Home / tencentcloudbase / cloudbase-ai-toolkit · GitHub

AGENTS.mdA

AGENTS.md from tencentcloudbase/cloudbase-ai-toolkit is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned

mdr add tencentcloudbase/cloudbase-ai-toolkit/AGENTS.md@git:20261016.77be12e

Pins git:20261016.77be12e in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 14 of 14 checks passed
Kind: AGENTS.md file
Repository: tencentcloudbase/cloudbase-ai-toolkit
Path: AGENTS.md
Versions recorded: 8
Latest version: git:20261016.77be12e, committed Oct 16, 2026
First version recorded: Aug 24, 2026
Size: 25,258 bytes
Repository stars: 1,141
License: MIT

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

<workflow>
1. 每当我输入新的需求的时候，为了规范需求质量和验收标准，你首先会搞清楚问题和需求
2. 需求评估：先根据需求大小、影响范围、复杂度和风险判断是否需要走完整 spec 流程。对于跨模块、中大型、高风险、涉及较多协作或验收边界不清晰的需求，必须先补齐 spec；对于小型、低风险、边界清晰的改动，不强制要求产出 spec，但仍需先明确目标、范围和验收标准。
3. 需求文档和验收标准设计：如果判断需要 spec，则先完成需求设计，按照 EARS 简易需求语法方法来描述，保存在 `specs/spec_name/requirements.md` 中，跟我进行确认，最终确认清楚后，需求定稿，参考格式如下

```markdown
# 需求文档

## 介绍

需求描述

## 需求

### 需求 1 - 需求名称

**用户故事：** 用户故事内容

#### 验收标准

1. 采用 ERAS 描述的子句 While <可选前置条件>, when <可选触发器>, the <系统名称> shall <系统响应>，例如 When 选择"静音"时，笔记本电脑应当抑制所有音频输出。
2. ...
...
```
4. 技术方案设计：对于需要 spec 的需求，在完成需求设计之后，你会根据当前的技术架构和前面确认好的需求，进行技术方案设计，保存在 `specs/spec_name/design.md` 中，精简但是能够准确描述技术架构（例如架构、技术栈、技术选型、数据库/接口设计、测试策略、安全性），必要时可以用 mermaid 来绘图，跟我确认清楚后，才进入下阶段。对于不需要 spec 的小需求，可以直接在对话中给出精简方案并继续执行。
5. 任务拆分：对于需要 spec 的需求，在完成技术方案设计后，你会根据需求文档和技术方案，细化具体要做的事情，保存在 `specs/spec_name/tasks.md` 中，跟我确认清楚后，才开始正式执行任务，同时更新任务状态。对于不需要 spec 的小需求，可以直接给出精简任务说明或直接执行。

   注：`specs/` 已加入 `.gitignore`，spec 文档只写在本地、**不要 `git add` 到公开仓库**（含内部信息，完整历史归档在私有仓库 `cloudbase-mcp-specs-archive`）。

格式如下

``` markdown
# 实施计划

- [ ] 1. 任务信息
  - 具体要做的事情
  - ...
  - _需求: 相关的需求点的编号

```
</workflow>

<project_rules>
1. 项目结构
   - doc 存放对外的文档
   - mcp 核心的 mcp package
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add tencentcloudbase/cloudbase-ai-toolkit/AGENTS.md@sha256:3311566dd37997a2

The line at the top of this page pins the label git:20261016.77be12e, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_sha7p24bvdles7ri.svg)](https://markdownregistry.com/a/art_sha7p24bvdles7ri)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 8 versions of this file, between Aug 24, 2026 and Oct 16, 2026, about one every 8 days.

version	committed	commit	size	audit
git:20261016.77be12e latest	2026-10-16	77be12e	25,258 B	A	view · diff
git:20261012.3666f15	2026-10-12	3666f15	25,105 B	A	view · diff
git:20260924.42f9654	2026-09-24	42f9654	23,805 B	A	view · diff
git:20260903.97cda34	2026-09-03	97cda34	23,541 B	A	view · diff
git:20260903.bbe2c73	2026-09-03	bbe2c73	23,501 B	A	view · diff
git:20260902.1938cad	2026-09-02	1938cad	23,289 B	A	view · diff
git:20260828.f484583	2026-08-28	f484583	22,137 B	A	view · diff
git:20260824.70353ed	2026-08-24	70353ed	15,683 B	A	view

Audit of the latest version

A 14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Size between 200 bytes and 200 KB (25258 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

tencentcloudbase/cloudbase-ai-toolkit · 1,141 stars · license MIT · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_sha7p24bvdles7ri
GET https://markdownregistry.com/api/v1/resolve?ref=tencentcloudbase/cloudbase-ai-toolkit/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/3311566dd37997a2e6fcb0d81b9123c94505de94ea6961e41d6bd6c41b1a11e3

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.

More from tencentcloudbase/cloudbase-ai-toolkit

project Cursor rule

tencentcloudbase/cloudbase-ai-toolkit · .cursor/rules/project.mdc

git:20250814.0b2a2ca · audit A · 1,141 stars

CLAUDE.md CLAUDE.md file

tencentcloudbase/cloudbase-ai-toolkit · CLAUDE.md

git:20260625.bd0be5f · audit B · 1,141 stars

ai-model-nodejs SKILL.md skill

tencentcloudbase/cloudbase-ai-toolkit · config/.claude/skills/ai-model-nodejs/SKILL.md · Use this skill for Node.js backend AI via @cloudbase/node-sdk (>=3.16.0) — cloud functions, CloudRun…

v2.35.2 · audit A · 1,141 stars

ai-model-web SKILL.md skill

tencentcloudbase/cloudbase-ai-toolkit · config/.claude/skills/ai-model-web/SKILL.md · Use this skill when a browser/Web app (React, Vue, Next, Nuxt, static sites, SPAs, dashboards, AI chat UI, 页面, 前端, 网页)…