Mpa Orchestrator logo

Mpa Orchestrator

Community
roedyrustam
mpa-orchestrator

Multi-Page Application (MPA) architecture and asset orchestration / Arsitektur Multi-Page Application (MPA) dan orkestrasi aset.

Overview

Publisherroedyrustam
Repositoryvibes-plug
Skill namempa-orchestrator
Stars
117
Forks
27
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by roedyrustam on GitHub. Read the source before you install it.

Installation

Install the Mpa Orchestrator AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/roedyrustam/vibes-plug/tree/main/skills/mpa-orchestrator
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/roedyrustam/vibes-plug.git /tmp/vibes-plug
mkdir -p .claude/skills
cp -r /tmp/vibes-plug/skills/mpa-orchestrator .claude/skills/mpa-orchestrator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mpa Orchestrator in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Mpa Orchestrator on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Mpa Orchestrator is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Multi-Page Application (MPA) Orchestrator (2026 Edition)

English | Bahasa Indonesia


English

Orchestration & Integration

Connects and orchestrates with relevant domain skills:

  • modern-web-guidance: HTML5/CSS standards, modern browser APIs, and accessibility guidelines.
  • htmx-hypermedia-expert: Hypermedia-Driven Applications (HDA) and HTML-over-the-wire swaps.
  • astro-framework-expert: Islands Architecture and zero-JS-by-default static rendering.
  • design-system-architect: Server-rendered HTML templates and consistent component tokens.
  • tailwind-expert: Tailwind CSS v4 styling across server templates.
  • ui-ux-pro-max: Multi-page layout hierarchy, editorial typography, and breadcrumb navigation.
  • visual-ui-auditor: Multimodal vision auditing of server-rendered pages and standard boilerplate pages.
  • anti-slop: Anti-slop MPA layouts, zero incomplete placeholder views, and strict adherence to mandatory standard pages.
  • seo: Comprehensive technical and on-page SEO optimization.

Description

A structured approach for building and orchestrating Multi-Page Application (MPA) architectures within a single repository. Acts as an orchestrator connecting MPA principles with specialized skills (like mvc-expert, saas-multi-tenant, senior-frontend) to deliver cohesive, server-rendered applications. In 2026, MPAs are increasingly built with Astro 5 for content-heavy sites or traditional server frameworks (Laravel, Django, Go) augmented with HTMX 2 or Alpine.js for interactivity.

Core MPA Principles in a Single Repository

  1. Centralized Architecture: Frontend views, backend logic, and routing in a unified codebase — simplifies deployment and reduces cognitive load.
  2. Server-Side Routing & Rendering: A Front Controller intercepts requests, fetches data, and renders complete HTML per route. Options in 2026:
    • Astro 5: Best for content-heavy sites — renders to static HTML by default, hydrates islands on demand.
    • Next.js 15 (Pages Router): Traditional MPA feel with React components.
    • Backend-driven: Laravel/Django/Gin templates rendered server-side.
  3. Islands Architecture (Astro 5):
    • Render 100% static HTML for non-interactive content.
    • Use client:load, client:idle, or client:visible directives to hydrate interactive islands only when needed.
    • Supports React, Vue, Svelte, Solid, or vanilla JS islands side by side.
  4. HTMX 2 — HTML-First Interactivity:
    • Enhance any server-rendered page with partial HTML swaps without writing JavaScript.
    • Works with any backend — Django, Laravel, Go, Node.js.
    • hx-get, hx-post, hx-target, hx-swap for declarative AJAX.
  5. Shared UI Ecosystem:
    • Maintain a layouts/ directory for base HTML structures.
    • Maintain a components/ directory for reusable UI elements.
  6. Asset Management: Centralize static assets in public/. Implement cache-busting for production.
  7. Session-based State: Use secure HTTP-only cookies and server sessions for auth, tenant context, and flash messages.

Bundler & Multi-Entry Configuration

In a modern frontend context (especially for MPAs), define multiple entry points in the bundler configuration. This generates separate, optimized JavaScript and CSS bundles for the public site versus the complex admin dashboard, drastically reducing overall payload sizes for general users.

