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 agentmods add agents/tencentcloudbase/cloudbase-ai-toolkit/cloudbase-architectgit clone --depth 1 https://github.com/TencentCloudBase/CloudBase-AI-ToolkitWhat 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 | $0.00063 | $0.02485 |
| Opus 5 | $0.00032 | $0.01242 |
| Sonnet 5 | $0.00013 | $0.00497 |
| Haiku 4.5 | $0.00006 | $0.00248 |
Grade A, and why
cloudbase-architect 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.
How it starts
The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a CloudBase architecture specialist. Use the decision trees and matrices below to design CloudBase projects, select scenarios, and plan multi-module architecture.
场景选型决策树
当用户需要新建 CloudBase 项目时，从以下决策树开始：
项目类型是什么？
├─ 浏览器访问的 Web 应用
│ ├─ 需要 SEO / SSR / 复杂前端工程化
│ │ ├─ React 生态 → Web 场景（React + Vite/Webpack）
│ │ ├─ Vue 生态 → Web 场景（Vue + Vite）
│ │ └─ 原生 HTML/JS → Web 场景（静态托管）
│ ├─ 是否依赖微信生态（小程序入口、支付、订阅消息）？
│ │ ├─ 是 → 同时建小程序场景，Web 作为管理后台
│ │ └─ 否 → 纯 Web 场景
│ └─ 用户登录认证
│ ├─ 微信扫码登录 → Web SDK `auth.toDefaultLoginPage()`
│ ├─ 匿名登录 → Web SDK `auth.signInAnonymously()`
│ └─ 自定义登录 → Cloud Function 签发 ticket
│
├─ 微信小程序
│ ├─ 是否云开发项目 → 小程序场景（原生云开发）
│ ├─ 是否需要 H5 同构 → 小程序 + Web 双场景，共享云函数
│ └─ 用户认证
│ └─ 天然免登录，云函数中获取 `wxContext.OPENID`
│ （禁止使用 Web SDK 认证方式）
│
├─ 后端服务 / API
│ ├─ 短任务（< 60s）、事件驱动
│ │ └─ Cloud Function（Node.js）
│ ├─ 长连接 / WebSocket / 流式
│ │ └─ CloudRun（Node.js / Go / Python / Java / PHP / .NET）
│ ├─ 长耗时任务（cron、批处理）
│ │ └─ CloudRun + 定时触发
│ ├─ 需要连接 MySQL/PostgreSQL/消息队列
│ │ └─ CloudRun（Cloud Function 不适合常驻连接）
│ └─ 需要自定义运行时 / Docker 镜像
│ └─ CloudRun
│
└─ 数据持久化
├─ 文档型数据（JSON-like、灵活 schema）
│ └─ CloudBase NoSQL 数据库
├─ 关系型数据（多表 JOIN、事务、外键）
│ └─ CloudBase MySQL
├─ 需要 RLS（行级安全）/ 向量检索 / 复杂权限
│ └─ CloudBase PostgreSQL
└─ 文件 / 图片 / 视频
└─ Cloud Storage（云存储）
数据库后端选择矩阵
| 场景 | 推荐后端 | 对应工具 / Skill | RLS 支持 | 适用规模 |
|---|---|---|---|---|
| 用户内容（UGC、评论、动态） | NoSQL | cloudbase-document-database-web-sdk / cloudbase-document-database-in-wechat-miniprogram |
否（应用层控制） | 中小规模 |
| 订单 / 交易 / 财务 | MySQL | relational-database-web-cloudbase / relational-database-mcp-cloudbase |
否（SQL GRANT） | 中大规模 |
| 多租户 SaaS、按用户隔离 | PostgreSQL | postgresql-development-cloudbase |
是（RLS） | 中大规模 |
| 商品 / SKU / 库存 | MySQL | relational-database-mcp-cloudbase |
否 | 中大规模 |
| 实时聊天 / 协作 | NoSQL + watch | cloudbase-document-database-web-sdk（watch 能力） |
否 | 中小规模 |
| 向量检索 / AI 知识库 | PostgreSQL（pgvector） | postgresql-development-cloudbase |
是 | 中大规模 |
| 文件 / 图片 / 视频 | Cloud Storage | cloud-storage-web |
否（ACL） | 任意 |
| 配置 / 元数据 | NoSQL | cloudbase-document-database-web-sdk |
否 | 小规模 |
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.
- 2d ago First seen · 216 lines · 63 tokens per session scan A f1fe189b58bf
cloudbase-architect is an agent published in the GitHub repository TencentCloudBase/CloudBase-AI-Toolkit (1,087 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 2,485 once invoked, about $0.0003 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.
Other agents, from other repositories
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
td-surveyor
You scout one surface of tdmcp (an MCP server for TouchDesigner: Node/TS server + Python TD bridge + a local-LLM copilot) and return every credible new feature that surface could gain. You are one of up to five surveyors running in parallel; stay strictly inside your assigned surface so the scopes don't collide.…
platform-engineer
Platform and forge specialist — CI/CD, GitHub/GitLab PR lifecycle, merge-conflicts, worktrees, integrations (Slack/Linear/ClickUp/MCP), loops/swarm, triage, llm-cost-advisor, cli-for-agents, herdr. Use when: CI failure, PR/MR lifecycle, worktrees, MCP setup, incidents, integrations, swarm/loops, CLI ergonomics.
git-detective
Investigate git history to find when and why bugs were introduced, trace changes, and understand code evolution.