A project rule set for a CloudBase AI Toolkit codebase. It defines coding conventions, repository folders, custom slash commands, and workflows for tasks such as new features or adding AI IDE support.

Listing available commands, planning and implementing new features, documenting requirements and designs, and adding configuration for another AI coding environment.

It gives agents consistent project-specific instructions instead of making them infer how this repository should be changed.

project — Cursor rule for Cursor by TencentCloudBase

About the project

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.

TencentCloudBase/CloudBase-AI-Toolkit · 1,138 stars · on GitHub · docs.cloudbase.net

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.

Clone the repo

git clone --depth 1 https://github.com/TencentCloudBase/CloudBase-AI-Toolkit

Made for: Cursor.

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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/tencentcloudbase/cloudbase-ai-toolkit/project/github.svg)](https://agentmods.dev/rules/tencentcloudbase/cloudbase-ai-toolkit/project)

Your own site

<a href="https://agentmods.dev/rules/tencentcloudbase/cloudbase-ai-toolkit/project"><img src="https://agentmods.dev/badge/rules/tencentcloudbase/cloudbase-ai-toolkit/project/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.

Your own site · 80×15

<a href="https://agentmods.dev/rules/tencentcloudbase/cloudbase-ai-toolkit/project"><img src="https://agentmods.dev/badge/rules/tencentcloudbase/cloudbase-ai-toolkit/project.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,312 This file is loaded in full into every session.

When invoked 1,312 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01312	$0.01312
Opus 5.5	$0.00525	$0.00525
Sonnet 5.5	$0.00262	$0.00262
Haiku 4.5	$0.00131	$0.00131

Measured 1mo ago against content hash 070347250682, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

project 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 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.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

project — 89% identical, 125 lines differ

.cursor/rules/project.mdc · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CloudBase AI Toolkit 项目规范

项目统一约束 ⚠️

代码规范（强制要求）

所有代码注释必须使用英文，禁止使用中文注释
代码中的变量名、函数名、类名等标识符应使用英文
代码中的字符串内容可以使用中文（如用户界面文本、错误信息等）
通过 CLI 提交 PR 的内容也是英文

提交规范（强制要求）

Git commit 信息必须使用英文，采用 conventional-changelog 风格
Commit 信息格式： type(scope): description，例如 feat(auth): add user authentication system
在 feat(xxx): 后面可以添加 emoji 字符
禁止在 commit 信息中使用中文

项目结构

doc 存放对外的文档
mcp 核心的 mcp package
config 用来给 AI IDE提供的规则和 mcp 预设配置
tests 自动化测试
specs 存放核心的迭代过程中沉淀的 spec

自定义斜杠命令

命令列表

`/list_commands`

功能： 列出所有可用的斜杠命令 触发条件： 当用户输入 /list_commands 时 行为： 显示所有可用的命令及其功能描述

`/new_feature`

功能： 新功能开发工作流 触发条件： 当用户输入 /new_feature 或提出新需求时 行为： 采用标准软件工程方式独立开展工作，每个环节完成后都需要用户确认后才可进行下一个环节 工作流程：

需求澄清：搞清楚问题和需求
需求文档设计：按照 EARS 简易需求语法方法描述，保存在 specs/spec_name/requirements.md
技术方案设计：描述技术架构，保存在 specs/spec_name/design.md
任务拆分：细化具体任务，保存在 specs/spec_name/tasks.md
执行任务：独立自主运行，及时更新任务状态

`/add_aiide`

功能： 新增 AI IDE 支持 触发条件： 当用户输入 /add_aiide 时 行为： 按照 CloudBase AI Toolkit 新增 AI IDE 支持工作流执行 步骤：

创建 IDE 特定配置文件（如 .mcp.json 和 CLAUDE.md）
更新 scripts/fix-config-hardlinks.sh 添加新目标文件到硬链接列表
执行硬链接脚本确保规则文件同步
创建 doc/ide-setup/{ide-name}.md 配置文档
更新 README.md、doc/index.md、doc/faq.md 中的 AI IDE 支持列表
更新 IDE 文件映射（在 mcp/src/tools/setup.ts 中）
验证硬链接状态和文档完整性
测试IDE特定下载功能是否正常工作

`/add_example`

功能： 新增用户案例/视频/文章 触发条件： 当用户输入 /add_example 时 行为： 按照 CloudBase AI Toolkit 新增用户案例工作流执行 步骤：

注意标题尽量用原标题，然后适当增加一些描述
更新 README.md
更新 doc/tutorials.md

`/sync_doc`

功能： 同步文档到官方文档库 触发条件： 当用户输入 /sync_doc 时 行为： 执行 cp -r doc/* {cloudbase-docs dir}/docs/ai/cloudbase-ai-toolkit/

`/update_readme`

功能： 更新 README 文档 触发条件： 当用户输入 /update_readme 时 行为：

按照中文文档更新英文文档（README-ZH.md → README.md）
英文文档中的banner 图是英文的，保持不变
复制 README-ZH.md 覆盖 mcp/

`/fix_config`

功能： 修复 config 中的硬链接 触发条件： 当用户输入 /fix_config 时 行为： 执行 sh ./scripts/fix-config-hardlinks.sh

Read the full file on GitHub · 128 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.

1mo ago First seen · 128 lines · 1,312 tokens per session scan A 070347250682

Subscribe to this mod's changes

project is a cursor rule published in the GitHub repository TencentCloudBase/CloudBase-AI-Toolkit (1,138 stars, last pushed today), licensed MIT. It adds 1,312 tokens to every session, about $0.0052 per session on Opus 5.5. 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.

ai cloudbase mcp miniprogram tencent web

project