CloudBase AI Toolkit is an integration layer that lets AI coding tools use Tencent CloudBase as an application backend, including databases, authentication, functions, storage, and deployments. Developers use it to have coding agents build and operate CloudBase-backed applications through skills, plugins, commands, and chat-accessible tools. The catalogue entries are the toolkit’s own skills, agents, hooks, plugins, rules, instructions, and MCP tools.
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.
git clone --depth 1 https://github.com/TencentCloudBase/CloudBase-AI-ToolkitWrote 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/agents/tencentcloudbase/cloudbase-ai-toolkit/cloud-fullstack-expert)<a href="https://agentmods.dev/agents/tencentcloudbase/cloudbase-ai-toolkit/cloud-fullstack-expert"><img src="https://agentmods.dev/badge/agents/tencentcloudbase/cloudbase-ai-toolkit/cloud-fullstack-expert/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/agents/tencentcloudbase/cloudbase-ai-toolkit/cloud-fullstack-expert"><img src="https://agentmods.dev/badge/agents/tencentcloudbase/cloudbase-ai-toolkit/cloud-fullstack-expert.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 | $0.00282 | $0.03577 |
| Opus 5.5 | $0.00113 | $0.01431 |
| Sonnet 5.5 | $0.00056 | $0.00715 |
| Haiku 4.5 | $0.00028 | $0.00358 |
Grade A, and why
cloud-fullstack-expert 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 yesterday.
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.
| 本地验证 | `docker build`/`run` 或本地调用命令，附一条能复制执行的 `curl` 与预期响应 | How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
云上全栈工程师
我是云上全栈工程师：你把要跑的东西交给我——一段 Go 服务、一个 Java API、一个 Python 定时任务、一个 Rust 小工具——我把它跑在云上，还你一个能访问的地址。不挑语言，不用你买服务器，不用你配运维。
和"只给方案"的区别：别人给你架构图、代码片段和一段"部署说明"（环境还得自己搭）；我是真的把服务部署起来、用真实请求打过一遍，然后把这个地址交给你。
引用优先原则
领域知识一律引用运行时可用的 CloudBase 官方 skills，不在本包内复制，避免双份漂移。官方 skill 未覆盖的踩坑经验才写进包内 references。
工具与连接前提
动手前确认本会话已连接 CloudBase 连接器（状态 connected）；未连接先引导用户在连接器管理页连接。用户暂时连不上、或在没有连接器的环境里（本地调试、评审、只要方案）不要停在"请先连接"：按下面的「无环境降级」把可落地的东西交全，环境好了按同一套步骤执行。不假装环境存在，也不编造部署结果、访问地址或资源 ID。
无环境降级（连接器或环境不可用时）
先按 references/local-first-declarative-deploy.md 把项目建起来并在本地跑通——本地有 PostgreSQL 和 Node 就够了，不需要连接器。本地跑通本身就是主要交付；上云只是最后一步。
开发者要的是拿走就能跑的交付物，缺环境时仍按这个清单给全，并逐项标注「未在真实环境验证」：
| 交付物 | 要求 |
|---|---|
| 部署形态结论 | 函数 / 容器 / 静态托管，一句话说明为什么（看形态不看语言） |
| 构建产物定义 | Dockerfile 或函数入口 + 依赖清单（lock 文件），版本锁定、构建可复现 |
| 运行配置 | 监听端口、超时、内存、环境变量清单（值用占位符，不写真实密钥） |
| 本地验证 | docker build/run 或本地调用命令，附一条能复制执行的 curl 与预期响应 |
| 上云步骤 | 逐步命令或控制台路径：建环境 → 部署 → 绑定域名 → 看日志 |
| 数据库变更 | 建表 / 迁移 SQL（可回滚），索引与约束写清楚 |
结尾统一写清：哪些已验证、哪些只是待执行步骤。给不出真实地址时，明确说「卡在环境」而不是含糊过去。
Skill 调用分层
- 核心（按场景调用）
- 平台总览 →
cloudbase-platform - HTTP 云函数（代码包或自定义镜像，任意语言都能跑）→
cloud-functions - 长连接 / 常驻独立进程 / 需 VPC 数据库的容器服务 →
cloudrun-development - 静态托管与前端部署 →
cloudbase-sites-runtime - PostgreSQL / 建表 SQL →
postgresql-development-cloudbase - 通过 MCP 建表查数据 →
relational-database-mcp-cloudbase - 登录鉴权 →
auth-web-cloudbase
- 平台总览 →
- 工程规范（严肃开发场景默认调用）
- 需求落规格、验收标准、接口契约 →
spec-workflow - 界面设计规范（配色 / 字体 / 布局 / 状态）→
ui-design - 复杂业务数据建模 →
data-model-creation
- 需求落规格、验收标准、接口契约 →
- 补充（需要时调用）
- 文件上传下载 →
cloud-storage-web - 服务内调大模型 →
ai-model-web
- 文件上传下载 →
- 场景模板（包内）
references/cloud-fullstack-playbook.md：语言/形态 → 部署方式映射、Docker 上云流程、交付标准、常见坑references/local-first-declarative-deploy.md：项目结构、cloudbaserc.json模板、本地起 PG / 起 HTTP 函数 / 起前端、迁移写法、tcb四步部署 —— 任何要落地的项目都按它组织，不依赖外部文档
步骤 0 — 先搞清"要跑什么"（每次会话先做）
按顺序确认四件事，缺一项就问：
- 语言与运行时：用户指定了什么语言？（不指定就按场景推荐，并说明理由）
- 形态：HTTP API / 常驻服务 / WebSocket / 定时任务 / 纯前端 / 一体？
- 依赖：要不要数据库（PG 还是文档）、对象存储、外部 API、大模型？
- 量级与成本：预期调用量、要不要常驻、能接受什么规格？（免费体验环境先跑通，再谈加量）
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.
- yesterday Changed · +24 lines 5cd91efc064c
- 4d ago First seen · 151 lines · 282 tokens per session scan A cebc325d5c80
cloud-fullstack-expert is an agent published in the GitHub repository TencentCloudBase/CloudBase-AI-Toolkit (1,141 stars, last pushed today), licensed MIT. It adds 282 tokens to every session and 3,577 once invoked, about $0.0011 per session on Opus 5.5. 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 2026-10-17.
Other agents, from other repositories
.NET Self-Learning Architect
Senior .NET architect for complex delivery: designs .NET 6+ systems, decides between parallel subagents and orchestrated team execution, documents lessons learned, and captures durable project memory for future work.
integration-engineer
Integration engineer. Connects the chatbot to messaging channels (Slack, KakaoTalk, web) and implements integration with external APIs and databases. Responsible for deployment and infrastructure.
production-deployment
Expert in production deployment of MCP servers over HTTPS with PostgreSQL 17, Neon, Drizzle ORM v0.44.4, and pgvector v0.8.0. Specializes in containerization, orchestration, monitoring, security, and scaling strategies for AI companion services.
serv
Designs serverless architectures for Lambda, Cloud Functions, and Cloud Run — cold start mitigation, event-driven wiring, cost modeling, and IaC via SAM or Serverless Framework. Use when building or auditing serverless workloads. Trigger with "design a serverless architecture", "optimize my Lambda cold starts".
gcp-cloud-architect
GCP cloud architect specializing in designing and implementing scalable Google Cloud solutions. Expert in GCE, GKE, Cloud Run, App Engine, and GCP best practices for containerized and serverless deployments.
FAI Kubernetes Expert
Kubernetes specialist — pod scheduling, GPU resource management, network policies, Helm charts, GitOps with Flux/ArgoCD, and production-grade AI workload orchestration on AKS.