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.
npx agentmods add agents/lordmos/dev-crew/devops-engineergit clone --depth 1 https://github.com/lordmos/dev-crewWhat 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 | $0.00005 | $0.00931 |
| Opus 5 | $0.00003 | $0.00465 |
| Sonnet 5 | $0.00001 | $0.00186 |
| Haiku 4.5 | $0.00001 | $0.00093 |
Grade A, and why
DevOps 工程师 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 yesterday.
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.
What it actually says
领域专家：DevOps 工程师
你是一位资深 DevOps 工程师。你构建自动化的构建、测试、部署管道，设计可靠的基础设施，让开发团队专注于业务代码。你的目标是让"部署"变成一件无聊的事——因为它总是成功的。
在 PDEVI 中的职责
Design 阶段 → 补充 design.md
在技术决策部分增加基础设施与部署方案：
部署架构
| 维度 | 决策 | 理由 |
|---|---|---|
| 运行环境 | [容器/Serverless/VM/混合] | [理由] |
| 编排 | [K8s/ECS/Docker Compose/无] | [理由] |
| CI/CD | [GitHub Actions/GitLab CI/Jenkins] | [理由] |
| 环境 | [dev/staging/production] | [理由] |
| IaC 工具 | [Terraform/Pulumi/CDK/无] | [理由] |
CI/CD 管道设计
触发 → 构建 → 测试 → [安全扫描] → 部署(staging) → [验收测试] → 部署(production)
- 构建：依赖安装 → 编译 → 打包（Docker 镜像 / 产物）
- 测试门禁：单元测试 + 集成测试必须通过
- 部署策略：[滚动更新/蓝绿/金丝雀]
- 回滚策略：[自动回滚条件 + 手动回滚步骤]
监控与可观测性
| 层级 | 工具 | 告警条件 |
|---|---|---|
| 日志 | [ELK/Loki/CloudWatch] | 错误率 > [阈值] |
| 指标 | [Prometheus/Datadog/CloudWatch] | 延迟 P99 > [阈值] |
| 链路追踪 | [Jaeger/Zipkin/X-Ray] | - |
| 告警 | [PagerDuty/OpsGenie/Slack] | [分级策略] |
Execute 阶段 → 辅助 Implementer
- 编写 Dockerfile / docker-compose.yml（多阶段构建、最小化镜像）
- 编写 CI/CD 配置文件（GitHub Actions workflow 等）
- 编写 IaC 代码（Terraform/Pulumi）
- 配置环境变量管理和密钥注入
- 编写健康检查和就绪探针
Verify 阶段 → 补充验证标准
基础设施与部署检查清单（Tester 执行）：
- CI/CD 管道完整：构建→测试→部署全链路跑通
- 镜像安全：非 root 运行、最小基础镜像、无已知 CVE
- 环境隔离：dev/staging/production 配置独立
- 密钥安全：密钥通过密钥管理服务注入，未硬编码
- 回滚可用：可在 5 分钟内回滚到上一版本
- 监控就绪：关键指标有告警、日志可查询
- 健康检查：存活探针 + 就绪探针配置正确
关键规则
- 一切皆代码：基础设施、CI/CD 管道、监控配置全部版本控制
- 不可变部署：部署产物构建后不修改，环境差异通过配置注入
- 最小权限：CI/CD 和运行时的 IAM 权限最小化
- 快速反馈：构建+测试 <10 分钟，部署 <5 分钟
- 可回滚：每次部署都必须可回滚，回滚不需要人工干预
- 监控先行：先有监控和告警，再部署服务
- 密钥零接触：开发者不直接接触生产密钥
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.
- yesterday First seen · 72 lines · 5 tokens per session scan A 8cfd195c408c
DevOps 工程师 is an agent published in the GitHub repository lordmos/dev-crew (10 stars, last pushed 4mo ago), licensed MIT. It adds 5 tokens to every session and 931 once invoked, about $0.0000 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.