Borrowing it
Nothing to install: this file belongs to BuaaJoseph/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/BuaaJoseph/claude-code-best-practice-zh/master/.claude/commands/workflows/best-practice/workflow-claude-subagents.mdgit 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/workflow-claude-subagents)<a href="https://agentmods.dev/commands/buaajoseph/claude-code-best-practice-zh/workflow-claude-subagents"><img src="https://agentmods.dev/badge/commands/buaajoseph/claude-code-best-practice-zh/workflow-claude-subagents.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 5.1 | $0.00017 | $0.01746 |
| Opus 5 | $0.00009 | $0.00873 |
| Sonnet 5 | $0.00003 | $0.00349 |
| Haiku 4.5 | $0.00002 | $0.00175 |
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 8d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
工作流变更日志 — Subagents 报告
你是 claude-code-best-practice 项目的协调员。你的工作是启动一个研究 agent，等待其结果，并生成一份关于 Subagents 参考报告（best-practice/claude-subagents.md）漂移情况的报告。
此工作流检查 exactly 两种类型的漂移：
- Frontmatter 字段 — 官方文档中添加或删除的任何字段
- 官方子代理（Sub-agents） — 添加或删除的任何内置 agent
要检查的版本： $ARGUMENTS（如果为空或不是数字，默认 10）
这是一个 先读后报告 的工作流。启动 agent，合并发现，然后生成报告。只有在用户批准后才采取行动。
第一阶段：启动研究 Agent
使用以下 prompt 生成 workflow-claude-subagents-agent：
研究 claude-code-best-practice 项目的 subagents 报告漂移情况。检查最近 $ARGUMENTS 个版本（默认：10）。
获取以下 2 个外部来源：
- 子代理参考：https://code.claude.com/docs/en/sub-agents
- Changelog：https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md
然后读取本地报告（
best-practice/claude-subagents.md）。检查 exactly 两件事：
- Frontmatter 字段：将官方文档的支持的 frontmatter 字段表与报告的 Frontmatter Fields 表进行比较。标记添加或删除的任何字段。
- 官方子代理（Sub-agents）：将官方文档的内置子代理列表与报告的 official agents 表进行比较。标记添加或删除的任何 agents。
第二阶段：读取之前的变更日志条目
在 agent 运行期间，读取 changelog/best-practice/claude-subagents/changelog.md 以获取最近 25 条目。解析优先级操作以识别：
- 重复出现的问题 — 之前出现过且仍未解决的问题
- 新问题 — 首次出现的问题
- 已解决的问题 — 之前标记的问题现已修复
第三阶段：生成报告
等待 agent 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相比添加或删除的字段
- 官方子代理（Sub-agent）变更 — 与我们的表相比添加或删除的内置 agents
以优先级的 操作项目 摘要表结束。每个项目必须包含 Status 列，显示 NEW、RECURRING (first seen: <date>) 或 RESOLVED：
优先级操作：
# | 类型 | 操作 | 状态
1 | 新字段 | 将 <field> 添加到 frontmatter 表 | NEW
2 | 已删除字段 | 从表中删除 <field> | RECURRING (first seen: <date>)
3 | 新 Agent | 将 <agent> 添加到 official agents 表 | NEW
4 | 已删除 Agent | 从表中删除 <agent> | NEW
还包括 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事项。
第三阶段半：追加摘要到变更日志
此阶段是强制性的 — 在向用户展示报告之前必须始终执行。
读取现有的 changelog/best-practice/claude-subagents/changelog.md 文件，然后在末尾 追加（不是覆盖）新条目。条目格式必须 exactly 如下：
---
## [<YYYY-MM-DD HH:MM AM/PM PKT>] Claude Code v<VERSION>
| # | 优先级 | 类型 | 操作 | 状态 |
|---|----------|------|--------|--------|
| 1 | HIGH/MED/LOW | <类型> | <操作描述> | <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.
- 8d ago First seen · 136 lines · 17 tokens per session scan A 7ba279b5e137
workflow-claude-subagents is a command published in the GitHub repository BuaaJoseph/claude-code-best-practice-zh (2 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 1,746 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.