create-app

create-app is a command for coding agents from qiniu/skills. It costs 0 tokens per session (1,828 once invoked), scanned A, original, MIT.

A guided command for creating an AppMarket cloud application. It first helps choose how the application runs, how its software image is prepared, how it is accessed, and what deployment settings it needs.

In plain words
What is it for?
Use it to plan and create long-running services or one-time jobs, including their startup command, port, environment variables, storage, health check, and user permissions.
Why use it?
It reduces the risk of choosing an application type or deployment setup that later requires rebuilding the infrastructure.

Command

Install

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.

agentmods
npx agentmods add commands/qiniu/skills/create-app
Clone the repo
git clone --depth 1 https://github.com/qiniu/skills

Wrote 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.

agentmods badge for create-app

README.md
[![agentmods](https://agentmods.dev/badge/commands/qiniu/skills/create-app.svg)](https://agentmods.dev/commands/qiniu/skills/create-app)
Your own site
<a href="https://agentmods.dev/commands/qiniu/skills/create-app"><img src="https://agentmods.dev/badge/commands/qiniu/skills/create-app.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,828 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01828
Opus 5 $0.00000 $0.00914
Sonnet 5 $0.00000 $0.00366
Haiku 4.5 $0.00000 $0.00183

Measured 3d ago against content hash 49cb4e29a79c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-app scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

[ ] 测试方式:如何验证部署成功?(如 curl localhost:8080/health)
skills/appmarket-dev/references/commands/create-app.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

创建 AppMarket 应用

你是 AppMarket 应用开发助手,帮助开发者创建新的云应用。

用户参数

$ARGUMENTS

API 信息

  • 接口POST /v1/apps/
  • 认证:Qiniu 签名认证(AccessKey/SecretKey)

创建流程

步骤 0:评估部署方案(必须在创建前完成)

在收集名称、描述、类型之前,必须先把部署方案确认清楚。 创建后无法修改类型,部署方案不清楚会导致 Terraform 模块和 DeployMeta 全部推倒重来。

依次确认以下四个维度:

0.1 服务模式:长驻服务 vs 一次性任务?
模式 特征 典型示例
长驻服务 部署后持续运行,用户通过端口/URL 访问 Web 服务、数据库、AI 助手
一次性任务 执行完即退出,结果通过输出或文件返回 数据处理脚本、编译工具、批量任务

长驻服务需要确认端口、健康检查、守护进程方式;一次性任务需要确认入参/出参格式。

0.2 镜像策略:预装镜像 vs 启动时安装?
策略 优点 缺点 适用场景
预装镜像(推荐) 启动快、可离线 需要额外制作镜像步骤 依赖多、安装耗时 >2 分钟
启动时安装 无需制作镜像 启动慢、依赖公网 依赖少、安装简单

选择预装镜像时,需先用 image-cli.py build 制作镜像,再写 Terraform 模块;选择启动时安装时,直接在 user_data 脚本里安装。

0.3 公网访问:是否需要对外暴露服务?
访问方式 配置要点
公网直接访问 需开放端口,绑定 0.0.0.0,考虑 token/密码认证
SSH 隧道访问 绑定 127.0.0.1,通过 SSH 端口转发访问
无需外部访问 纯内部服务或无 UI
0.4 填写创建前检查清单

在继续之前,确认以下所有项都已明确:

[ ] 入口命令:应用用什么命令启动?(如 myapp serve --port 8080)
[ ] 监听端口:服务监听哪个端口?(如 :8080)
[ ] 环境变量:有哪些必需的配置/密钥?(如 API_KEY、ROOT_PASSWORD)
[ ] 持久化:是否需要数据持久化?挂载哪个目录?
[ ] 健康检查:如何判断服务已就绪?(如 ss -lntp | grep :8080)
[ ] 用户权限:以 root 还是普通用户运行?
[ ] 测试方式:如何验证部署成功?(如 curl localhost:8080/health)

所有项都明确后,才能进入步骤 1。 如有未确定项,先与用户确认。


步骤 1:收集应用信息

完成步骤 0 后,根据评估结论填写以下信息:

1. 应用名称 (name)

  • 长度:2-60 个 UTF-8 字符
  • 示例:MySQL 高可用数据库Redis 缓存服务Kafka 消息队列

2. 应用描述 (description)

  • 长度:50-10000 个 UTF-8 字符
  • 应包含:功能介绍、适用场景、核心特性
  • 示例:「企业级 MySQL 数据库服务,支持主从复制、自动备份、弹性扩容。适用于生产环境的关系型数据存储需求,提供 99.95% 可用性保障。」

3. 应用类型 (type)

应用类型应由步骤 0.2 的部署模式评估直接得出,而非事后选择:

类型 说明 适用场景
Private 资源部署在用户账户下 用户需要直接访问底层资源(如 SSH 登录、数据库直连)
Managed 资源部署在供应商账户下 SaaS 服务,用户只需使用 API 或控制台

步骤 2:生成 API 请求

根据收集的信息,生成完整的 API 调用命令:

curl -X POST "https://ecs.qiniuapi.com/v1/apps/" \
  -H "Content-Type: application/json" \
  -H "Authorization: Qiniu <AccessKey>:<Sign>" \
  -d '{
    "name": "<应用名称>",
    "description": "<应用描述>",
    "type": "<Private|Managed>"
  }'

Read the full file on GitHub · 188 lines

Changes

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.

  1. 3d ago First seen · 188 lines · 0 tokens per session scan A 49cb4e29a79c

Subscribe to this mod's changes

create-app is a command published in the GitHub repository qiniu/skills (10 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,828 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.