情况 - 添加错误处理和验证

错误处理模式

# 示例：遵循代码库中的错误处理模式
try:
    # 主要功能实现
    result = perform_operation(input_data)
    return create_success_response(result)
except ValidationError as e:
    # 输入验证错误 - 用户友好的消息
    logger.warning(f"输入验证失败: {e}")
    return create_error_response("输入数据无效，请检查格式")
except PermissionError as e:
    # 权限错误 - 安全日志记录
    logger.error(f"权限被拒绝: {e}")
    return create_error_response("您没有执行此操作的权限")
except Exception as e:
    # 意外错误 - 详细日志记录
    logger.error(f"意外错误: {e}", exc_info=True)
    return create_error_response("操作失败，请稍后重试")

测试驱动方法

理解期望行为 - 从PRP和测试中
实现最小可行版本 - 通过基本测试
迭代改进 - 添加功能和处理边缘情况
重构和优化 - 保持代码质量

Read the full file on GitHub · 164 lines

Changes

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.

5d ago First seen · 164 lines · 36 tokens per session scan A cab13e370265

Subscribe to this mod's changes

execute-prp is a command published in the GitHub repository maike009/context-engineering-intro-CN (2 stars, last pushed 1y ago), licensed MIT. It adds 36 tokens to every session and 1,447 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to execute-prp, differing in 184 lines, and is treated as a copy.

Planning

execute-prp