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 alisunstar/OpenSunstar --skill modelscope-api-skillgit clone --depth 1 https://github.com/alisunstar/OpenSunstarWrote 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/alisunstar/opensunstar/modelscope-api-skill)<a href="https://agentmods.dev/skills/alisunstar/opensunstar/modelscope-api-skill"><img src="https://agentmods.dev/badge/skills/alisunstar/opensunstar/modelscope-api-skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/alisunstar/opensunstar/modelscope-api-skill"><img src="https://agentmods.dev/badge/skills/alisunstar/opensunstar/modelscope-api-skill.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00088 | $0.05682 |
| Opus 5.5 | $0.00035 | $0.02273 |
| Sonnet 5.5 | $0.00018 | $0.01136 |
| Haiku 4.5 | $0.00009 | $0.00568 |
Grade C, and why
modelscope-api scanned grade C with 2 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 1mo 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
"curl -fsSL https://modelscope.cn/skills/install.sh | bash -s -- @Alipay/alipay-payment-integration", Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://www.modelscope.cn/openapi/v1/skills?page_number=1&page_size=10&search=股票" | python -m json.tool How it starts
The opening of the file, as written. The whole thing — 576 lines — stays where its author put it; the contents beside it link to each section on GitHub.
魔塔社区（ModelScope）API 完整手册
概述
本 Skill 封装魔塔社区全部可用 API，包括：模型库、数据集、技能中心（80K+ 技能）、MCP 广场（9.4K+ 服务器）。支持Token自动引导注册。
两种响应格式注意：
/api/v1/*（旧）：PascalCase →{"Code": 200, "Data": {...}}/openapi/v1/*（新）：snake_case →{"success": true, "data": {...}}
第一步：Token 设置（首次使用必读）
⚠️ 安全警告：此技能包含只读操作和变更操作。部署、删除、安装等变更操作需要你明确确认。请使用最小必要权限的 Token。
权限建议
| 操作类型 | 所需权限 | 说明 |
|---|---|---|
| 只读操作（搜索、查询） | 读取权限 | 无需 Token，公开可用 |
| 下载操作（模型、数据集） | 下载权限 | 需要 Token |
| 变更操作（创建、部署、删除） | 写入权限 | 必须明确用户确认 |
💡 建议：优先使用只读 Token，仅在需要下载/部署时才提供写入权限。
Token 获取与使用原则
🔒 核心原则：Token 只在当前会话中使用，不写入任何文件，不保存到记忆。
Token 优先级（从上到下）：
- 环境变量
MODELSCOPE_API_TOKEN（最安全，推荐） - 直接提供（没有环境变量时，AI 会直接询问你）
没有 Token 时：直接告诉 AI「我的魔塔 Token 是 xxx」，AI 会在本次会话中使用它，执行完即丢弃。
情况 A：已有 Token
方式一（推荐）：设置环境变量
export MODELSCOPE_API_TOKEN="ms-xxxxxx"
方式二：直接告诉 AI（AI 不会记录，仅当前会话使用）
没有 Token → 引导注册：
- 打开注册页面：https://www.modelscope.cn/my/overview
- 用手机号/支付宝/钉钉完成注册登录
- 登录后，点右上角头像 → 「访问令牌」(Access Token)
- 点「新建令牌」，填写名称（如
workbuddy） - ⚠️ 重要：权限选择「只读」或「下载」，除非你需要部署功能，否则不要选「全部」
- 复制生成的 Token（格式：
ms-xxxxxx），只显示一次，务必保存
⚠️ Token 即密码，不要提交到 GitHub。
获取 Token 后，直接告诉 AI 或设置环境变量，AI 在当前会话中使用后即丢弃，不记录。
能力一：技能中心（Skills）
总技能数：80,505+
1.1 搜索/列出技能
curl -s "https://www.modelscope.cn/openapi/v1/skills?page_number=1&page_size=10&search=股票" | python -m json.tool
Query 参数：
| 参数 | 类型 | 说明 |
|---|---|---|
page_number |
int | 页码，默认 1 |
page_size |
int | 每页数量，默认 10 |
search |
string | 搜索关键词（匹配 display_name） |
无需 Token 即可访问。
响应示例：
{
"success": true,
"data": {
"total": 80505,
"skills": [
{
"id": "@Alipay/alipay-payment-integration",
"display_name": "支付宝支付集成skill",
"description": "...",
"category": "developer-tools",
"view_count": 21881,
"downloads": 2069
}
]
}
}
What ships with it
6 files 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.
- 1mo ago First seen · 576 lines · 88 tokens per session scan C d479cfad4233
modelscope-api is a skill published in the GitHub repository alisunstar/OpenSunstar (31 stars, last pushed 14d ago), licensed Apache-2.0. It adds 88 tokens to every session and 5,682 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
reward-design
A guide to defining the scores that an AI agent receives during trial-and-error training. It covers checks based on rules, human preferences, or another model, and distinguishes rewarding the final result from rewarding the steps taken.
kv-cache-design
A guide to arranging an AI agent's conversation so previously processed text can be reused. A KV cache stores intermediate results for earlier tokens, while a prompt cache reuses a stable beginning across requests.
v4-best-practices
Use when working with deepseek-v4-pro or deepseek-v4-flash in thinking mode on multi-step or plan-driven tasks. Provides rules to prevent stale references, unverified plan assumptions, and vague plan output.
agent-evolution
A guide to making an AI agent improve from its past runs. It covers how to judge results, extract reusable lessons, and decide whether to store them as knowledge, instructions, code, or model training.
knowledge-org
A guide to organising large bodies of knowledge so an AI system can navigate relationships, summaries, and layers instead of searching only flat text chunks. It covers tree indexes, knowledge graphs, file-like structures, incremental updates, and long-term memory layouts.
post-training-strategy
A guide to choosing and planning ways to improve an AI model after its initial training. It explains when to add knowledge, teach a response format, use trial-and-error training, or use a smaller model to learn from a larger one.