--- title: Neckbeard – a DevOps/platform/SRE plugin for your agent description: Neckbeard is a pre-alpha coding-agent plugin (built for Claude Code, Codex, Cursor and other SKILL.md-speaking agents) that turns an application into... canonical: https://daily.dev/posts/neckbeard-a-devops-platform-sre-plugin-for-your-agent-hdbhxocnk twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Neckbeard – a DevOps/platform/SRE plugin for your agent | daily.dev og:description: Neckbeard is a pre-alpha coding-agent plugin (built for Claude Code, Codex, Cursor and other SKILL.md-speaking agents) that turns an application into... og:url: https://daily.dev/posts/neckbeard-a-devops-platform-sre-plugin-for-your-agent-hdbhxocnk og:image: https://api.daily.dev/og/posts/HDBHxoCNk.png og:image:alt: Neckbeard – a DevOps/platform/SRE plugin for your agent og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Neckbeard – a DevOps/platform/SRE plugin for your agent **[Hacker News](https://daily.dev/sources/hn)** · 7 min read · 0 upvotes · 0 comments ## Summary Neckbeard is a pre-alpha coding-agent plugin (built for Claude Code, Codex, Cursor and other SKILL.md-speaking agents) that turns an application into reviewable cloud infrastructure plus a monthly cost estimate. It renders from a bundled catalog of tested OpenTofu modules across AWS, GCP, or Azure, with GitHub Actions or GitLab CI, and serverless containers or Kubernetes. The agent only analyzes and explains while planning, rendering, and validation remain deterministic code, so infrastructure is never invented by the model. It reports validation in three verdict levels (V0 static, V1 plan, V2 deploy) rather than implying unproven deployability, prices real reference workloads across six compute options via Infracost (from $77/mo on Cloud Run to over $800/mo on AKS), and names every unpriced or unsupported resource instead of force-fitting it into a module. Live deploy/update/rollback is proven on AWS and Azure serverless paths; GCP, GitLab, Kubernetes, and promotion/recovery drills are implemented but not yet exercised. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What does it cost per month to run an HTTP service with a worker, cron job, and Postgres on different cloud compute options? For the smallest tier reference app (HTTP service, worker, cron, Postgres) across all three environments, pricing via Infracost shows Cloud Run at $77/month, Container Apps around $98/month, ECS Fargate at $250/month, EKS at $396/month, GKE regional at $754/month, and AKS around $801/month. Container Apps and AKS figures are approximate because Infracost cannot yet price all their compute. _Developers comparing serverless versus Kubernetes costs can track pricing tools and findings like this on daily.dev._ ### How does an AI coding agent avoid generating broken or insecure infrastructure code? Infrastructure is generated by keeping agent reasoning and infrastructure rendering separate: the agent only reads the app, asks clarifying questions, and maps findings onto a pre-tested module catalog, while planning, rendering, and validation run as deterministic code producing a hash-verified blueprint.yaml lockfile. The agent never invents infrastructure directly, avoiding plausible-looking but subtly broken HCL. _Teams weighing AI-generated infra against hand-written IaC can follow approaches like this on daily.dev._ ### What is the difference between V0, V1, and V2 validation levels for infrastructure code? V0 is static validation (tofu validate, checkov policy, kubeconform) that runs without cloud credentials, V1 is an authenticated plan requiring cloud credentials, and V2 is deployment verification also requiring cloud credentials. Each level is reported as either PASSED or NOT EXERCISED, so static validation is never mistaken for proof that something actually deploys. _Engineers setting up staged infra validation pipelines can explore patterns like this on daily.dev._ ## Community take How the wider developer community reacted, aggregated from 1 discussion and 82 comments across hackernews (as of 2026-10-14). **TL;DR:** Reaction is mostly curious and lightly skeptical banter: people poke fun at the AI-generated readme tone and the project's joke-heavy branding, while a few raise genuine questions about whether this abstraction layer is needed over hand-written OpenTofu/Ansible or simpler/cheaper hosting like Hetzner. **Sentiment:** 25% positive · 55% mixed · 20% skeptical **The case for** - Some see value in giving LLMs opinionated architectural defaults they otherwise lack. - The deterministic, non-LLM-invented deployment approach addressed a cost-risk concern once pointed out. - The plugin/skill-with-tools pattern is seen as reducing token use and making agent behavior more predictable and testable. **The pushback** - Several found the AI-generated readme tone ('claudisms') off-putting and in need of editing. - Some questioned why a plugin is needed when existing tools (OpenTofu, Ansible) or just prompting an agent directly already work. - It's seen as aimed at small/medium cloud setups and not fitting complex enterprise networking/IAM landscapes. - Cheaper alternatives like Hetzner or self-hosted VPS were suggested as better value than the cloud reference pricing shown. **By community** - hackernews (mixed): Discussion mixes playful jokes about the name and readme tone with substantive but good-natured questions about the product's necessity and scope. **Hottest debate:** Whether this kind of opinionated plugin/abstraction is actually needed versus just using OpenTofu/Ansible directly or prompting an agent without it. **Open questions** - How well would this scale to complex enterprise environments with multi-layer IAM, networking, and landing zones? - Will cheaper providers like