Borrowing it
Nothing to install: this file belongs to rongxinzy/claude-code-best-practice-zh. 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/rongxinzy/claude-code-best-practice-zh/main/.claude/commands/workflows/best-practice/workflow-claude-subagents.mdgit clone --depth 1 https://github.com/rongxinzy/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/rongxinzy/claude-code-best-practice-zh/workflow-claude-subagents)<a href="https://agentmods.dev/commands/rongxinzy/claude-code-best-practice-zh/workflow-claude-subagents"><img src="https://agentmods.dev/badge/commands/rongxinzy/claude-code-best-practice-zh/workflow-claude-subagents/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/rongxinzy/claude-code-best-practice-zh/workflow-claude-subagents"><img src="https://agentmods.dev/badge/commands/rongxinzy/claude-code-best-practice-zh/workflow-claude-subagents.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00016 | $0.01734 |
| Opus 5 | $0.00008 | $0.00867 |
| Sonnet 5 | $0.00003 | $0.00347 |
| Haiku 4.5 | $0.00002 | $0.00173 |
Grade A, and why
workflow-claude-subagents 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 10d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
工作流变更日志 —— 子代理报告
你是 claude-code-best-practice 项目的协调员。你的工作是启动研究代理，等待其结果，并呈现关于子代理参考报告（best-practice/claude-subagents.md）差异的报告。
此工作流精确检查两种类型的差异：
- Frontmatter 字段 —— 官方文档中添加或删除的任何字段
- 官方子代理 —— 添加或删除的任何内置代理
检查版本数： $ARGUMENTS（默认：如果为空或非数字则为 10）
这是一个先读取后报告的工作流。启动代理，合并发现，生成报告。仅在用户批准时采取行动。
阶段 1: 启动研究代理
使用此提示生成 workflow-claude-subagents-agent：
研究 claude-code-best-practice 项目的子代理报告差异。检查最后 $ARGUMENTS 个版本（默认：10）。
获取这 2 个外部来源：
- 子代理参考：https://code.claude.com/docs/zh-CN/agents
- 变更日志：https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md
然后读取本地报告（
best-practice/claude-subagents.md）。精确检查两件事：
- Frontmatter 字段：将官方文档支持的 frontmatter 字段表格与报告的 Frontmatter 字段表格对比。标记任何添加或删除的字段。
- 官方子代理：将官方文档的内置子代理列表与报告的官方代理表格对比。标记任何添加或删除的代理。
阶段 2: 读取之前的变更日志条目
在代理运行时，读取 changelog/best-practice/claude-subagents/changelog.md 获取最近 25 个条目。解析优先行动项以识别：
- 重复项目 —— 之前出现过且仍未解决的问题
- 新增项目 —— 首次出现的问题
- 已解决项目 —— 之前标记的问题现已修复
阶段 3: 生成报告
**等待代理完成。**生成包含以下部分的报告：
- Frontmatter 字段变更 —— 官方文档与我们的报告中添加或删除的字段
- 官方子代理变更 —— 与我们的表格相比添加或删除的内置代理
以优先的行动项摘要表格结尾。每个项目必须包含显示 新增、重复（首次出现：<日期>） 或 已解决 的 状态 列：
优先行动项：
# | 类型 | 行动 | 状态
1 | 新字段 | 添加 <字段> 到 frontmatter 表格 | 新增
2 | 删除字段 | 从表格删除 <字段> | 重复（首次出现：<日期>）
3 | 新代理 | 添加 <代理> 到官方代理表格 | 新增
4 | 删除代理 | 从表格删除 <代理> | 新增
还要包含一个自上次运行以来已解决部分，列出之前运行中不再是问题的项目。
阶段 3.5: 追加摘要到变更日志
此阶段是强制的 —— 在向用户呈现报告之前始终执行。
读取现有的 changelog/best-practice/claude-subagents/changelog.md 文件，然后在末尾追加（不要覆盖）新条目。条目格式必须完全为：
---
## [<YYYY-MM-DD HH:MM AM/PM PKT>] Claude Code v<版本>
| # | 优先级 | 类型 | 行动 | 状态 |
|---|----------|------|--------|--------|
| 1 | 高/中/低 | <类型> | <行动描述> | <状态> |
| ... | ... | ... | ... | ... |
状态格式 —— 必须使用以下三种格式之一：
已完成 (原因)—— 已采取行动并成功解决无效 (原因)—— 发现不正确、不适用或有意的暂停 (原因)—— 行动推迟，等待外部依赖或用户决定
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.
- 10d ago First seen · 137 lines · 16 tokens per session scan A 0bdb899c98b1
workflow-claude-subagents is a command published in the GitHub repository rongxinzy/claude-code-best-practice-zh (6 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 1,734 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
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.