Project rules for a CloudBase AI Toolkit codebase, including its folders, naming practices, commits, and slash commands.

Listing commands, planning new features, adding AI-IDE support, organizing specifications, and maintaining the project structure.

They give the coding agent consistent project-specific instructions instead of relying on guesswork.

project — Cursor rule by TencentCloudCommunity

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 rules/tencentcloudcommunity/mcp-server/project

Clone the repo

git clone --depth 1 https://github.com/TencentCloudCommunity/mcp-server

Made for: Cursor.

Per session 2,583 This file is loaded in full into every session.

When invoked 2,583 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin 89% copy Near-identical to another mod 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	$0.02583	$0.02583
Opus 5	$0.01291	$0.01291
Sonnet 5	$0.00517	$0.00517
Haiku 4.5	$0.00258	$0.00258

Measured 2d ago against content hash 528a8e827896, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

Origin

This is a copy

89% identical to project — 125 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

src/CloudBase-AI-ToolKit/.cursor/rules/project.mdc · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 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）

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 · 251 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.

2d ago First seen · 251 lines · 2,583 tokens per session scan A 528a8e827896

Subscribe to this mod's changes

project is a cursor rule published in the GitHub repository TencentCloudCommunity/mcp-server (28 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,583 tokens to every session, about $0.0129 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to project, differing in 125 lines, and is treated as a copy.

Planning mcp mcp-server mcp-servers-directory mcp-tools tencent-cloud tencentcloud

project