Hetzner or DigitalOcean be added as supported targets? **Highlights** > It does sound cool and as an infra nerd myself it reads sensible, I just don't see why I would want another abstraction layer between my cloud deployments being rolled out and the tf/hcl files that I maintain. Why would I want to install another interface between me, the planfile and the running environment? Genuine question > — [hangrybear666 on hackernews · 1 comments](https://news.ycombinator.com/item?id=50093318) > This seems like a great way to wake up and have your cloud spend skyrocket because an LLM assumed wrong. > — [llama052 on hackernews · 1 comments](https://news.ycombinator.com/item?id=50095014) > Why not opentofu and ansible? Version and run it. I don’t see why i need this. > — [janwirth on hackernews · 1 comments](https://news.ycombinator.com/item?id=50093072) > Why do you need a plug-in for this? You can just ask the agents to do all this stuff and it works fine in my experience. > — [jablongo on hackernews · 3 comments](https://news.ycombinator.com/item?id=50095070) > Can this be used with the ponytail skill? https://github.com/DietrichGebert/ponytail/tree/main > — [cousinbryce on hackernews · 1 comments](https://news.ycombinator.com/item?id=50093184) **Source threads** - [hackernews](https://news.ycombinator.com/item?id=50091794) · 51 points · 82 comments ## Similar posts on daily.dev - [AWS Just Turned "Deploy to AWS" Into a Five-Word Prompt](https://daily.dev/posts/aws-just-turned-deploy-to-aws-into-a-five-word-prompt-lryanigc1) · DevOps.com · 1 upvotes · 0 comments - [AWS Releases Aws-Bench to Evaluate Agents on Cloud Tasks](https://daily.dev/posts/aws-releases-aws-bench-to-evaluate-agents-on-cloud-tasks-0shw5bgj3) · InfoQ · 1 upvotes · 0 comments - [Agentic Infrastructure](https://daily.dev/posts/agentic-infrastructure-j6xmsieb9) · Vercel · 1 upvotes · 0 comments --- Tags: [#cloud](https://daily.dev/tags/cloud), [#golang](https://daily.dev/tags/golang), [#claude-code](https://daily.dev/tags/claude-code), [#iac](https://daily.dev/tags/iac), [#opentofu](https://daily.dev/tags/opentofu) [View this post on daily.dev](https://daily.dev/posts/neckbeard-a-devops-platform-sre-plugin-for-your-agent-hdbhxocnk) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Neckbeard – a DevOps/platform/SRE plugin for your agent","url":"https://daily.dev/posts/neckbeard-a-devops-platform-sre-plugin-for-your-agent-hdbhxocnk","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/neckbeard-a-devops-platform-sre-plugin-for-your-agent-hdbhxocnk"},"datePublished":"2026-10-14T21:07:53.395Z","dateModified":"2026-10-14T23:08:37.488Z","description":"Neckbeard is a pre-alpha coding-agent plugin (built for Claude Code, Codex, Cursor and other SKILL.md-speaking agents) that turns an application into...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/936f359c9e5908370154a4c698a8d6df?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/936f359c9e5908370154a4c698a8d6df?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Hacker News","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Hacker News","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/hn","url":"https://daily.dev/sources/hn"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/neckbeard-a-devops-platform-sre-plugin-for-your-agent-hdbhxocnk","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"cloud,golang,claude-code,iac,opentofu","timeRequired":"PT7M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hacker News","item":"https://daily.dev/sources/hn"},{"@type":"ListItem","position":3,"name":"Neckbeard – a DevOps/platform/SRE plugin for your agent"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/neckbeard-a-devops-platform-sre-plugin-for-your-agent-hdbhxocnk#faq","mainEntity":[{"@type":"Question","name":"What does it cost per month to run an HTTP service with a worker, cron job, and Postgres on different cloud compute options?","acceptedAnswer":{"@type":"Answer","text":"For the smallest tier reference app (HTTP service, worker, cron, Postgres) across all three environments, pricing via Infracost shows Cloud Run at $77/month, Container Apps around $98/month, ECS Fargate at $250/month, EKS at $396/month, GKE regional at $754/month, and AKS around $801/month. Container Apps and AKS figures are approximate because Infracost cannot yet price all their compute. Developers comparing serverless versus Kubernetes costs can track pricing tools and findings like this on daily.dev."}},{"@type":"Question","name":"How does an AI coding agent avoid generating broken or insecure infrastructure code?","acceptedAnswer":{"@type":"Answer","text":"Infrastructure is generated by keeping agent reasoning and infrastructure rendering separate: the agent only reads the app, asks clarifying questions, and maps findings onto a pre-tested module catalog, while planning, rendering, and validation run as deterministic code producing a hash-verified blueprint.yaml lockfile. The agent never invents infrastructure directly, avoiding plausible-looking but subtly broken HCL. Teams weighing AI-generated infra against hand-written IaC can follow approaches like this on daily.dev."}},{"@type":"Question","name":"What is the difference between V0, V1, and V2 validation levels for infrastructure code?","acceptedAnswer":{"@type":"Answer","text":"V0 is static validation (tofu validate, checkov policy, kubeconform) that runs without cloud credentials, V1 is an authenticated plan requiring cloud credentials, and V2 is deployment verification also requiring cloud credentials. Each level is reported as either PASSED or NOT EXERCISED, so static validation is never mistaken for proof that something actually deploys. Engineers setting up staged infra validation pipelines can explore patterns like this on daily.dev."}}]} ```