plan

plan is a command for Claude Code from rongxinzy/claude-code-best-practice-zh. It costs 8 tokens per session (3,216 once invoked), scanned A, original, MIT.

A planning command for turning an approved feature request and its research into detailed project documents.

In plain words
What is it for?
Use it after research has recommended building a feature to create its specifications, architecture notes, API agreements, and staged task list.
Why use it?
It organizes requirements, affected parts of the codebase, technical design, and implementation steps before coding begins.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; mentions Claude Code.

Good fit Use it after research has recommended building a feature to create its specifications, architecture notes, API agreements, and staged task list.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/rongxinzy/claude-code-best-practice-zh/plan
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.

Clone the repo
git clone --depth 1 https://github.com/rongxinzy/claude-code-best-practice-zh

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.

agentmods badge for plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/rongxinzy/claude-code-best-practice-zh/plan.svg)](https://agentmods.dev/commands/rongxinzy/claude-code-best-practice-zh/plan)
Your own site
<a href="https://agentmods.dev/commands/rongxinzy/claude-code-best-practice-zh/plan"><img src="https://agentmods.dev/badge/commands/rongxinzy/claude-code-best-practice-zh/plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,216 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00008 $0.03216
Opus 5 $0.00004 $0.01608
Sonnet 5 $0.00002 $0.00643
Haiku 4.5 $0.00001 $0.00322

Measured 7d ago against content hash 8c3788598cf2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

plan 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.

development-workflows/rpi/.claude/commands/rpi/plan.md · 417 lines

How it starts

The opening of the file, as written. The whole thing — 417 lines — stays where its author put it; the contents beside it link to each section on GitHub.

用户输入

$ARGUMENTS

必须解析用户输入以提取功能标识(rpi/ 中的文件夹名称)。

目的

此命令为功能请求创建全面的规划文档。它在功能的 RPI 文件夹中生成详细的规范、技术设计和实现计划。

前提条件

  • 功能文件夹存在于 rpi/{功能标识}/
  • 研究已完成并获得 GO 建议(rpi/{功能标识}/research/RESEARCH.md 存在)

输出位置:所有文件保存到 rpi/{功能标识}/plan/

这是 RPI 工作流的第 3 步(研究批准 GO 后)。

大纲

  1. 加载上下文:从 rpi/{功能标识}/ 读取研究报告和项目章程(如果存在)
  2. 理解需求:解析功能范围和需求
  3. 分析技术需求:审查架构和依赖
  4. 设计架构:创建高级架构和 API 契约
  5. 分解实现:创建分阶段任务分解
  6. 生成文档:创建结构化文档文件
  7. 验证输出:确保所有质量门通过
  8. 报告完成:提供摘要和后续步骤

阶段

阶段 0:加载上下文

前提条件:提供了功能标识

过程

  1. 验证研究已完成

    • 检查 rpi/{功能标识}/research/RESEARCH.md 存在
    • 验证 GO 建议(如果 NO-GO 或 CONDITIONAL 则警告)
  2. 读取研究发现

    • 提取产品分析
    • 提取技术发现
    • 提取技术可行性评估
    • 注意风险和约束
  3. 加载项目章程(如果存在):

    • 查找仓库中的章程或原则文档
    • 提取相关约束和偏好

输出

  • 研究摘要
  • 章程上下文(如果找到)
  • 规划约束

验证

  • 研究报告存在
  • 确认 GO 建议
  • 章程已加载(如果存在)

阶段 1:理解功能需求

前提条件:阶段 0 完成

过程

  1. 从研究报告解析功能描述

    • 提取功能名称和主要目标
    • 识别目标组件
    • 理解面向用户与技术功能
    • 确定功能复杂级别
  2. 识别受影响的组件

    • 主要组件(功能所在位置)
    • 次要组件(集成点)
    • 需要的共享工具
    • 外部依赖
  3. 研究现有模式

    • 在代码库中搜索类似功能
    • 审查组件架构和模式
    • 识别可重用的代码和模式

输出

  • 功能范围文档(内部)
  • 受影响的组件列表
  • 现有模式目录

验证

  • 功能名称和目标明确定义
  • 目标组件已识别
  • 功能复杂性已评估

阶段 2:分析技术需求

前提条件:阶段 1 完成

过程

  1. 审查组件架构

    • 读取组件 README 和文档
    • 审查现有代码结构
    • 识别使用的架构模式
  2. 识别技术依赖

    • 内部依赖(其他组件、共享工具)
    • 外部依赖(API、服务、库)
    • 数据库/存储需求
    • 认证/授权需求
  3. 评估集成点

    • 需要创建或修改的 API
    • 需要的数据库模式更改
    • 事件/消息流
    • 前端-后端集成
  4. 评估技术风险

    • 对现有功能的破坏性更改
    • 性能影响
    • 安全问题
    • 数据迁移需求

输出

  • 技术需求文档(内部)
  • 依赖映射
  • 集成点图
  • 风险评估

验证

  • 理解组件架构
  • 识别所有依赖
  • 映射集成点
  • 评估技术风险

阶段 3:设计功能架构

前提条件:阶段 1-2 完成

Agent:senior-software-engineer

过程

  1. 设计高级架构

    • 组件/模块结构
    • 数据流图
    • API 接口
    • 数据库模式更改
  2. 定义实现方法

    • 文件结构和组织
    • 代码组织模式
    • 测试策略
    • 错误处理方法
  3. 规划数据库/存储更改(如果适用):

    • 新集合/表
    • 模式修改
    • 迁移策略
    • 数据验证规则
  4. 设计 API 契约(如果适用):

    • 请求/响应格式
    • 认证需求
    • 错误响应

Read the full file on GitHub · 417 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.

  1. 7d ago First seen · 417 lines · 8 tokens per session scan A 8c3788598cf2

Subscribe to this mod's changes

plan is a command published in the GitHub repository rongxinzy/claude-code-best-practice-zh (6 stars, last pushed 4mo ago), licensed MIT. It adds 8 tokens to every session and 3,216 once invoked, about $0.0000 per session on Opus 5. 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.