Implementation Checklist:

  • Create separate HTML entry points in the root/public directory (e.g., index.html, admin.html).
  • Configure the frontend bundler (Vite/Webpack) to output multiple bundles.
  • Set up server-side routing (Nginx or Node.js) to serve the correct entry HTML based on the URL path.
  • Ensure shared components and utilities are properly tree-shaken and split into common chunks.

Example: Vite Config for Multiple Entries

javascript
import { defineConfig } from 'vite';
import { resolve } from 'path';

export default defineConfig({
  build: {
    rollupOptions: {
      input: {
        main: resolve(__dirname, 'index.html'),
        admin: resolve(__dirname, 'admin.html'),
        app: resolve(__dirname, 'app.html')
      }
    }
  }
});

Framework Selection Guide

NeedRecommended Stack
Content site / Blog / DocsAstro 5 + MDX + Tailwind v4
Full server-rendered app (PHP)Laravel 11 + Livewire 3 / Alpine.js
Full server-rendered app (Python)Django 5 + HTMX 2 + Alpine.js
Full server-rendered app (Go)Templ + HTMX 2 + Tailwind v4
React MPA with SSRNext.js 15 Pages Router or App Router

Orchestration Guidelines

  • With htmx-hypermedia-expert: MUST execute FIRST before any HTML/CSS task to ensure modern frontend standards.
  • With mvc-expert: Enforce MVC pattern — Controllers handle logic, Views handle rendering.
  • With saas-multi-tenant: Integrate tenant identification in core routing middleware — every page load initializes tenant_id context securely.
  • With senior-frontend / ui-ux-pro-max: Enhance with Alpine.js for reactive UI or HTMX 2 for HTML-driven partial updates — no heavy client-side bundles.
  • With seo: Maximize MPA's inherent SEO advantages — every page returns fully populated HTML, correct meta tags, and Schema.org JSON-LD on initial load.
  • vs spa-orchestrator: Choose MPA when SEO is critical, data is mostly read-heavy, and complex client-side state is not required. Choose SPA when the app is highly interactive and session-based (like dashboards).

Trigger Conditions

  • Building a web application using the Multi-Page Application (MPA) approach in a single repository.
  • Refactoring or migrating an existing app to a centralized MPA architecture.
  • Building content sites, marketing pages, or SEO-critical applications.
  • Using Astro 5 for static or content-heavy sites with optional interactive islands.
  • Adding interactivity to server-rendered pages with HTMX 2 without a full SPA rewrite.

Progressive Enhancement View-Transition Header Helper (TypeScript)
typescript
export function buildMpaDocumentHeaders(cacheMaxAgeSeconds = 60): Record<string, string> {
  return {
    'Content-Type': 'text/html; charset=utf-8',
    'Cache-Control': `public, max-age=${cacheMaxAgeSeconds}, stale-while-revalidate=300`,
    'Vary': 'HX-Request, Accept-Encoding',
    'X-Content-Type-Options': 'nosniff'
  };
}

Sovereign Execution, Token Efficiency & Invariants

DimensionSovereign Mandate & Deterministic Contract
Frontier Model CascadeMedium / High (GPT-5.6 Sol Medium, Gemini 4 Argon, Claude Sonnet 5.5 High, Grok 4.7 High Fast)
Availability FallbackGemini 4 Argon/Pro -> Gemini 3.8 Flash; Claude Opus 5.5 -> Claude Opus 4.6 (Zero unhandled missing-model errors)
KV-Cache & Token ProtocolPin static instructions & schemas at prompt prefix (kv-cache-prefix-optimizer); pass surgical CONTEXT_MAP.md slices (<250 tokens/call) during Swarm Fan-Out
SaaT CLI & MCP DispatchCLI: vibes skill exec mpa-orchestrator <audit|eval|verify|generate|blueprint> / MCP: vibes_skill_dispatch, vibes_ast_query, vibes_compile_cache, vibes_optimize_budget, vibes_verify_gate
NFR & Anti-Slop InvariantsP99 API Gateway Latency < 85ms, OpenAPI 3.1 / TypeSpec strict schema parity, RFC 9457 Problem Details error contracts, Idempotency-Key enforcement; 100% complete zero-placeholder output verified via node scripts/check-anti-slop.js --strict


