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 commands/buaajoseph/claude-code-best-practice-zh/plangit 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/commands/buaajoseph/claude-code-best-practice-zh/plan)<a href="https://agentmods.dev/commands/buaajoseph/claude-code-best-practice-zh/plan"><img src="https://agentmods.dev/badge/commands/buaajoseph/claude-code-best-practice-zh/plan.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 | $0.00008 | $0.03207 |
| Opus 5 | $0.00004 | $0.01604 |
| Sonnet 5 | $0.00002 | $0.00641 |
| Haiku 4.5 | $0.00001 | $0.00321 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 416 lines — stays where its author put it; the contents beside it link to each section on GitHub.
用户输入
$ARGUMENTS
你必须解析用户输入以提取功能 slug(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 文件夹中生成详细规范、技术设计和实施计划。
前置条件:
- 功能文件夹存在于
rpi/{feature-slug}/ - 研究完成并获得 GO 建议(
rpi/{feature-slug}/research/RESEARCH.md存在)
输出位置:所有文件保存到 rpi/{feature-slug}/plan/
这是 RPI 工作流的步骤 3(研究批准 GO 之后)。
大纲
- 加载上下文:读取研究报告和项目宪法(如果存在)
- 理解需求:解析功能范围和需求
- 分析技术需求:审查架构和依赖项
- 设计架构:创建高级架构和 API 契约
- 分解实施:创建分阶段的任务分解
- 生成文档:创建结构化文档文件
- 验证输出:确保所有质量关卡通过
- 报告完成:提供摘要和下一步
阶段
阶段 0:加载上下文
前置条件:提供了功能 slug
流程:
-
验证研究完成:
- 检查
rpi/{feature-slug}/research/RESEARCH.md存在 - 验证 GO 建议(如果是 NO-GO 或 CONDITIONAL 则警告)
- 检查
-
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
-
加载项目宪法(如果存在):
- 在代码库中查找宪法或原则文档
- 提取相关约束和偏好
输出:
- 研究摘要
- 宪法上下文(如果找到)
- 规划约束
验证:
- 研究报告存在
- GO 建议已确认
- 宪法已加载(如果存在)
阶段 1:理解功能需求
前置条件:阶段 0 完成
流程:
-
从研究报告中解析功能描述:
- 提取功能名称和主要目标
- 识别目标组件
- 理解面向用户的 vs 技术功能
- 确定功能复杂性级别
-
识别受影响的组件:
- 主要组件(功能所在的位置)
- 辅助组件(集成点)
- 需要的共享工具
- 外部依赖项
-
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
- 识别可复用的代码和模式
输出:
- 功能范围文档(内部)
- 受影响组件列表
- 现有模式目录
验证:
- 功能名称和目标已明确定义
- 目标组件已识别
- 功能复杂性已评估
阶段 2:分析技术需求
前置条件:阶段 1 完成
流程:
-
审查组件架构:
- 阅读组件 README 和文档
- 审查现有代码结构
- 识别使用的架构模式
-
识别技术依赖项:
- 内部依赖项(其他组件、共享工具)
- 外部依赖项(API、服务、库)
- 数据库/存储需求
- 认证/授权需求
-
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
-
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)
- 依赖项映射
- 集成点图表
- 风险评估
验证:
- 组件架构已理解
- 所有依赖项已识别
- 集成点已映射
- 技术风险已评估
阶段 3:设计功能架构
前置条件:阶段 1-2 完成
Agent:senior-software-engineer
流程:
-
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
-
定义实施方法:
- 文件结构和组织
- 代码组织模式
- 测试策略
- 错误处理方法
-
规划数据库/存储更改(如适用):
- 新集合/表
- 模式修改
- 迁移策略
- 数据验证规则
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 · 416 lines · 8 tokens per session scan A 9d433b04e7d6
plan is a command published in the GitHub repository BuaaJoseph/claude-code-best-practice-zh (2 stars, last pushed 4mo ago), licensed MIT. It adds 8 tokens to every session and 3,207 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.