Borrowing it
Nothing to install: this file belongs to Rito-w/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/Rito-w/claude-code-best-practice-zh/main/.claude/commands/workflows/agent-collections.mdgit clone --depth 1 https://github.com/Rito-w/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/rito-w/claude-code-best-practice-zh/agent-collections)<a href="https://agentmods.dev/commands/rito-w/claude-code-best-practice-zh/agent-collections"><img src="https://agentmods.dev/badge/commands/rito-w/claude-code-best-practice-zh/agent-collections.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 | $0.02008 |
| Opus 5 | $0.00009 | $0.01004 |
| Sonnet 5 | $0.00003 | $0.00402 |
| Haiku 4.5 | $0.00002 | $0.00201 |
Grade A, and why
agent-collections 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 7d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
工作流 — 代理集合（Agent Collections）
通过并行研究列出的仓库来更新 README.md 中的 AGENT COLLECTIONS 表格。启动研究代理，合并结果，报告变更，经批准后更新表格。
仓库列表
| # | 仓库 | 所有者 |
|---|---|---|
| 1 | msitarzewski/agency-agents |
msitarzewski |
| 2 | VoltAgent/awesome-claude-code-subagents |
VoltAgent（精选 awesome-list） |
当发现新的代理集合仓库时，将它们添加到这里 AND Phase 1 的研究提示中。
表格格式
README 表格包含以下列：
| Name | ★ | <img src="!/tags/a.svg" height="14"> |
- 名称（Name）：
[短名称](github-url)— 使用仓库的可识别短名称（如msitarzewski/agency-agents、awesome-claude-code-subagents）。仅在名称不明确时使用完整的owner/repo。 - ★（Stars）：星标数四舍五入到
k（如 92k、19k、1.2k）。低于 1000 显示精确数字。 - 代理数量：仅数字。对于 awesome-list 中代理是链接而非文件的情况，使用
N+ (curated list)格式。
排序顺序：按星标数降序排列（最高的在前）。
Phase 0：读取当前状态
读取以下文件：
README.md—## 🤖 AGENT COLLECTIONS表格（记录当前星标数和代理数量）changelog/agent-collections/changelog.md— 之前的变更日志条目（可能尚不存在 — 首次运行时创建）
Phase 1：启动研究代理
立即 spawn 一个 development-workflows-research-agent 覆盖所有仓库。（现有的研究代理是通用的 — 它可以统计任何仓库的 agents/skills/commands/stars。）
研究这些 Claude Code 代理集合（agent-collection） 仓库。每个仓库主要是子代理定义文件的库（定义代理的
.md文件），而非完整的工作流方法论。仓库 1：msitarzewski/agency-agents (https://github.com/msitarzewski/agency-agents) — agency 风格子代理集合 仓库 2：VoltAgent/awesome-claude-code-subagents (https://github.com/VoltAgent/awesome-claude-code-subagents) — 精选 awesome-list（链接到外部子代理，并非所有代理都以文件形式存储在仓库中）
对于每个仓库，返回：
- 星标数（Stars） — 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 — 通过 GitHub git tree API 统计子代理定义
.md文件：https://api.github.com/repos/{owner}/{repo}/git/trees/HEAD?recursive=1并 grep 传统代理目录下的路径。
- 对于
msitarzewski/agency-agents：代理通常位于agents/、.claude/agents/或分类子目录下。统计看起来像子代理定义的.md文件（frontmatter 包含name:和description:）。排除 README/CHANGELOG/LICENSE/docs。- 对于
VoltAgent/awesome-claude-code-subagents：统计 README.md 中列出的代理（如链接到外部仓库的项目符号/表格行）。明确标记为"curated list, not files in repo"。- 如果一个仓库既有精选索引又有自己的代理文件，报告两个数字并解释。
- 显著变更 — 过去 30 天内有任何重大添加或移除吗？
为每个仓库返回结构化报告：
REPO: msitarzewski/agency-agents STARS: <number>k (<exact>) AGENTS: <count> (<file pattern used, e.g., ".md files under agents/ via git tree">) NOTES: <anything unusual — flat layout vs categorized, README-only catalog, deprecated agents, curated-list disclaimer> CHANGES: <changes or "No significant changes"> CONFIDENCE: <0-1>
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.
- 7d ago First seen · 165 lines · 17 tokens per session scan A ffc1ab1ea280
agent-collections is a command published in the GitHub repository Rito-w/claude-code-best-practice-zh (10 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 2,008 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.