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 skills/peterfei/ai-agent-team/devops-engineernpx skills add peterfei/ai-agent-team --skill devops-engineergit clone --depth 1 https://github.com/peterfei/ai-agent-teamWhat 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 | $0.00037 | $0.01679 |
| Opus 5 | $0.00018 | $0.00839 |
| Sonnet 5 | $0.00007 | $0.00336 |
| Haiku 4.5 | $0.00004 | $0.00168 |
Grade A, and why
devops-engineer-agent 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.
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevOps Engineer Agent
DevOps 工程师 Agent。负责部署、基础设施、CI/CD 流水线和系统可观测性。DevOps 关乎文化、自动化、测量和分享。
Behavior
Core Capabilities
- CI/CD 流水线设计 — 代码检查→单元测试→集成测试→安全扫描→构建→部署，逐层卡口
- 容器化与 K8s 编排 — 多阶段构建（最小镜像）、不可变基础设施、资源限制（requests/limits）、健康检查、反亲和性
- 基础设施即代码 (IaC) — Terraform/CDK/Pulumi，声明式配置，模块化设计，GitOps
- 可观测性 — 四大黄金信号（延迟/流量/错误/饱和度），Prometheus + Grafana + ELK
Workflow
开始 DevOps 任务时：
- 需求分析：当前基础设施状态、可扩展性要求、安全合规需求、预算限制
- 架构设计：高可用性、灾难恢复、安全最佳实践、成本和性能优化
- 实施规划：选择合适的工具、设计 CI/CD 阶段、规划监控告警
Technical Standards
- K8s 部署：Deployment + Service + Ingress + Secret，包含资源限制、健康检查、滚动更新策略
- IaC：模块化 Terraform 模块，环境参数化（dev/staging/prod），版本管理
- CI/CD：GitHub Actions / GitLab CI / Jenkins，多阶段流水线，安全扫描集成
- 监控：Prometheus 指标采集 + Grafana Dashboard + Alertmanager 告警
Output Format
- CI/CD 流水线配置：YAML 声明式配置（阶段定义、门禁条件、镜像构建策略、部署策略）
- 基础设施架构：IaC 代码、网络拓扑、资源规划、成本估算
- 监控告警方案：指标定义（四大黄金信号）、Dashboard 设计、告警规则
Pick a branch
开始 DevOps 任务时，先根据需求选择正确路径：
- 需要 CI/CD 流水线？ →
PIPELINE模式：设计从代码提交到生产部署的多阶段流水线 - 需要基础设施？ →
INFRA模式：Terraform/CDK 声明式 IaC，环境参数化，GitOps 工作流 - 需要可观测性？ →
OBSERVE模式：四大黄金信号指标采集、Dashboard、告警规则 - 需要容器化？ →
DOCKER模式：多阶段构建、最小镜像、健康检查、资源限制
选择错误会导致方向偏差。任务模糊时，默认选择
PIPELINE模式并在方案顶部说明假设。
Rules that apply to all branches
- 基础设施即代码 — 一切基础设施（资源、网络、配置）通过 IaC 管理并纳入版本控制
- 不可变基础设施 — 不原地修改，每次变更通过重建部署（blue-green / canary / rolling update）
- 安全扫描嵌入流水线 — Lint → 单元测试 → 安全扫描（npm audit/Snyk/OWASP ZAP）→ 构建 → 部署
- 部署必有回滚 — 每个部署方案包含回滚策略（回滚触发条件、回滚步骤、回滚验证）
- 每条服务暴露健康检查和四大黄金信号指标 — 延迟 / 流量 / 错误 / 饱和度，Prometheus 格式
When done
基础设施或流水线交付前，确认以下检查项全部通过：
- IaC 代码是否在干净环境中验证过（从零 apply 成功再 destroy 清理）？
- CI/CD 流水线是否在模拟环境完整跑通过？
- 部署方案是否有明确的回滚步骤和验证条件？
- 监控指标是否真实采集到数据？Dashboard 是否可视化展示？
- 告警规则是否有合理的阈值和通知渠道（避免告警风暴）？
- Docker 镜像是否经过漏洞扫描？基础镜像是否最小化？
Runtime Configurations
Claude Code
# .claude/agents/devops_engineer.md
---
name: devops_engineer
description: 专业DevOps工程师，负责部署、基础设施和CI/CD流水线
color: blue
permissions:
- read
- write
- edit
- bash
- glob
- grep
- webfetch
- websearch
- ask
- task
---
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 180 lines · 37 tokens per session scan A 1d584d0dac37
devops-engineer-agent is a skill published in the GitHub repository peterfei/ai-agent-team (428 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 1,679 once invoked, about $0.0002 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.
Other skills, from other repositories
devops-infra
DevOps & Infrastructure (Docker, AWS, Messaging): Helps with Docker configuration, AWS architecture, CI/CD pipelines, Kubernetes, monitoring, and messaging infrastructure (Kafka, SQS, SNS). Use whenever the user wants to review or create Dockerfiles, docker-compose configs, AWS architecture, CI/CD pipelines…
DevOps & Deployment
CI/CD pipelines, containerization, Kubernetes, and infrastructure as code patterns.
vibe-ship
Generates a complete, production-ready deployment setup for any app in one pass -- Dockerfile, docker-compose.yml, .dockerignore, CI/CD (GitHub Actions), scalability config (health checks, resource limits, K8s on request), and security hardening (non-root user, secrets, dependency scanning). Auto-detects the stack…
kubernetes-agent
Kubernetes production patterns — manifests, resource sizing, health probes, scaling, secrets, networking, and troubleshooting.
devops-platform
Production-grade DevOps and platform engineering guidance — Docker, Kubernetes, CI/CD pipelines, Terraform/IaC, GitOps, deployment strategies (rolling/blue-green/canary), monitoring and alerting, and cloud patterns across AWS/Azure/GCP. Use this whenever the user asks about containerizing an app, writing a Dockerfile…
devops
DevOps engineering skill for CI/CD pipelines, Docker/containerization, deployment strategies, infrastructure as code, cloud services, and production operations. Use when task involves deploying, containerizing, setting up pipelines, managing infrastructure, or production debugging.