CloudBase-AI-Toolkit AGENTS.md

A requirements-and-planning guide for CloudBase-AI-Toolkit, a project that includes documentation, an MCP package, configuration, tests, and skills. It describes how to record requirements, technical designs, and implementation tasks.

In plain words
What is it for?
Use it when planning a feature that needs a written specification, technical design, acceptance criteria, or a task checklist.
Why use it?
It helps turn loosely described work into agreed requirements and an organised implementation plan, while keeping private specifications out of the public repository.

Instructions file for CodexOpenCode

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 instructions/tencentcloudbase/cloudbase-ai-toolkit/agents-md
Clone the repo
git clone --depth 1 https://github.com/TencentCloudBase/CloudBase-AI-Toolkit

Made for: Codex, OpenCode.

Per session 6,129 This file is loaded in full into every session.
When invoked 6,129 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.06129 $0.06129
Opus 5 $0.03064 $0.03064
Sonnet 5 $0.01226 $0.01226
Haiku 4.5 $0.00613 $0.00613

Measured 2d ago against content hash a88b13e8de5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

CloudBase-AI-Toolkit AGENTS.md 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.

AGENTS.md · 313 lines

How it starts

The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.

# 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. ...
...
  1. 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。

  2. 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

# 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

<project_rules>

  1. 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
    • skills 项目级 skills 源目录
    • specs 需求/设计/任务文档(本地目录,不提交到公开仓库。含内部信息,仅保留 plugin-marketplace-listing/npm-supply-chain-security-hardening/ 两个被代码或规范依赖的子目录;完整历史归档在私有仓库 cloudbase-mcp-specs-archive
  2. AGENTS 文件约定

    • AGENTS.md 为项目及子目录的唯一可信源
    • CLAUDE.mdCODEBUDDY.md 均为指向 AGENTS.md 的软链
    • 新增子目录时,只需创建 AGENTS.md,用软链补齐 CLAUDE.md
  3. Skills & Rules 目录约定

    • .agents/skills 为 skills 的唯一可信源,.codebuddy/skills.claude/skills 软链至此
    • .agents/rules 为 rules 的唯一可信源(尚未创建时以 .agents/rules 为目标)
    • 新增 skills 请直接添加到 skills/ 目录,.agents/skills/ 下的软链会自动关联
    • 如果使用 npx skills 命令添加 skills 时保留 Universal 选项,不用重复添加 claudecodebuddy 选项
    • 某个目录中只要有 AGENTS.mdCLAUDE.md.agents/skills.claude/skills 中的任意一个,就需要自动补齐
  4. 项目子目录规则

    • mcp/ 子目录同样适用本约定:mcp/AGENTS.md 为源,mcp/CLAUDE.mdmcp/CODEBUDDY.md 为软链 </project_rules>

<internal_dirs>

本地内部目录的存放、同步与获取

两个目录都不提交到公开仓库,只在本地维护并归档到私有仓:

目录 内容 为什么不入库
specs/ 规格 / 设计 / 审视报告 含内部任务 ID、审视报告、评测/归因上下文
.workbuddy/ IDE 本地状态:AI 每日记忆、plans、expert 会话历史 类比 .idea/ / .vscode/,本就不该进版本控制;记忆里带内部任务 ID 与未公开决策

specs/ 里仅 specs/plugin-marketplace-listing/specs/npm-supply-chain-security-hardening/ 两个被代码或规范依赖的子目录留在仓库里,其余全部忽略。.workbuddy/ 全量忽略。

:新 spec 照旧写在本仓库 specs/<name>/{requirements,design,tasks}.md,只是不要 git add.workbuddy/ 由 IDE 自行维护,不用管。

Read the full file on GitHub · 313 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.

  1. 2d ago First seen · 313 lines · 6,129 tokens per session scan A a88b13e8de5e

Subscribe to this mod's changes

CloudBase-AI-Toolkit AGENTS.md is an instructions file published in the GitHub repository TencentCloudBase/CloudBase-AI-Toolkit (1,087 stars, last pushed yesterday), licensed MIT. It adds 6,129 tokens to every session, about $0.0306 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.