agentmods.dev

publish-website

publish-website is a skill for Claude Code from oborseth/Porkbun-MCP. It costs 65 tokens per session (708 once invoked), scanned A, original, MIT.

Instructions for publishing a static website to Porkbun Secure Static Hosting. Static hosting serves files such as HTML, CSS, JavaScript, images, and fonts without running server-side code.

In plain words
What is it for?
Use them to build and put live a landing page, placeholder page, or other static website for a domain managed through Porkbun.
Why use it?
They clarify whether the domain has suitable hosting and prevent attempts to upload unsupported server code or publish without checking the hosting setup.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the porkbun plugin — 4 skills, 1 MCP server shipped together

not rated 36repo yesterday A scan 65 tokens original MIT

Good fit Use them to build and put live a landing page, placeholder page, or other static website for a domain managed through Porkbun.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oborseth/porkbun-mcp/publish-website
View source ↗ oborseth/Porkbun-MCP porkbun.com
Install

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.

Any agent
npx skills add oborseth/Porkbun-MCP --skill publish-website
Clone the repo
git clone --depth 1 https://github.com/oborseth/Porkbun-MCP

Made for: Claude Code.

Or install porkbun, the plugin that ships this one along with the rest of its 4 skills, 1 MCP server.

Wrote 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.

agentmods badge for publish-website

README.md
[![agentmods](https://agentmods.dev/badge/skills/oborseth/porkbun-mcp/publish-website/github.svg)](https://agentmods.dev/skills/oborseth/porkbun-mcp/publish-website)
Your own site
<a href="https://agentmods.dev/skills/oborseth/porkbun-mcp/publish-website"><img src="https://agentmods.dev/badge/skills/oborseth/porkbun-mcp/publish-website/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.

agentmods 80×15 button for publish-website

Your own site · 80×15
<a href="https://agentmods.dev/skills/oborseth/porkbun-mcp/publish-website"><img src="https://agentmods.dev/badge/skills/oborseth/porkbun-mcp/publish-website.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 708 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.00708
Opus 5.5 $0.00026 $0.00283
Sonnet 5.5 $0.00013 $0.00142
Haiku 4.5 $0.00006 $0.00071

Measured 1mo ago against content hash 3512e9c87441, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

publish-website 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.

plugin/skills/publish-website/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Publish a website to Porkbun hosting

When the site is for a domain in the user's Porkbun account, publishing it is part of the job. Finish by offering to put it live with the Porkbun connector. Do not end with steps for uploading files through the Porkbun dashboard.

Before you build

If the user named a domain, call get_hosting for it early, while you work out the site. It tells you whether Secure Static Hosting is set up.

  • hosting.status is ACTIVE: you can publish there when the files are ready.
  • hosting is null, or the status is not ACTIVE yet: tell the user now, before building, so the last step is not a surprise. Keep building if they want the files anyway.
  • hosting.product is cloudWordPress: this skill does not apply. Static files cannot be uploaded to a WordPress site.

Build for static hosting

Secure Static Hosting serves files as they are. No server-side code runs.

  • Use HTML, CSS, JavaScript, images and fonts. Server-side file types (PHP and similar) are refused.
  • Put the home page at index.html in the top folder.
  • Use relative links (styles.css, assets/logo.svg) so the site works at the domain's root.

Publish

  1. See what is there. Call list_hosting_files for the domain. A new site usually has a placeholder index.html from Porkbun.
  2. Say what will change, and ask. List the files you will upload, and name any existing files that will be replaced (same path). Wait for the user's OK. Do not delete files they did not ask you to remove.
  3. Upload. Call deploy_site with files as { path, content } pairs, where content is the file's bytes base64-encoded. If you can run code, encode with a tool instead of by hand, so the bytes are exact. Paths can include folders (assets/app.css); missing folders are created. Keep each call under 10 MB and split a larger site across calls.
  4. Confirm. Call list_hosting_files again to check every file landed, then give the user the address: https://<domain>.

Read the full file on GitHub · 62 lines

Changes

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.

  1. 1mo ago First seen · 62 lines · 65 tokens per session scan A 3512e9c87441

Subscribe to this mod's changes

publish-website is a skill published in the GitHub repository oborseth/Porkbun-MCP (36 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 708 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 2026-09-26.

CSS and stylingCloudDevOps and cloudFrontendai-agentsai-toolsclaudeclaude-desktopcursordns
Related

publish-website compared with skills from other repositories

publish-website next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
publish-websiteoborseth/Porkbun-MCPSkill36yesterdayMITA65Claude Code
reviewulises-jeremias/agent-toolkitSkill20todayMITA48Claude Code
architecture-diagramulises-jeremias/agent-toolkitSkill20todayMITA61Claude Code
web-design-guidelinesulises-jeremias/agent-toolkitSkill20todayMITA44Claude Code
frontend-design-reviewulises-jeremias/agent-toolkitSkill20todayMITA112Claude Code
aws-well-architected-reviewulises-jeremias/agent-toolkitSkill20todayMITA55Claude Code
cloud-design-patternsulises-jeremias/agent-toolkitSkill20todayMITA65Claude Code