agent-fleet skillA
agent-fleet is agent-read markdown (skill) from yan-labs/yan-skills: 通用多模型子任务执行工具。用户想把一个任务派给别的模型(Gemini、DeepSeek、Kimi/Moonshot,或任何 Anthropic 兼容端点)去跑,尤其是想同时并行跑好几个不同模型的任务("同时起一个 Gemini 写文案的任务和一个 DeepSeek 做调研的任务""这个用 Kimi 跑""帮我用 DeepSeek 头脑风暴一下""开几个后台任务分别用不同模型跑")时使用。底层用 Claude Agent SDK 驱动一个 bypassPermissions 的自主 Agent(能读写文件、跑 bash、多轮工具调用直到任务完成),纯本地执行,不经过任何 Kollab 基础设施,模型接的是用户自己配置的第三方 API key。.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# agent-fleet 把一个任务派给别的模型去跑,而不是自己动手。核心命令: ```bash cd agent-fleet # 单个任务 node bin/agent-fleet.mjs run --model <友好名字> --prompt "<任务描述>" [--cwd <目录>] [--json] # 一次并发跑一批不同模型的任务 node bin/agent-fleet.mjs run-many --config batch.json [--json] # 看有哪些模型可用、密钥配没配 node bin/agent-fleet.mjs list-models ``` `<友好名字>` 来自 [`models.config.json`](./models.config.json),当前预置:`deepseek-v4-pro`、 `deepseek-v4-flash`、`kimi`、`gemini`(Gemini 没有官方 Anthropic 兼容端点,需要用户自己填一个网关 地址才能用,不填直接报错,不会假装能跑),以及 `kollab-gateway` 系列(走 Kollab 自己的公开 LLM 网关,用账号自助生成的 `kollab_live_*` key,不用等第三方审批,即用即验证过): `kollab-gateway`(默认 `gemini-3.8-flash`)、`kollab-gateway-copy`(文案/创意,同样是 `gemini-3.8-flash`)、`kollab-gateway-research`(调研摘要,`grok-4.6`)、`kollab-gateway-bulk` (批量机械任务,`gemini-3.5-flash-lite`)。 **用户想同时跑多个不同模型的任务时**,优先用 `run-many` 一次性提交(内部真正并发跑完),而不是 自己手写多次串行调用,或者对每个模型分别开一个后台 shell 进程——除非用户明确要求那种交互方式。 **按任务类型选模型**:批量文案/创意 → `kollab-gateway-copy`(或有 DeepSeek key 时用 `deepseek-v4-flash`);批量翻译/格式转换 → `kollab-gateway-bulk`(或 `deepseek-v4-flash`); 简单调研摘要 → `kollab-gateway-research`(或有 Moonshot key 时用自带联网搜索的 `kimi`); 高质量单次产出(长文案定稿、复杂推理)→ `deepseek-v4-pro`;**多轮工具调用容错要求高的任务不要 …
Read the whole file at its exact version.
How to install
mdr add yan-labs/yan-skills/agent-fleet@git:20260922.7a67fdemdr add yan-labs/yan-skills/agent-fleet@sha256:ae94ff9959e28406Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_iyp6doflncei6si2)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260922.7a67fde latest | 2026-09-22 | 7a67fde | 4,097 B | A | view · diff |
| git:20260921.5866ebb | 2026-09-21 | 5866ebb | 2,800 B | A | view · diff |
| git:20260921.9a8ca92 | 2026-09-21 | 9a8ca92 | 2,117 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4097 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
yan-labs/yan-skills · 203 stars · license MIT · pushed 2026-09-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_iyp6doflncei6si2 GET https://markdownregistry.com/api/v1/resolve?ref=yan-labs/yan-skills/agent-fleet GET https://markdownregistry.com/api/v1/blob/ae94ff9959e284066e09b0b3a416f8539bddd14e04a7ce9ad9e4c1ce4c53bf2e
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
More from yan-labs/yan-skills
Every file in yan-labs/yan-skills