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/workflow-conceptsgit 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-concepts)<a href="https://agentmods.dev/commands/buaajoseph/claude-code-best-practice-zh/workflow-concepts"><img src="https://agentmods.dev/badge/commands/buaajoseph/claude-code-best-practice-zh/workflow-concepts.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 | $0.00015 | $0.03277 |
| Opus 5 | $0.00008 | $0.01639 |
| Sonnet 5 | $0.00003 | $0.00655 |
| Haiku 4.5 | $0.00002 | $0.00328 |
Grade A, and why
workflow-concepts 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.
This is a copy
94% identical to workflow-concepts — 223 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
工作流变更日志 — README 概念
您是 claude-code-best-practice 项目的协调员。您的工作是并行启动两个研究 agent，等待它们的结果，合并发现，并呈现一份关于 README CONCEPTS 部分（README.md）漂移的统一报告。
要检查的版本： $ARGUMENTS（如果为空或不是数字，默认为 10）
这是一个先读取后报告的工作流。启动 agent，合并结果，产生报告。只有在用户批准后才采取行动。
阶段 0：并行启动两个 Agent
立即使用 Task 工具在同一条消息中并行启动两个 agent：
Agent 1：workflow-concepts-agent
使用 subagent_type: "workflow-concepts-agent" 生成。给它这个提示：
研究 claude-code-best-practice 项目的 README CONCEPTS 部分漂移。检查最近 $ARGUMENTS 个版本（默认：10）。
获取这 3 个外部来源：
- Claude Code 文档索引：https://code.claude.com/docs/en
- Claude Code 变更日志：https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md
- Claude Code 功能概览：https://code.claude.com/docs/en/overview
然后读取本地 README.md（特别是 CONCEPTS 表）、CLAUDE.md 和
reports/claude-global-vs-project-settings.md。分析官方文档列出的 Claude Code 概念/功能与我们 README CONCEPTS 表中记录的差异。返回涵盖缺失概念、变更概念、弃用概念、URL 准确性、描述准确性和徽章准确性的结构化发现报告。
Agent 2：claude-code-guide
使用 subagent_type: "claude-code-guide" 生成。给它这个提示：
研究最新的 Claude Code 功能和概念。我需要您找到应该记录的所有 Claude Code 概念/功能的完整列表。对于每个，提供：
- 官方功能名称
- 官方文档 URL
- 文件系统位置（例如
.claude/commands/、~/.claude/teams/）- 简要描述（一行）
- 引入时间（如果知道版本/日期）
具体检查这些可能缺失的概念：
- Worktrees — 用于并行开发的 git worktree 隔离
- Agent Teams — 多 agent 协调
- Tasks — 跨会话的持久任务列表
- Auto Memory — Claude 自己编写的项目学习
- Keybindings — 自定义键盘快捷键
- Remote Connections — SSH、Docker、云开发
- IDE Integration — VS Code、JetBrains 扩展
- Model Configuration — 模型选择和路由
- GitHub Integration — PR 审查、问题分类
- 来自近期 Claude Code 版本的任何其他概念
要彻底 — 搜索网络，获取文档，并为您找到的每件事提供具体的版本号和详细信息。
两个 agent 独立运行并返回它们的发现。
阶段 0.5：读取验证清单
在 agent 运行期间，如果存在，读取 changelog/best-practice/concepts/verification-checklist.md。此文件包含累积的验证规则。如果尚不存在则跳过此步骤 — 它将在阶段 2 中创建。
阶段 1：读取之前的变更日志条目
在合并发现之前，如果存在，读取文件 changelog/best-practice/concepts/changelog.md 以获取之前的变更日志条目。每个条目由 --- 分隔。解析这些先前条目中的优先级操作，以便您可以将它们与当前发现进行比较。这让您能够识别：
- 重复出现的问题 — 之前出现过但仍未解决的问题
- 新解决的问题 — 之前运行中出现但现在已修复的问题
- 新问题 — 首次在此运行中出现的问题
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 · 231 lines · 15 tokens per session scan A ca79c7e4f75b
workflow-concepts is a command published in the GitHub repository BuaaJoseph/claude-code-best-practice-zh (2 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 3,277 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to workflow-concepts, differing in 223 lines, and is treated as a copy.
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.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.