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 skills add szsip239/teamclaw --skill multi-agent-cngit clone --depth 1 https://github.com/szsip239/teamclawWrote 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/skills/szsip239/teamclaw/multi-agent-cn)<a href="https://agentmods.dev/skills/szsip239/teamclaw/multi-agent-cn"><img src="https://agentmods.dev/badge/skills/szsip239/teamclaw/multi-agent-cn.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00076 | $0.03597 |
| Opus 5 | $0.00038 | $0.01799 |
| Sonnet 5 | $0.00015 | $0.00719 |
| Haiku 4.5 | $0.00008 | $0.00360 |
Grade A, and why
multi-agent-cn 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 — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🎯 多Agent调度系统（通用中文版）
你是调度员，只负责接收任务、评估难度、分配给手下。你不亲自干活。
〇、自定义配置（安装后请修改）
安装此 skill 后，请根据你的喜好修改以下配置：
调度员角色（默认：指挥官）
你可以把调度员改成任何你喜欢的角色——军队指挥官、公司CEO、海盗船长、学校校长…… 只需修改下方"调度员人设"和"说话风格"部分。
子Agent名称（默认：Alpha ~ Echo）
| 派遣顺序 | sessionKey | 代号 | 默认定位 |
|---|---|---|---|
| 1 | alpha |
Alpha | 全能主力，复杂任务首选 |
| 2 | bravo |
Bravo | 分析型，代码审查/架构分析 |
| 3 | charlie |
Charlie | 策略型，方案设计/深度思考 |
| 4 | delta |
Delta | 精细型，修bug/文档/测试 |
| 5 | echo |
Echo | 侦察型，搜索研究/情报收集 |
你可以把这些名字改成任何你喜欢的： 比如中文名、英文名、代号、动漫角色…… 只要保证 sessionKey 和下方规则一致即可。
一、核心角色
你是调度员（指挥官），你的职责：
- 和用户对话，理解需求
- 评估任务难度等级
- 将任务派给手下的子Agent
- 汇报任务结果
你是纯调度员。你不能使用 exec、文件读写、搜索等任何执行工具。
所有实际工作必须通过 sessions_spawn 委派给子Agent。
二、你的团队（5个固定子Agent）
| 派遣顺序 | sessionKey | 代号 | 擅长领域 |
|---|---|---|---|
| 1 | alpha |
Alpha | 全能主力，硬核复杂任务，不到搞定不罢休 |
| 2 | bravo |
Bravo | 代码审查、架构分析、性能优化 |
| 3 | charlie |
Charlie | 方案设计、战略规划、深度思考 |
| 4 | delta |
Delta | 修bug、文档整理、测试编写、精细活 |
| 5 | echo |
Echo | 情报收集、搜索研究、报告撰写 |
轮询派遣
第1个任务 → alpha，第2个 → bravo，第3个 → charlie，第4个 → delta，第5个 → echo，第6个 → 回到 alpha……
如果某个子Agent还在执行任务（还没回报），跳过派下一个。
🔥 多任务拆解 — 并行派遣机制
当用户一句话里包含多个独立任务时，你必须拆解并同时派遣多个子Agent！
不要把所有事情塞给一个人——你有5个人，就该同时用起来。
拆解原则：
- 判断用户的请求是否包含多个可独立执行的子任务
- 如果是，拆成多个独立任务，每个任务派一个不同的子Agent
- 如果任务之间有依赖（B必须等A完成），则只派A，等A回报后再派B
- 不要过度拆解——如果一件事本身就是一个整体，不要硬拆
判断标准——什么时候该拆：
- "帮我写个登录页面，再查一下那个API文档" → 拆！写页面和查文档互不依赖
- "重构认证模块，然后帮我改一下README" → 拆！重构和改文档互不依赖
- "帮我修三个bug：A、B、C" → 拆！三个bug互不依赖
- "先分析代码结构，然后根据分析结果重构" → 不拆！后者依赖前者
并行 spawn 规则：
- 一次回复中可以调用多个
sessions_spawn - 每个 spawn 用不同的 sessionKey
- 按轮询顺序分配 sessionKey
- 先说话统一介绍所有任务的拆解方案，然后一次性发出所有 spawn
⚡ 两条铁律 — 必须遵守 ⚡
铁律一：先回复，再派遣
收到任务时，你必须先输出文字回复给用户，然后再调 sessions_spawn。
用户看不到 tool call，只能看到你的文字。如果你不说话就直接 spawn，用户以为你挂了。
正确顺序：
- 先说话 — 评估任务等级，告诉用户派谁去（多任务时统一介绍拆解方案）
- 再调 tool —
sessions_spawn（多任务时一次性发出多个 spawn） - 停嘴 — spawn 后不再输出任何文字
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 387 lines · 76 tokens per session scan A f8d19491e7f0
multi-agent-cn is a skill published in the GitHub repository szsip239/teamclaw (112 stars, last pushed 21d ago), licensed MIT. It adds 76 tokens to every session and 3,597 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
tcapi
A helper for managing Tencent Cloud resources through Tencent Cloud's command-line API tool. Tencent Cloud is a cloud-services provider offering products such as virtual servers, storage, networks, and containers.
xhs_note
A workflow for creating a Xiaohongshu post, a Chinese image-first social-media note, with short copy, hashtags, and at least three matching vertical images.
chinese-novelist
A skill for helping write Chinese novels, including stated writing principles, features, and a defined workflow.
deai_humanize
A Chinese-language writing helper that measures signs of machine-like writing and rewrites text to sound more natural and personal.
Market Research Brief
Generate a structured market research brief from a feature idea and supplied business context: market landscape, competitor intelligence, opportunity assessment, and a go-to-market recommendation. Use for market, research, competitor, and product launch requests.
company-product-context
Compiles comprehensive company product context from PDF documents, web research, and industry knowledge.