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 AlexK020908/infra-designer --skill frontendgit clone --depth 1 https://github.com/AlexK020908/infra-designerWrote 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/alexk020908/infra-designer/frontend)<a href="https://agentmods.dev/skills/alexk020908/infra-designer/frontend"><img src="https://agentmods.dev/badge/skills/alexk020908/infra-designer/frontend/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/skills/alexk020908/infra-designer/frontend"><img src="https://agentmods.dev/badge/skills/alexk020908/infra-designer/frontend.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 | $0.00000 | $0.00726 |
| Opus 5 | $0.00000 | $0.00363 |
| Sonnet 5 | $0.00000 | $0.00145 |
| Haiku 4.5 | $0.00000 | $0.00073 |
Grade A, and why
frontend 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 10d 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 — 20 lines — stays where its author put it; the contents beside it link to each section on GitHub.
web.frontend (Vercel / static)
The web frontend — and, for a Next.js app on Vercel, its serverless API routes too. It is its own node, NEVER bundled into backend compute (an App Runner/ECS service is the API, not the place to host the SPA). Config knobs: framework ("next" | "static" | "react"), target ("vercel" | "aws").
Choosing a target
target: "vercel"(default) — git-push deploys, global edge network, zero servers; the right default for Next.js/SSR and for most "I just want my app online" cases. Emits NO CloudFormation; deployed via the Vercel CLI (vercel deploy). For a full-stack Next.js app, this single node is the frontend AND the API.target: "aws"— a static build (SPA/SSG) served from a private S3 bucket via CloudFront with Origin Access Control. Use when the team wants everything inside AWS, or the frontend is purely static assets. Emits the bucket + distribution as one self-contained node; upload the build withaws s3 sync ./dist s3://<bucket>.
When AWS is overkill (the honest default)
- For a simple app — basic CRUD, a frontend, low/steady traffic, no correctness-critical or scaling requirements — a full AWS stack is over-engineering. The cheaper, lower-ops answer is a Vercel app (frontend + API routes) with a serverless Postgres (Neon/Supabase): git-push deploy, nothing to patch, generous free tiers. Surface this to the user instead of silently emitting App Runner + RDS + CloudFront.
- Reach for the AWS backend (
aws.apprunner.service/aws.ecs.service+aws.rds.postgres) when the app genuinely needs it: background workers, queues, VPC-private data stores, heavy/stateful infra, or strict cost/compliance control over the whole stack.
Connecting a Vercel frontend to data (the gotcha)
- A Vercel app CANNOT reach
aws.rds.postgresdirectly: RDS is VPC-private (the security floor forbids public RDS), and Vercel is external. The lint warns on this edge. Two clean options: (1) use a serverless Postgres with a public TLS endpoint + pooling (Neon/Supabase) — the natural pairing for Vercel; or (2) keep the DB behind an AWS backend (aws.apprunner.service) that the Vercel frontend calls over HTTPS. - The frontend's outgoing edge to a backend means it needs that backend's URL (e.g.
NEXT_PUBLIC_API_URL) — for Vercel, set it as a Vercel env var from the stack's outputs; for an AWS static build, bake it in at build time.
What ships with it
2 files 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.
- 10d ago First seen · 20 lines · 0 tokens per session scan A 8a7e70456417
frontend is a skill published in the GitHub repository AlexK020908/infra-designer (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 726 tokens. 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 2026-08-31.
Other skills, from other repositories
website-builder
Build an approved Vite/React/Tailwind plan, collect assets, verify static output, deploy to GitHub Pages, and emit metadata. Use for implementing tasks.md. Don't use for design review, planning, backend services, or unapproved specs.
azure-front-door
Expert knowledge for Azure Front Door development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring apex domains, rules engine, caching/streaming, Private Link…
azure-static-web-apps
Expert knowledge for Azure Static Web Apps development including troubleshooting, decision making, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when wiring SWA APIs to Azure DBs, configuring custom domains/DNS, auth/roles, CI/CD, or plan limits, and other Azure Static…
terraform-skill
Use when working with Terraform or OpenTofu - creating modules, writing tests (native test framework, Terratest), setting up CI/CD pipelines, reviewing configurations, choosing between testing approaches, debugging state issues, implementing security scanning (trivy, checkov), or making infrastructure-as-code…
terraform-cli-setup
A setup guide for installing and initializing Terraform, a tool for managing infrastructure from configuration files. It also covers basic provider downloads and mirror settings, but not cloud-provider credentials.
alicloud_cli
A Chinese-language reference for the Alibaba Cloud command-line tool, which lets developers manage Alibaba Cloud services from a terminal. It uses an offline copy of the documentation as its main source.