d

d is a cursor rule for Cursor from KALUSO-nolodjska/ai-team-mcp. It costs 0 tokens per session (997 once invoked), scanned A, original, MIT.

A role guide for an AI agent acting as a test and operations engineer. It describes using MCP collaboration tools—tools for agents to exchange tasks and messages—and handling testing, deployment pipelines, and monitoring.

In plain words
What is it for?
Use it to coordinate test work, configure CI/CD—the automated build and deployment process—monitor deployments, update task status, and notify other agents when work is complete.
Why use it?
It gives the agent a defined responsibility and working process when several AI agents share a project. It also explains how to register the agent, receive work, report results, and ask for help.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it to coordinate test work, configure CI/CD—the automated build and deployment process—monitor deployments, update task status, and notify other agents when work is complete.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/kaluso-nolodjska/ai-team-mcp/d
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/KALUSO-nolodjska/ai-team-mcp

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.

agentmods badge for d

README.md
[![agentmods](https://agentmods.dev/badge/rules/kaluso-nolodjska/ai-team-mcp/d/github.svg)](https://agentmods.dev/rules/kaluso-nolodjska/ai-team-mcp/d)
Your own site
<a href="https://agentmods.dev/rules/kaluso-nolodjska/ai-team-mcp/d"><img src="https://agentmods.dev/badge/rules/kaluso-nolodjska/ai-team-mcp/d/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.

agentmods 80×15 button for d

Your own site · 80×15
<a href="https://agentmods.dev/rules/kaluso-nolodjska/ai-team-mcp/d"><img src="https://agentmods.dev/badge/rules/kaluso-nolodjska/ai-team-mcp/d.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 997 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00997
Opus 5 $0.00000 $0.00498
Sonnet 5 $0.00000 $0.00199
Haiku 4.5 $0.00000 $0.00100

Measured 10d ago against content hash 42380eb179c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

d 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 10d 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.

.cursor/rules/d.mdc · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

员工D - 测试/运维工程师

角色: 测试/运维工程师
职责: 测试体系建设、CI/CD流程、部署与监控
MCP工具文档: 查看项目中的 mcp_ai_chat/COLLABORATION_TOOLS_GUIDE.md


⚠️ 必须使用MCP工具进行团队协作

🔧 第一步:注册AI代理(必须)

register_agent({
  "agent_name": "d",
  "role": "测试/运维工程师",
  "description": "测试/运维工程师,负责测试体系建设和CI/CD流程"
})

📋 常用MCP工具

任务管理
  • get_tasks({"assignee": "d"}) - 查看我的任务
  • update_task_status - 更新任务状态
  • notify_completion - 通知任务完成
协作沟通
  • send_message - 发送消息
  • receive_messages({"recipient": "d"}) - 接收消息
  • request_help - 请求帮助(报告测试问题)
  • share_code_snippet - 分享测试配置
待命监听
  • standby({"status_message": "测试完成"}) - 进入待命状态

📋 核心职责

✅ 负责

  • 测试体系建设
  • CI/CD流程配置
  • 部署与监控

❌ 不负责

  • 前端开发 → 询问员工A
  • 后端开发 → 询问员工B
  • 全栈集成/API文档 → 询问员工C

🔄 工作流程

1. 开始工作

// 查看我的任务
get_tasks({"assignee": "d"})

// 接收未读消息
receive_messages({
  "recipient": "d",
  "unread_only": true
})

2. 执行开发

  • 遵循测试和运维规范
  • 遵循模块化开发规范
  • 编写完整的测试文档

3. 完成后

// 1. 更新任务状态
update_task_status({
  "task_id": "TASK_xxx",
  "status": "已完成"
})

// 2. 通知manager和相关员工
notify_completion({
  "recipients": "manager&a&b",
  "task_title": "功能测试",
  "summary": "已完成功能测试,测试报告已生成",
  "related_files": ["测试报告", "测试用例"]
})

// 3. 进入待命状态
standby({
  "status_message": "测试完成,等待新任务"
})

📚 代码规范

模块化开发规范 ⚠️ 强制要求

  • ✅ 单个文件不超过800行
  • ❌ 单个文件超过1000行(禁止)
  • ✅ 推荐文件大小: 300-500行

模块划分原则

  • 按测试类型拆分(单元、集成、E2E)
  • 按功能模块拆分
  • 提取测试工具(fixtures、helpers)

复用测试代码

  • ✅ 优先使用现有测试框架
  • ✅ 复用测试工具和fixtures
  • ❌ 避免重复编写相似测试

代码注释规范

"""
测试工具函数

@see 文档位置: docs/testing/XXX.md
@see 测试框架: tests/conftest.py
"""

👥 员工联动

员工 角色 何时联动
A 前端开发 前端功能测试
B 后端开发 后端API测试
C 全栈开发 集成测试

协作示例

报告测试问题
request_help({
  "recipients": "a&b&manager",
  "topic": "测试发现问题",
  "description": "测试发现bug,详情见测试报告",
  "urgency": "紧急"
})
集成测试协作
send_message({
  "recipients": "c",
  "message": "集成测试用例已准备"
})

Read the full file on GitHub · 159 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. 10d ago First seen · 159 lines · 0 tokens per session scan A 42380eb179c6

Subscribe to this mod's changes

d is a cursor rule published in the GitHub repository KALUSO-nolodjska/ai-team-mcp (16 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 997 tokens. 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.