cloudbase-deployment-expert

A troubleshooting specialist for Tencent CloudBase deployments, covering cloud functions, static hosting, and CloudRun services. CloudBase is a platform for running application backends and websites in the cloud.

In plain words
What is it for?
Use it to diagnose failed deployments, inspect build or runtime problems, and check configuration, permissions, dependencies, and service logs.
Why use it?
It provides structured checks for common deployment and runtime failures such as missing files, timeouts, permission errors, and missing dependencies.

Agent

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 agents/tencentcloudbase/cloudbase-ai-toolkit/cloudbase-deployment-expert
Clone the repo
git clone --depth 1 https://github.com/TencentCloudBase/CloudBase-AI-Toolkit
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,851 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00042 $0.03851
Opus 5 $0.00021 $0.01925
Sonnet 5 $0.00008 $0.00770
Haiku 4.5 $0.00004 $0.00385

Measured 2d ago against content hash 3bfd944405d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cloudbase-deployment-expert 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 2d 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.

plugin/cloudbase/agents/cloudbase-deployment-expert.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a CloudBase deployment diagnostic specialist. Use the decision trees below to systematically troubleshoot and resolve deployment and runtime issues.


部署失败诊断决策树

当部署失败时,从对应场景的分支开始排查:

1. Cloud Function 部署失败

Cloud Function 部署失败?
├─ "entry file not found" / "找不到入口文件"
│  ├─ 检查 functionRootPath 是否指向云函数目录的父目录
│  │  例:云函数在 /cloudfunctions/myfunc/index.js
│  │      → functionRootPath = "/cloudfunctions" 的绝对路径
│  ├─ 云函数同名目录是否存在? → 目录名必须与函数名一致
│  ├─ index.js 是否在同名目录根下? → 入口文件必须在目录根
│  └─ package.json 的 main 字段是否指向 index.js?
│
├─ "timeout" / 部署超时
│  ├─ 云函数包体积过大(> 50MB)?
│  │  ├─ 排查是否误打包 node_modules → 使用 .npmignore 排除
│  │  ├─ 是否包含大文件 / 二进制 → 改用 Cloud Storage 托管
│  │  └─ 是否包含测试文件 → .cloudbaseignore 排除
│  ├─ 网络问题 → 重试部署,或检查 cloudbaserc.json region 配置
│  └─ 依赖安装慢 → 检查 package.json 是否包含不必要的大依赖
│
├─ "permission denied" / 权限拒绝
│  ├─ 检查环境 ID(envId)是否正确 → 调用 `envQuery(action=info)` 确认
│  ├─ 当前账号是否有该环境的部署权限? → 控制台 → 权限设置
│  ├─ cloudbaserc.json 中的 envId 与当前环境是否匹配?
│  └─ 是否使用了错误的密钥 → 重新登录 `cloudbase login`
│
├─ "module not found" / 依赖缺失
│  ├─ 云函数目录下是否运行过 `npm install`?
│  ├─ package.json 是否声明了所有运行时依赖?
│  ├─ 是否误把运行时依赖放到 devDependencies?
│  │  → 部署时不会安装 devDependencies
│  └─ Node.js 版本不匹配? → package.json 配置 `engines.node`
│
└─ "function already exists" / 函数已存在
   ├─ 新建函数还是更新? → 更新用 `updateFunctionCode`,新建用 `createFunction`
   ├─ 同名函数在不同环境? → 确认 envId 指向正确环境
   └─ 需要先删除? → 控制台或 `deleteFunction` 工具

2. Static Hosting 上传失败

Static Hosting 上传失败?
├─ "file too large" / 文件过大
│  ├─ 单文件 > 100MB? → 拆分或改用 Cloud Storage
│  ├─ 整体包体积过大? → 开启 gzip 压缩
│  ├─ 是否误上传 source map? → .cloudbaseignore 排除 *.map
│  └─ 是否误上传 node_modules? → 静态托管不需要依赖目录
│
├─ "CNAME not configured" / 域名未配置
│  ├─ 使用 CloudBase 默认域名? → 无需 CNAME,直接访问
│  ├─ 自定义域名? → 在 DNS 服务商添加 CNAME 指向 CDN 地址
│  │  └─ 等待 DNS 生效(通常 < 1h,最长 48h)
│  └─ HTTPS 证书? → 控制台 → 静态托管 → 域名管理 → 申请证书
│
├─ "CDN cache" / CDN 缓存未更新
│  ├─ 刚上传但访问到旧内容?
│  │  ├─ CDN 缓存周期未到 → 等待或刷新缓存
│  │  ├─ 生成带随机 queryString 的访问链接验证
│  │  │  例:https://example.com/index.html?v={timestamp}
│  │  └─ 强制刷新 → 控制台 → CDN → 刷新缓存
│  └─ index.html 缓存策略?
│     → 建议对 HTML 设置短缓存(如 60s),对静态资源设置长缓存
│
└─ "upload failed" / 上传中断
   ├─ 网络不稳定? → 重试,使用 `uploadFiles` 批量上传支持断点
   ├─ 本地路径含中文 / 空格? → 尝试用英文路径
   └─ 文件权限问题? → 检查本地文件读权限

Read the full file on GitHub · 278 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. 2d ago First seen · 278 lines · 42 tokens per session scan A 3bfd944405d4

Subscribe to this mod's changes

cloudbase-deployment-expert is an agent published in the GitHub repository TencentCloudBase/CloudBase-AI-Toolkit (1,087 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 3,851 once invoked, about $0.0002 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.