role-DevOps

role-DevOps is a skill for Claude Code, Codex from TashanGKD/tashan-cursor-skills. It costs 61 tokens per session (12,397 once invoked), scanned D, original, MIT.

A DevOps role responsible for keeping software running reliably, scaling it as usage grows, and monitoring systems in production. DevOps covers deployment, operations, and automation.

In plain words
What is it for?
Use it to plan deployments, CI/CD pipelines, monitoring, alerts, rollback steps, and infrastructure changes.
Why use it?
It reduces manual release work and helps teams detect failures, capacity problems, and AI usage costs before they become larger incidents.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it to plan deployments, CI/CD pipelines, monitoring, alerts, rollback steps, and infrastructure changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tashangkd/tashan-cursor-skills/role-devops
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.

Any agent
npx skills add TashanGKD/tashan-cursor-skills --skill role-devops
Clone the repo
git clone --depth 1 https://github.com/TashanGKD/tashan-cursor-skills

Made for: Claude Code, Codex.

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 role-DevOps

README.md
[![agentmods](https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/role-devops/github.svg)](https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/role-devops)
Your own site
<a href="https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/role-devops"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/role-devops/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 role-DevOps

Your own site · 80×15
<a href="https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/role-devops"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/role-devops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 12,397 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 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 $0.00061 $0.12397
Opus 5 $0.00030 $0.06198
Sonnet 5 $0.00012 $0.02479
Haiku 4.5 $0.00006 $0.01240

Measured 9d ago against content hash 50045e3f5311, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade D, and why

role-DevOps scanned grade D with 3 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 9d 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

r = httpx.post( "https://openclaw.tashan.chat/api/internal/chat",

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

> ⚠️ **管理员用户(Administrators 组成员)的公钥不放 `~/.ssh/authorized_keys`**,必须放以下专用路径:

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

> **错误示范**:说了「✅ 任务完成」但只做了一条 `curl /health`。
skills/role-DevOps/SKILL.md · 1,017 lines

How it starts

The opening of the file, as written. The whole thing — 1,017 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DevOps / 运维角色

他山AI产品专用。生产环境的看门人,AI调用成本监控是新职责。


我是谁

核心职责:保障产品在生产环境中稳定、可扩展、可观测地运行。

第一性原理

  • 自动化优先:能脚本化的不手动操作,能 CI/CD 的不手动发布
  • 可观测性内建:每个关键节点有监控,异常必须有告警
  • 弹性扩展:用量增长时系统能平滑扩容
  • AI 调用成本的实时监控是运维的新职责,与服务器成本同等重要

知识导航表(执行任务前必须按顺序读取)

层级 文档 用途
D0 认知根确认 _内部总控/开发规范/部署架构总览.md 先于一切:确认本次部署的认知根——当前生产环境是什么状态?新部署对哪些现有服务有影响?端口是否冲突?带此问题进入任务
① 元项目顶层 _内部总控/元项目导航.md 确认任务所属子项目,了解顶层约束
② 当前子项目 项目群/[项目]/DEPLOY_ARCH.md 当前部署架构(必须更新)
③ 任务层文档 项目群/[项目]/技术架构师/技术架构.md 基础设施需求
④ 总规范库 _内部总控/开发规范/AI调用服务器助手接口规范.md AI助手接口规范(请求格式/认证/调用方式)
④-b 部署约束 .cursor/rules/deploy-arch-maintenance.mdc 部署架构文档维护规则(RULE-21~25)
⑤ 角色专属 .cursor/skills/role-DevOps/knowledge/部署踩坑速查.md 历史踩坑速查

元认知前置(每次激活后必须先回答)

执行任何部署任务前,必须回答以下三个问题(F-028):

  1. 有没有更好的方法? 有没有比当前方案更简单或更可靠的部署方式?
  2. 是否考虑全面了? 有没有遗漏回滚方案、监控配置、或数据迁移步骤?
  3. 是否需要先搜索? 对 Docker/nginx/CI-CD 配置不确定时,先搜索再动手。

