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/rongxinzy/claude-code-best-practice-zh/development-workflowsgit 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/development-workflows)<a href="https://agentmods.dev/commands/rongxinzy/claude-code-best-practice-zh/development-workflows"><img src="https://agentmods.dev/badge/commands/rongxinzy/claude-code-best-practice-zh/development-workflows.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 | $0.00020 | $0.03150 |
| Opus 5 | $0.00010 | $0.01575 |
| Sonnet 5 | $0.00004 | $0.00630 |
| Haiku 4.5 | $0.00002 | $0.00315 |
Grade A, and why
development-workflows 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
工作流 —— 开发工作流
通过并行研究 10 个仓库来更新 README.md 中的 DEVELOPMENT WORKFLOWS 表格。启动代理,合并结果,呈现变更,如获批准则更新表格。
10 个仓库
| # | 仓库 | 所有者 |
|---|---|---|
| 1 | github/spec-kit |
GitHub (John Lam / Den Delimarsky) |
| 2 | Fission-AI/OpenSpec |
Fission-AI (@0xTab) |
| 3 | humanlayer/humanlayer |
HumanLayer (Dex Horthy) |
| 4 | affaan-m/everything-claude-code |
Affaan Mustafa |
| 5 | gsd-build/get-shit-done |
Lex Christopherson |
| 6 | obra/superpowers |
Jesse Vincent |
| 7 | garrytan/gstack |
Garry Tan (YC CEO) |
| 8 | bmad-code-org/BMAD-METHOD |
BMAD Code Org |
| 9 | EveryInc/compound-engineering-plugin |
Every.to |
| 10 | Yeachan-Heo/oh-my-claudecode |
Yeachan Heo (@bellman_ych) |
表格格式
README 表格有以下列:
| 名称 | ★ | 独特性 | 方案 | <img src="!/tags/a.svg" height="14"> | <img src="!/tags/c.svg" height="14"> | <img src="!/tags/s.svg" height="14"> |
- 名称:
[简称](github-url)— 使用项目名称,而非所有者/仓库 - ★: 星标数四舍五入到
k(例如,98k、10k、4.1k)。低于 1000 显示确切数字 - 独特性: 使用
的 2-3 个 shields.io 徽章标签。空格用下划线,连字符用--,+用%2B,/用%2F - 方案: 方案实现的图标 + 链接名称。图标
<img src="!/tags/c.svg" height="14">表示命令,<img src="!/tags/a.svg" height="14">表示代理,<img src="!/tags/s.svg" height="14">表示技能。名称链接到仓库中的实际文件 - 代理/命令/技能数量: 仅数字(例如,
25、0、108+)
排序顺序: 按星标数降序排列(最高优先)。不要按方案类型分组。
阶段 0: 读取当前状态
读取以下文件:
README.md——## ⚙️ DEVELOPMENT WORKFLOWS表格(注意当前星标数、标签、方案链接、数量)changelog/development-workflows/changelog.md—— 之前的变更日志条目
阶段 1: 启动 2 个研究代理
立即在单条消息中生成两个代理(并行)。每个使用 subagent_type: "development-workflows-research-agent"。
代理 1(3 个仓库)
研究以下 3 个 Claude Code 工作流仓库:
仓库 1: github/spec-kit (https://github.com/github/spec-kit) 仓库 2: affaan-m/everything-claude-code (https://github.com/affaan-m/everything-claude-code) 仓库 3: obra/superpowers (https://github.com/obra/superpowers)
对于每个仓库,返回:
- 星标数 — 使用 GitHub API
https://api.github.com/repos/{owner}/{repo},读取stargazers_count。四舍五入到k。- 代理数量 — 计算
agents/或.claude/agents/中的.md文件数。对于 obra,还需计算技能分派的隐式子代理。- 技能数量 — 计算
skills/或.claude/skills/中的文件夹数。- 命令数量 — 计算
commands/或.claude/commands/中的.md文件数。对于 spec-kit,计算templates/commands/中的文件。- 方案实现 — 查找方案/规划代理、技能或命令。返回其名称、类型(agent/skill/command)和文件路径。
- 独特性标签 — 2-3 个简短标签(每个 2-3 个词),捕捉该工作流的独特之处。
- 显著变更 — 最近有任何重大变更吗?新的代理/技能/命令、主要版本?
每个仓库返回结构化报告:
REPO: github/spec-kit STARS: <数字>k AGENTS: <数量> COMMANDS: <数量> SKILLS: <数量> PLAN: <名称> (<类型>) — <文件路径> TAGS: <标签1>, <标签2>, <标签3> CHANGES: <变更或"无显著变更">
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 · 210 lines · 20 tokens per session scan A 6786fddfa1f5
development-workflows is a command published in the GitHub repository rongxinzy/claude-code-best-practice-zh (6 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 3,150 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.