Bahasa Indonesia

Integrasi Orkestrasi

Terhubung dan mengorkestrasi skill domain yang relevan:

  • modern-web-guidance: Standar HTML5/CSS, API browser modern, dan pedoman aksesibilitas.
  • htmx-hypermedia-expert: Hypermedia-Driven Applications (HDA) dan pertukaran HTML-over-the-wire.
  • astro-framework-expert: Islands Architecture dan rendering statis zero-JS-by-default.
  • design-system-architect: Template HTML server-rendered dan token komponen konsisten.
  • tailwind-expert: Styling Tailwind CSS v4 di seluruh template server.
  • ui-ux-pro-max: Hierarki tata letak multi-page, tipografi editorial, dan navigasi breadcrumb.
  • visual-ui-auditor: Audit visual multimodal untuk halaman server-rendered dan halaman standar wajib.
  • anti-slop: Layout MPA anti-slop, nol tampilan placeholder tidak lengkap, kepatuhan halaman standar wajib.
  • seo: Optimasi SEO teknis dan on-page menyeluruh.

Deskripsi

Pendekatan terstruktur untuk membangun dan mengorkestrasi arsitektur Multi-Page Application (MPA) di dalam satu repositori. Bertindak sebagai orkestrator yang menghubungkan prinsip MPA dengan skill spesialis lain untuk menghasilkan aplikasi server-rendered yang kohesif dan modern. Di 2026, MPA semakin banyak dibangun dengan Astro 5 untuk situs konten-berat atau framework server tradisional yang diperkuat dengan HTMX 2 atau Alpine.js.

Prinsip Inti MPA

  1. Arsitektur Terpusat: View frontend, logika backend, dan routing dalam satu codebase.
  2. Routing & Rendering Sisi Server: Front Controller menangkap permintaan, mengambil data, dan me-render HTML lengkap per rute.
  3. Islands Architecture (Astro 5): Render HTML statis 100% secara default, hidrate island interaktif hanya saat diperlukan.
  4. HTMX 2 — Interaktivitas HTML-First: Tingkatkan halaman server-rendered dengan pertukaran HTML parsial tanpa menulis JavaScript.
  5. Ekosistem UI Bersama: Direktori layouts/ dan components/ untuk elemen UI yang dapat digunakan kembali.
  6. State Berbasis Session: Cookie HTTP-only dan session sisi server untuk autentikasi dan konteks tenant.

Konfigurasi Bundler & Multi-Entry

Dalam konteks frontend modern (khususnya untuk MPA), tentukan beberapa entry points pada konfigurasi bundler. Ini akan menghasilkan bundel JavaScript dan CSS yang terpisah dan optimal antara situs publik dan dashboard admin, sehingga secara drastis mengurangi ukuran payload bagi pengguna umum.

Checklist Implementasi:

  • Buat titik entri HTML terpisah di direktori utama/publik (misal: index.html, admin.html).
  • Konfigurasi bundler frontend (Vite/Webpack) untuk menghasilkan multiple bundle.
  • Siapkan routing di sisi server (Nginx atau Node.js) untuk menyajikan HTML entri yang benar berdasarkan path URL.
  • Pastikan komponen dan utilitas yang dipakai bersama dioptimalkan (tree-shaking) dan dipisah ke dalam common chunks.

Panduan Pemilihan Framework

KebutuhanStack yang Direkomendasikan
Situs konten / Blog / DocsAstro 5 + MDX + Tailwind v4
Aplikasi server-rendered (PHP)Laravel 11 + Livewire 3 / Alpine.js
Aplikasi server-rendered (Python)Django 5 + HTMX 2 + Alpine.js
Aplikasi server-rendered (Go)Templ + HTMX 2 + Tailwind v4
React MPA dengan SSRNext.js 15 Pages Router atau App Router