激活后立即执行

Step -2【路径解析(document-path-resolver)】
        Glob: .cursor/project-config.md
        IF 存在:
          Read: .cursor/project-config.md
          解析:PATH_技术架构、PATH_产品定义
          注意:DEPLOY_ARCH.md 路径通常在项目根目录,如有自定义请在 project-config.md 中声明
          输出:「📌 已从 project-config.md 加载路径映射」
        IF 不存在:使用默认路径,静默通过

Step 0  【场景判断】本次任务是「本地 dev 启动」还是「生产部署」?
        
        本地 dev 启动(uvicorn --reload + vite dev):
          → 跳过 Step 1-3,直接执行 Step L1-L3(本地启动流程)
          → 完成后执行 Step L4(本地验证清单,见下方)
          → 不更新 DEPLOY_ARCH.md
        
        生产部署(Docker + CI/CD):
          → 正常执行 Step 1-5

Step 1  确认测试工程师的"测试通过报告"已就绪
Step 2  检查部署架构文档(DEPLOY_ARCH.md)
Step 3  执行部署流程(六步标准流程)
Step 4  【强制】部署后生产环境验证(见下方「部署后验证清单」)
Step 5  更新 DEPLOY_ARCH.md 变更记录

⚠️ 本地 dev 启动验证清单(RULE-LOC,本地模式下强制,不可只做 /health)

错误示范:说了「✅ 任务完成」但只做了一条 curl /health。 本地启动后必须跑完以下 9 项,有任何 ❌ 必须先修复再说完成。

Step L1  准备工作
  □ 修复 .env(检查路径是否跨平台,特别是 Windows → macOS/Linux)
  □ 创建/激活 Python venv,安装 requirements.txt
  □ 确认 Node 版本正确(nvm use XX)

Step L2  启动服务
  □ 后端:uvicorn main:app --port [BACKEND_PORT] --reload(后台)
  □ 前端:npm run dev(后台,等待 "ready in" 出现)

Step L3  等待就绪(两个服务均出现就绪日志后再执行 L4)

Step L4  本地验证清单(9 项,必须全部 ✅ 才能说「服务已就绪」)

  [V1] 后端健康检查
       curl http://localhost:{BACKEND_PORT}/health → {"status":"ok"}

  [V2] 前端代理是否打通(/api → 后端)
       curl http://localhost:{FRONTEND_PORT}/api/health → {"status":"ok"}

  [V3] 核心会话接口
       curl http://localhost:{BACKEND_PORT}/session → 含 session_id 字段

  [V4] 模型列表接口
       curl http://localhost:{BACKEND_PORT}/models → models 数组非空

  [V5] 智能体列表接口
       curl http://localhost:{BACKEND_PORT}/agents → agents 数组非空

  [V6] 本次新增/修改的路由(必测)
       针对本次开发的每个新路由,至少发一次请求确认可达(非 404/500)
       示例:curl http://localhost:{BACKEND_PORT}/twin/prompts → 非 404

  [V7] 认证端点存在性(期望 422,不是 404/405)
       curl -X POST http://localhost:{BACKEND_PORT}/auth/login -d '{}' → HTTP 422

  [V8] SSE 流式端点防护(空消息→期望 400,不是 500)
       curl -X POST http://localhost:{BACKEND_PORT}/chat -d '{"message":""}' → HTTP 400

  [V9] 前端 HTML 完整性
       curl http://localhost:{FRONTEND_PORT}/ | grep '<div id="root">' → 非空

  [V10] 数据库认证可用性(仅当 DATABASE_URL 已配置时执行)
       发送格式正确但凭证错误的登录请求 → 期望 HTTP 401(非 503)
       503 = 数据库未连通(需检查 DATABASE_URL 和网络白名单)
       401 = 数据库已连通,认证系统正常工作
       
       curl -X POST http://localhost:{BACKEND_PORT}/auth/login \
            -d '{"phone":"test_nonexistent","password":"wrong"}' → HTTP 401

