Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mhrsdev/AI-Agent-Skills-Librarynpx agentmods add skills/mhrsdev/ai-agent-skills-library/05-website-rebuildWrote 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/mhrsdev/ai-agent-skills-library/05-website-rebuild)<a href="https://agentmods.dev/skills/mhrsdev/ai-agent-skills-library/05-website-rebuild"><img src="https://agentmods.dev/badge/skills/mhrsdev/ai-agent-skills-library/05-website-rebuild/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/mhrsdev/ai-agent-skills-library/05-website-rebuild"><img src="https://agentmods.dev/badge/skills/mhrsdev/ai-agent-skills-library/05-website-rebuild.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 | $0.00206 | $0.04309 |
| Opus 5 | $0.00103 | $0.02155 |
| Sonnet 5 | $0.00041 | $0.00862 |
| Haiku 4.5 | $0.00021 | $0.00431 |
Grade A, and why
website-rebuild 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 7d 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 — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Full Website Rebuild Agent
Take an existing website URL and rebuild it from scratch into an extraordinary, production-ready website. The result should look like a $20,000+ agency build — visually stunning, conversion-optimized, fully accessible, and SEO-complete.
How This Skill Works
This skill runs 14 phases in strict order. Each phase produces documentation before moving on. Do not skip or reorder phases. The user provides a URL and you do the rest.
Input: A website URL (the site to rebuild) Output: A live Vercel-deployed website + GitHub repo + 11 documentation files
Tech Stack — Exact. Do Not Deviate.
Framework: Astro 5.x — static site generator, zero JavaScript by default, perfect for SEO.
Styling: Tailwind CSS v4 (via Vite plugin)
Images: Astro <Image> component from astro:assets (built-in optimization, WebP/AVIF)
SEO: @astrojs/sitemap integration + manual JSON-LD
View Transitions: Astro View Transitions (built-in, zero JS page transitions)
Blog/Content: Astro Content Collections with MDX. Frontmatter: title, date, description, author, tags, featuredImage.
Deployment: Vercel via GitHub (push to main = auto-deploy)
Package Manager: npm (not pnpm, not yarn — npm only)
Linting: ESLint + Prettier from the start
Initialization — Run These Exact Commands
npm create astro@latest <project-name> -- --template minimal --no-install
cd <project-name>
npm install
npx astro add tailwind --yes
npx astro add sitemap --yes
npx astro add mdx --yes
npm install -D prettier
That's it. The project is ready.
If Something Fails During Build
Fix the code. Do NOT:
- Switch Node versions
- Switch package managers
- Reinstall the framework
- Add React or any other UI framework unless specifically needed for an interactive tool (Phase 11b)
- Change the project structure
Astro File Structure
src/
layouts/
BaseLayout.astro ← shared HTML shell, <head>, nav, footer
BlogPostLayout.astro ← blog post template
pages/
index.astro ← homepage
about.astro ← about page
services.astro ← services page
contact.astro ← contact page
blog/
index.astro ← blog listing
[...slug].astro ← dynamic blog post pages
tools/ ← interactive tools (Phase 11b)
404.astro ← custom 404
components/
Header.astro ← navigation
Footer.astro ← footer
Hero.astro ← hero section
... ← section components as needed
content/
config.ts ← content collection schema
blog/
*.mdx ← blog posts
styles/
global.css ← @import "tailwindcss"; + CSS custom properties
assets/
images/ ← optimized images (processed by Astro)
public/
images/ ← static images (served as-is)
favicon.svg
robots.txt
What ships with it
6 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.
- 7d ago First seen · 326 lines · 206 tokens per session scan A d88b85b1675a
website-rebuild is a skill published in the GitHub repository mhrsdev/AI-Agent-Skills-Library (6 stars, last pushed 2mo ago), licensed MIT. It adds 206 tokens to every session and 4,309 once invoked, about $0.0010 per session on Opus 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 2026-09-03.
Other skills, from other repositories
mockup-extraction
Extract reusable components from approved HTML mockups during implementation. Identifies patterns, maps CSS to Tailwind, and populates prototype-patterns.md for visual fidelity. Use at start of /implement for UI-first features.
shadcn-integration
Integration guide for shadcn/ui components with OKLCH design tokens. Use when setting up shadcn, customizing themes, or adding components to Next.js projects. Auto-trigger on /init --tokens --shadcn flag.
web-clone
URL-driven website cloning with visual + functional verification.
skill-premium-web-experience
Use for creating, redesigning, or transforming websites into premium, cinematic, conversion-focused web experiences with visual research, storytelling, scroll-driven interaction, responsive design, motion, performance, accessibility, and visual QA.
skill-frontend-ux-guardrails
Use as a frontend UX quality gate for responsive behavior, overflow, accessibility, interaction usability, touch targets, typography, layout stability, mobile behavior, focus states, reduced motion, and final visual validation.
skill-impeccable
Orquestra melhorias de frontend inspiradas no Impeccable a partir de pedidos conversacionais de design, UX, acessibilidade, responsividade, tipografia, layout, cor, motion, clareza, hardening e polish.