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/implementgit clone --depth 1 https://github.com/BuaaJoseph/claude-code-best-practice-zhWhat 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 | $0.00010 | $0.04278 |
| Opus 5 | $0.00005 | $0.02139 |
| Sonnet 5 | $0.00002 | $0.00856 |
| Haiku 4.5 | $0.00001 | $0.00428 |
Grade A, and why
implement 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 3d 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 — 634 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
此命令根据规划文档执行功能的分阶段实施。它编排专业 agent，强制执行验证关卡，并确保在整个实施过程中符合宪法。
前置条件：
- 功能文件夹存在于
rpi/{feature-slug}/ - 规划完成（
rpi/{feature-slug}/plan/PLAN.md存在）
输出位置：rpi/{feature-slug}/implement/
这是 RPI 工作流的步骤 4（最后一步 - 实际实施）。
标志
--phase N：执行特定阶段编号（1-8），如果省略则从阶段 1 开始--validate-only：仅验证当前阶段，不实施--skip-validation：跳过验证关卡并继续（谨慎使用）
可用 Agent
所有 Agent 使用 Opus 模型以获得最大质量。
实施 Agent
| Agent | 类型 | 何时使用 |
|---|---|---|
senior-software-engineer |
自定义 | 所有实施任务 |
支持 Agent
| Agent | 类型 | 目的 |
|---|---|---|
Explore |
内置 | 实施前的代码探索 |
code-reviewer |
自定义 | 代码评审和质量验证 |
constitutional-validator |
自定义 | 验证是否符合项目宪法 |
documentation-analyst-writer |
内置 | 文档生成 |
Agent 路由
所有实施任务由 senior-software-engineer agent 处理。
阶段 0：加载上下文和规则
前置条件：从用户输入解析功能 slug
流程：
0.1 加载项目宪法
- 在代码库中检查宪法或原则文档
- 如果存在，提取：
- 技术约束（类型安全、测试、组件隔离）
- 业务原则（质量标准、工作流）
- 架构边界
- 在实施期间存储约束以便强制执行
0.2 加载领域特定指南
根据要修改的文件，加载相关的项目指南：
- 检查特定组件的 README 文件
- 检查编码风格指南
- 检查测试需求文档
0.3 分析实施范围
- 读取
rpi/{feature-slug}/plan/PLAN.md - 识别所有要修改的文件
- 将文件映射到实施 agent
输出：
- 宪法上下文摘要
- 领域规则已加载
- 文件到 agent 的映射
- 阶段执行计划
验证：
- 宪法已加载（如果存在）
- 受影响文件的领域规则已加载
- 所有文件已映射到 agent
- 执行计划已理解
分阶段实施工作流
阶段实施循环
对于 PLAN.md 中的每个阶段：
┌─────────────────────────────────────────────────────────────────┐
│ 阶段 N: [阶段名称] │
├─────────────────────────────────────────────────────────────────┤
│ │
│ 1. 代码发现 (Explore Agent) │
│ └─→ 在更改之前了解现有代码 │
│ │
│ 2. 实施 (senior-software-engineer) │
│ └─→ 实施阶段交付物 │
│ │
│ 3. 自我验证 │
│ └─→ 工程师对照阶段检查清单进行验证 │
│ │
│ 4. 代码评审 (code-reviewer Agent) │
│ └─→ 安全性、正确性、可维护性 │
│ │
│ 5. 用户验证关卡 │
│ └─→ 停止并请求用户批准 │
│ ├─→ 通过：继续下一阶段 │
│ ├─→ 有条件通过：记录问题，继续 │
│ └─→ 失败：修复问题，重新验证 │
│ │
│ 6. 文档更新 │
│ └─→ 在 PLAN.md 中更新阶段状态 │
│ │
└─────────────────────────────────────────────────────────────────┘
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.
- 3d ago First seen · 634 lines · 10 tokens per session scan A 80811492816c
implement is a command published in the GitHub repository BuaaJoseph/claude-code-best-practice-zh (2 stars, last pushed 4mo ago), licensed MIT. It adds 10 tokens to every session and 4,278 once invoked, about $0.0001 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
git
Git operations with intelligent commit messages and workflow optimization.
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.