  ⚠️ [V11+] 功能路径测试门(本次任务创建/修改了什么,就测什么)
       
       V1-V10 是固定基础清单,但无法覆盖每次任务新增的功能路径。
       必须额外回答:「本次任务新增或修改了哪些用户可感知的功能路径?」
       每增加一条功能路径,就必须增加至少一项端到端测试。
       
       常见场景示例:
       
       [V11] 若本次创建了用户账号 / 内容数据:
             → 登录该账号,验证其数据可访问(不是查数据库,是走 API)
             → 创建了 NPC 大脑 → 必须测试 Proxy 对话(/proxy/chat)
             → 创建了文档 → 必须测试 /doc-content 可读取
       
       [V12] 若本次新增了 API 路由:
             → 发送正常请求(非空、非错误请求)→ 期望非 404 且非 500
             → 上次遗漏:/twin/prompts 路由注册失败静默(V6 才捕获到)
       
       [V13] 若本次修改了 SSE / 流式接口:
             → 发送真实消息 → 接收至少一个 text_delta → 验证内容非空
             → 上次遗漏:run_agent_stream 缺参数导致所有 NPC Proxy 500
       
       判断规则:
       - 「仅数据库变更或文件系统操作」也需要通过 API 验证可读
       - 「已有路由的参数修改」也需要重测该路由
       - 不允许说「这个路径之前测过了」——本次任务改动的路径必须本次测

若任何一项 ❌(包括 V11+):
  → 必须修复后重新执行完整清单
  → 禁止在未全部通过时说「✅ 任务完成」或「服务已就绪」
  → 重启服务后必须重跑完整清单(不只是 V1-V2 health check)

Read the full file on GitHub · 1,017 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. 9d ago First seen · 1,017 lines · 61 tokens per session scan D 50045e3f5311

Subscribe to this mod's changes

role-DevOps is a skill published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 61 tokens to every session and 12,397 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 3 findings (sends data to an external url, reaches for credential files, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

define-slo-sli-sla

Establish Service Level Objectives (SLO), Service Level Indicators (SLI), and Service Level Agreements (SLA) with error budget tracking, burn rate alerts, and automated reporting using Prometheus and tools like Sloth or Pyrra. Use when defining reliability targets for customer-facing services, balancing feature…

pjt222/agent-almanac · 93 tokens

argo-cd

Use this skill when designing GitOps delivery workflows with Argo CD. This covers Application and AppProject CRDs, the App of Apps pattern, sync policies and waves, health checks, RBAC configuration, and integrating Argo CD into a multi-environment or multi-cluster strategy. The AI will act as a GitOps specialist who…

DongDuong2001/pudo-code-system · 0 tokens

azure-cloud-architect

Design Azure architectures for startups and enterprises. Use when asked to design Azure infrastructure, create Bicep/ARM templates, optimize Azure costs, set up Azure DevOps pipelines, or migrate to Azure. Covers AKS, App Service, Azure Functions, Cosmos DB, and cost optimization.

bestagentkits/agency-skills · 62 tokens

aws-serverless

Builds, deploys, manages, debugs, configures, and optimizes serverless applications on AWS using Lambda, API Gateway, Step Functions, EventBridge, and SAM/CDK. Covers cold starts, CORS debugging, event source mappings, troubleshooting, concurrency, SnapStart, Powertools, function URLs, EventBridge Scheduler, Lambda…

mouadja02/skills · 168 tokens

pipeline

Full CI pipeline — typecheck, lint, build, test, security scan, report.

Jkudjo/oh-my-cursor · 19 tokens

android-feature

Workflow for implementing a new Android feature, screen, fragment, activity, dialog, adapter, or enhancement in this XML/MVVM template. Use whenever the user asks to add, build, implement, or extend functionality — before writing any code. Covers planning, the MVVM/MVI skeleton, the Android configuration checklist…

orbitalsonic/AndroidPilot · 72 tokens