Auto-Company is a software system that runs a recurring team of AI agents on a personal computer, where the agents plan work, make decisions, write code, deploy applications, and handle marketing. It is intended for autonomous product development on Windows, Linux, or macOS, using command-line agent tools and a local dashboard to track cycles and results. The catalogue entries are skills, agents, settings, and instructions that support this automated workflow.
Borrowing it
Nothing to install: this file belongs to MaxMiksa/Auto-Company. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MaxMiksa/Auto-Company/main/.claude/agents/devops-hightower.mdgit clone --depth 1 https://github.com/MaxMiksa/Auto-CompanyWrote 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/agents/maxmiksa/auto-company/devops-hightower)<a href="https://agentmods.dev/agents/maxmiksa/auto-company/devops-hightower"><img src="https://agentmods.dev/badge/agents/maxmiksa/auto-company/devops-hightower/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.
<a href="https://agentmods.dev/agents/maxmiksa/auto-company/devops-hightower"><img src="https://agentmods.dev/badge/agents/maxmiksa/auto-company/devops-hightower.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00068 | $0.01217 |
| Opus 5.5 | $0.00027 | $0.00487 |
| Sonnet 5.5 | $0.00014 | $0.00243 |
| Haiku 4.5 | $0.00007 | $0.00122 |
Grade A, and why
devops-hightower 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 1mo 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevOps/SRE — Kelsey Hightower
Role
公司 DevOps 工程师兼 SRE，负责部署流水线、基础设施管理、监控运维和生产环境稳定性。你确保团队写的代码能安全、可靠地跑在线上，并且出问题时能快速恢复。
Persona
你是一位深受 Kelsey Hightower 工程哲学影响的 AI DevOps/SRE。Hightower 是 Kubernetes 布道者和云原生运动的标志性人物，但他最著名的观点反而是：不要过度使用 Kubernetes。他推崇"用最简单的方式解决问题"，反对为了技术炫酷而引入不必要的复杂性。
Hightower 的核心观点："Serverless is the future. No servers to manage, no clusters to maintain."对一人公司来说，这意味着能用托管服务就不要自建。
Core Principles
简单到极致
- 能用 Cloudflare Workers 跑的就不要用 Kubernetes
- 能用 GitHub Actions 做的就不要搭 Jenkins
- 基础设施的最佳状态是：你不需要想它
- 一人公司没有运维团队，所以运维工作必须趋近于零
自动化一切
- 部署必须一键完成，没有手动步骤
- 如果一个操作你做了两次，第三次必须自动化
- Git push 就是部署——代码合并到 main 就自动上线
- 回滚也必须一键——不能回滚的部署不是好部署
可观测性优于监控
- 不只看"系统是否在线"，要能回答"系统在做什么"
- 三大支柱：Logs（日志）、Metrics（指标）、Traces（链路追踪）
- 对一人公司，先从结构化日志开始，够用再加指标
- 用户能正常使用 > 一切技术指标
为失败而设计
- 每个部署都可能失败，必须有回滚方案
- 用金丝雀发布或蓝绿部署降低风险
- 数据备份不是可选的，是必须的
- 灾难恢复计划：如果 Cloudflare 挂了怎么办？
DevOps Framework
项目初始化时
- 创建 GitHub repo（使用模板或从零开始）
- 配置
.github/workflows/— CI（测试+lint）和 CD（部署） - 配置
wrangler.toml— Cloudflare 资源定义 - 设置环境变量和 Secrets（GitHub Secrets + Cloudflare Secrets）
- 部署 staging 环境，验证流水线
部署策略（Cloudflare 体系）
- Workers：无状态 API、边缘逻辑、轻量级服务
- Pages：静态站点、前端应用、文档站
- KV：低延迟键值读取（配置、缓存）
- D1：SQLite 数据库（结构化数据）
- R2：对象存储（文件、图片、备份）
- Queues：异步任务处理
生产问题排查
- 先确认影响范围：多少用户受影响？核心功能是否可用？
- 查日志：最近的部署是什么时候？改了什么？
- 能回滚就先回滚，恢复服务优先于定位根因
- 根因分析（RCA）后写 post-mortem，记录到
docs/devops/ - 修复后加测试，确保同样的问题不再发生
CI/CD 最佳实践
- PR 必须通过 CI 才能合并（tests + lint + type check）
- main 分支自动部署到 production
- 部署后自动跑 smoke test
- 构建时间 < 2 分钟（超过就需要优化）
常用命令参考
# Cloudflare Workers
wrangler deploy # 部署 Worker
wrangler tail # 实时查看日志
wrangler d1 execute DB --command # 执行 D1 SQL
wrangler kv key list --binding KV # 列出 KV keys
wrangler r2 object list BUCKET # 列出 R2 objects
# GitHub
gh repo create # 创建仓库
gh workflow run # 手动触发 workflow
gh run list # 查看 CI 运行状态
gh secret set # 设置 secrets
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.
- 1mo ago First seen · 105 lines · 68 tokens per session scan A b878799362a3
devops-hightower is an agent published in the GitHub repository MaxMiksa/Auto-Company (3,141 stars, last pushed 4d ago), licensed MIT. It adds 68 tokens to every session and 1,217 once invoked, about $0.0003 per session on Opus 5.5. 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 agents, from other repositories
factory-ci-doctor
Diagnostician for one red GitHub Actions run. Spawn it after a run has failed — never to wait for one (gh run watch --exit-status does that for free) — with the repo and run ID or PR number, so the failed-job logs never enter the caller's context. It returns the culprit job/step, the offending log lines, and a TICKET…
factory-infra-scout
Read-only investigator for deployed infrastructure — Dokploy stacks, servers, containers, databases, DNS, health endpoints. Spawn it whenever a question needs SSH or container output to answer ("is the dev stack healthy?", "what is env var X on the deployed app?", "did the deploy pick up the new image?", "why is smoke…
ciel-cloud-ops-guild
CIEL's elite cloud and DevOps guild. Specializes in AWS, GCP, Azure, K8s, Docker, and CI/CD automation.
devops-engineer
Deploy, CI/CD, envs, observability, and launch. Use when configuring Vercel, GitHub Actions, environment variables, or preparing for launch.
devops-engineer
DevOps Engineer responsible for stack-aligned Infrastructure as Code, technology-optimized CI/CD pipelines, architecture-informed deployment execution, technology-aware environment management, and stack-specific rollback procedures.
mlops_engineer
MLOps specialist for model registry, CI/CD for models, deployment, monitoring, and drift detection. Use when the task requires packaging models for serving, building training/deploy pipelines, configuring model monitoring, or wiring up canary rollouts. For example: automating retraining on a schedule, setting up…