Panduan Orkestrasi

  • Dengan modern-web-guidance: WAJIB dieksekusi PERTAMA KALI sebelum tugas HTML/CSS untuk memastikan standar frontend modern.
  • Dengan mvc-expert: Pastikan MPA mengikuti pola MVC secara ketat.
  • Dengan saas-multi-tenant: Integrasikan identifikasi tenant di middleware routing inti.
  • Dengan senior-frontend / ui-ux-pro-max: Tingkatkan dengan Alpine.js atau HTMX 2 untuk interaksi tanpa bundle berat.
  • Dengan seo: Setiap halaman mengembalikan HTML penuh, tag meta, dan JSON-LD terisi saat load awal.
  • vs spa-orchestrator: Pilih MPA saat SEO kritis dan data kebanyakan read-heavy. Pilih SPA saat aplikasi sangat interaktif seperti dashboard.

Kondisi Pemicu

  • Membangun aplikasi web dengan pendekatan MPA dalam satu repositori.
  • Refaktor atau migrasi aplikasi yang ada ke arsitektur MPA terpusat.
  • Membangun situs konten, halaman marketing, atau aplikasi kritis SEO.
  • Menggunakan Astro 5 untuk situs statis atau konten-berat dengan island interaktif opsional.
  • Menambahkan interaktivitas ke halaman server-rendered dengan HTMX 2 tanpa menulis ulang ke SPA.

📄 Standard Pages Mandate (CRITICAL)

MANDATORY: Whenever you are building a new application, landing page, or website, you MUST automatically create the following standard pages:

  1. About Page (/about)
  2. Profile Page (/profile)
  3. Contact Page (/contact)
  4. Terms of Reference / Terms of Service (/terms)
  5. Privacy Policy (/privacy-policy)

These pages must be generated with standard boilerplate content that can later be customized to fit the specific application. Do not wait for the user to ask for them; they are a strict requirement for all web projects. / WAJIB: Otomatis buatkan halaman standar (About, Profile, Contact, Terms, Privacy Policy) pada setiap pembuatan aplikasi/website baru dengan konten boilerplate yang bisa disesuaikan nanti.

Matriks Eksekusi Berdaulat, Efisiensi Token & Invarian

DimensiMandat Berdaulat & Kontrak Deterministik
Kaskade Model FrontierMedium / High (GPT-5.6 Sol Medium, Gemini 4 Argon, Claude Sonnet 5.5 High, Grok 4.7 High Fast)
Invarian Fallback KetersediaanGemini 4 Argon/Pro -> Gemini 3.8 Flash; Claude Opus 5.5 -> Claude Opus 4.6 (Bebas gagal saat model belum tersedia/kuota penuh)
Protokol Hemat Token & KV-CacheKunci instruksi & skema statis di prefix awal (kv-cache-prefix-optimizer); kirim potongan CONTEXT_MAP.md (<250 token/panggilan) saat Fan-Out
Eksekusi SaaT CLI & MCPCLI: vibes skill exec mpa-orchestrator <audit|eval|verify|generate|blueprint> / MCP: vibes_skill_dispatch, vibes_ast_query, vibes_compile_cache, vibes_optimize_budget, vibes_verify_gate
Invarian NFR & Anti-SlopLatensi P99 API < 85ms, paritas skema ketat OpenAPI 3.1 / TypeSpec, kontrak error RFC 9457 Problem Details, penegakan Idempotency-Key; kode 100% tuntas tanpa placeholder diverifikasi melalui node scripts/check-anti-slop.js --strict

Frequently asked questions

What does the Mpa Orchestrator AI skill do?

Multi-Page Application (MPA) architecture and asset orchestration / Arsitektur Multi-Page Application (MPA) dan orkestrasi aset.

Why use Mpa Orchestrator on TypingMind?

Because you install it once and use it with any model. Mpa Orchestrator is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Mpa Orchestrator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/roedyrustam/vibes-plug/tree/main/skills/mpa-orchestrator. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Mpa Orchestrator?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Mpa Orchestrator?

As many as you like. As long as a model supports skills, you can use Mpa Orchestrator with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Mpa Orchestrator AI skill free?

Yes. It is published on GitHub by roedyrustam under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