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 agentmods add skills/austinfox/claude-plugins/subdomain-deploynpx skills add austinfox/claude-plugins --skill subdomain-deploygit clone --depth 1 https://github.com/austinfox/claude-pluginsWrote 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/austinfox/claude-plugins/subdomain-deploy)<a href="https://agentmods.dev/skills/austinfox/claude-plugins/subdomain-deploy"><img src="https://agentmods.dev/badge/skills/austinfox/claude-plugins/subdomain-deploy.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 | $0.00155 | $0.03802 |
| Opus 5 | $0.00077 | $0.01901 |
| Sonnet 5 | $0.00031 | $0.00760 |
| Haiku 4.5 | $0.00015 | $0.00380 |
Grade A, and why
subdomain-deploy scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
After deploy, smoke-test against the **custom domain**, not the `*.vercel.app` URL — see Gotchas. If your local resolver hasn't picked up the new subdomain yet, force it via curl `--resolve`: How it starts
The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Personal Subdomain Deploy (austinfox.com)
Stand up a new personal project at <name>.austinfox.com on Vercel with the right access pattern and storage strategy for the project. This skill is for Austin's personal projects only — not client work, not company projects.
Non-Negotiables
These are the rules that distinguish this workflow from generic "deploy to Vercel":
- One Vercel project per subdomain. Never combine multiple personal projects into a single Vercel project, never use path-based routing across them. Each subdomain gets its own GitHub repo, its own Vercel project, its own env vars, its own analytics.
- Default stack: Bun + Vite + React 19 + TypeScript. Bun is the runtime/package manager; Vite is the dev server/bundler — they do different jobs and both are needed. Add Tailwind v4 (via
@tailwindcss/vite) when styling is non-trivial. Don't reach for Next.js for static personal projects. - Auth is custom Edge middleware, never Vercel's built-in Password Protection. Vercel's feature requires the Advanced Deployment Protection add-on (~$150/mo). The middleware patterns in
references/are no-ops when their env vars are unset, so they cost nothing during local dev. - Wildcard DNS is already set on Porkbun (
*.austinfox.com → cname.vercel-dns.com). New subdomains require zero DNS work —vercel domains addis sufficient. - Private GitHub repo by default. Personal projects are private unless the user explicitly says otherwise.
When to Use This Skill
Activate when the user's request implies creating a brand-new project on an austinfox.com subdomain. Strong signals:
- "deploy this" / "ship this" + the project is local-only and has no Vercel link yet
- "put it on austinfox.com" / "set up
<name>.austinfox.com" - "spin up a new personal project"
- Mentions of austinfox.com or a subdomain like
lettera.austinfox.com
Do NOT use this skill when:
- The project is already linked to a Vercel project — in that case use the generic
deploy-to-vercelskill. - The user wants to deploy to a non-austinfox.com domain — use the generic flow.
- The user is deploying a redeploy / preview / hotfix to an existing project — use the generic flow.
What ships with it
3 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.
- 4d ago First seen · 250 lines · 155 tokens per session scan A 63600a5759eb
subdomain-deploy is a skill published in the GitHub repository austinfox/claude-plugins (4 stars, last pushed 1mo ago), licensed MIT. It adds 155 tokens to every session and 3,802 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
pulumi-migrate-from-discovered-stack
Migrate a CloudFormation or ARM stack into a Pulumi stack, sourced from a stack that Pulumi Cloud's Discovery feature has already found and exposed via the discovered-stacks API. Load this skill when the user has a discovered stack in Pulumi Cloud and wants to bring its resources under Pulumi management. Do NOT load…
pulumi-component
Guide for authoring Pulumi ComponentResource classes. Use when creating reusable infrastructure components, designing component interfaces, setting up multi-language support, or distributing component packages.
pulumi-overview
Use this skill for any task that creates, modifies, inspects, or destroys cloud infrastructure or SaaS configuration, from one-off CLI operations to full multi-resource projects, across providers in the Pulumi ecosystem. A typical project spans many providers (AWS or Azure or GCP, Kubernetes, Cloudflare, Auth0…
provider-upgrade
Upgrade any Pulumi provider to a newer version and reconcile the resulting diff. Use when users want to upgrade or update a provider (including editing package.json, requirements.txt, pyproject.toml, go.mod, or Pulumi.yaml to bump a provider SDK), check for breaking changes before or during an upgrade, fix resources…
pulumi-best-practices
Load when the user is writing, reviewing, or debugging Pulumi TypeScript/Python programs; asks about Output or apply() usage; wants to create ComponentResource classes; needs to refactor resources without destroying them (aliases); is setting up secrets or config; or is configuring a pulumi preview/up CI workflow.…
pulumi-arm-to-pulumi
Convert or migrate Azure ARM (Azure Resource Manager) templates, Bicep templates, or code to Pulumi, including importing existing Azure resources. This skill MUST be loaded whenever a user requests migration, conversion, or import of ARM templates, Bicep templates, ARM code, Bicep code, or Azure resources to Pulumi.