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 skills add huangwb8/skills --skill devops-specialistgit clone --depth 1 https://github.com/huangwb8/skillsWrote 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.
[](https://agentmods.dev/skills/huangwb8/skills/devops-specialist)<a href="https://agentmods.dev/skills/huangwb8/skills/devops-specialist"><img src="https://agentmods.dev/badge/skills/huangwb8/skills/devops-specialist.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.01307 |
| Opus 5 | $0.00028 | $0.00654 |
| Sonnet 5 | $0.00011 | $0.00261 |
| Haiku 4.5 | $0.00006 | $0.00131 |
Grade A, and why
devops-specialist 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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevOps Specialist - DevOps 与运维专家
何时使用
- 需要搭建/改造 CI/CD(GitHub Actions / GitLab CI 等)
- 需要容器化、镜像瘦身、多阶段构建、非 root 运行
- 需要编排(Docker Compose / Kubernetes)
- 需要 IaC(Terraform/Ansible)或环境一致性治理
- 需要监控告警/日志/健康检查/发布回滚策略
输入
- 目标环境:本地 / 云 / K8s / 传统服务器
- 运行约束:端口、CPU/内存、可用性目标、合规要求
- 构建/测试现状:语言、包管理、测试命令、产物形式
- 机密策略:Secrets 来源与注入方式(严禁写入仓库)
输出
- 最小可用的交付路径:构建 → 测试 → 发布(含回滚)
- 关键配置文件(按需):CI 工作流、Dockerfile、Compose、K8s manifests、IaC
- 可观测性骨架:健康检查、日志字段、指标与告警入口
工作流(建议顺序)
-
基线盘点
- 现有构建/测试命令是什么?是否可在干净环境复现?
- 产物是什么?(wheel/jar/binary/image)
-
CI/CD 最小闭环
- 先做到:每次提交可自动构建 + 运行核心测试
- 再做到:产物发布(制品库/镜像仓库)+ 部署(环境隔离)
-
容器化与运行时安全
- 多阶段构建、最小基础镜像、
.dockerignore - 非 root 用户运行、只暴露必要端口、read-only filesystem(可选)
- 多阶段构建、最小基础镜像、
-
编排与配置管理
- 小规模:Compose
- 中大型/多环境:Kubernetes(Deployment/Service/Ingress/ConfigMap/Secret)
-
IaC 与环境一致性
- Terraform 管资源,Ansible 管配置(按项目选择)
- 避免“手工改线上”造成不可追溯漂移
-
可观测性与运维
- 健康检查(liveness/readiness)
- 结构化日志(含 request_id/trace_id)
- 指标与告警(先覆盖关键路径)
安全与可靠性硬门槛
- 不在仓库中写入密钥/Token/证书
- 部署必须可回滚(版本化产物 + 回滚指令/策略)
- 失败必须显式(CI fail-fast;部署失败要能定位原因)
- 默认最小权限(CI 权限、云权限、K8s RBAC)
约束
公共硬约束
本块由 docs/templates/skill-common-constraints.md 统一维护;每个 SKILL.md 的 ## 约束 必须逐字同步本块,不得在副本中改写公共规则。
- 任务需要落盘时,使用唯一的
./.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/根目录;共享材料放入shared/,Skill 专属材料放入该 Skill 的input/、output/、log/。 - 正式交付物、源代码和正式计划按项目约定保存,不写入任务工作区;未经授权不覆盖、删除、迁移或远程写入。
- 项目维护变更检查 BAC 可用性并记录需求、AI 产出、工具结果、文件改动和验证摘要;BAC 只做过程审计,不替代署名、责任或合规判断。
- 不记录 API Key、访问令牌、密码、Cookie、环境/凭据文件、私有 Prompt、身份信息、本地用户名、主机名或不必要的大体积原始数据。
- 文件路径必须规范化并限制在授权项目范围内;外部 URL、子进程和网络访问遵循最小权限,防止路径遍历、SSRF 和命令注入。
- Skill 版本唯一记录在自身
config.yaml:skill_info.version;公开 API、协议、目录或配置变更同步文档与CHANGELOG.md。 bensz-collect-bugs是一个 Agent Skill;仅将 Bensz Agent Skill 或 Bensz 基础设施本身的设计缺陷交给它。先脱敏写入~/.bensz-skills/bugs/,当前任务不中断,只有用户明确要求才公开上报,禁止直接修改用户已安装的 Skill 源码。
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.
- yesterday Changed · +8 lines 9ca58d5b2fed
- 7d ago First seen · 91 lines · 55 tokens per session scan A 1052869acdd7
devops-specialist is a skill published in the GitHub repository huangwb8/skills (48 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 1,307 once invoked, about $0.0003 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-engineer
Creates Dockerfiles, configures CI/CD pipelines, writes Kubernetes manifests, and generates Terraform/Pulumi infrastructure templates. Handles deployment automation, GitOps configuration, incident response runbooks, and internal developer platform tooling. Use when setting up CI/CD pipelines, containerizing…
deploy
Elixir/Phoenix deployment patterns — Dockerfile, fly.toml, runtime.exs, mix release, rel/ overlays. Use when configuring Fly.io, Docker, CI/CD, health checks, or production migrations.
securing-cloud-and-supply-chain
A guide to protecting cloud infrastructure and the software supply chain, the systems and dependencies used to build and deliver software.
provisioning-infrastructure
Cloud-native infrastructure knowledge reference covering Kubernetes, Helm, Kustomize, Operators, CRDs, GitOps (ArgoCD, Flux), and IaC (Terraform, Pulumi, CDK). Use when provisioning infrastructure, managing clusters, or working with GitOps workflows.
appveyor-automation
Automate Appveyor tasks via Rube MCP (Composio). Always search tools first for current schemas.
buildkite-automation
Automate Buildkite tasks via Rube MCP (Composio). Always search tools first for current schemas.