Skip to main content
plugin

app-stack — Claude Code plugin: what it does, how to install

The app-stack Claude Code plugin guides SaaS development from idea to production with Next.js, Supabase, Clerk, and Netlify. Its skills cover product stages, authorization, UI, analytics, and more.

MIT ★ 741 updated 2026-11-14

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add phuryn/product-engineering
/plugin install app-stack@product-engineering
Open on GitHub

What app-stack does

app-stack bundles 14 skills for building a SaaS with Next.js, Supabase, Clerk, and Netlify. They cover the path from an initial idea to a production product, including product stages, multi-tenant authorization, UI design, environments, and secrets. Other skills address transactional email, uptime monitoring, cookieless analytics, and legal pages.

The collection also covers remote MCP servers, ChatGPT plugins, and Claude agents embedded in an app. Its Supabase guidance uses CLI migrations and separate connection strings for each database. The analytics skill uses Microsoft Clarity with cookies off by default and PostHog for landing-page events.

What it helps with

  • map a SaaS product’s path from idea to production
  • define access rules for a multi-tenant app
  • separate development and production environments
  • plan uptime checks and incident alerts
  • collect product analytics without cookies

Example prompts for the agent

  • Map the stages for taking our SaaS from idea to production.
  • Define authorization for an app with multiple workspaces.
  • Plan uptime monitoring for the app and its scheduled jobs.

How to install app-stack

Plugin marketplace

/plugin marketplace add phuryn/product-engineering
/plugin install app-stack@product-engineering

Step by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own

Questions about app-stack

How do I install app-stack in Claude Code?

Add the marketplace with /plugin marketplace add phuryn/product-engineering, then install the plugin with /plugin install app-stack@product-engineering.

What does app-stack do?

It adds 14 skills for SaaS development with Next.js, Supabase, Clerk, and Netlify. Topics include product stages, authorization, UI, environments, monitoring, and analytics.

What topics do the app-stack skills cover?

Alongside app development, they cover remote MCP servers, ChatGPT plugins, embedded Claude agents, transactional email, analytics, and legal pages.

Source text

app-stack · MIT
# app-stack — build a SaaS with coding agents

Next.js (App Router) + Supabase + Clerk + Netlify, from an idea to a product in production. The rules were learned on real products; each states its principle first, so most carry to another stack.

## Install

```bash
claude plugin marketplace add phuryn/product-engineering
claude plugin install app-stack@product-engineering
```

Codex, Cursor and other agents: see the collection's root `README.md`.

## Skills (14)

- **app-lifecycle** — The detailed path for a SaaS from idea to production, stage by stage: what each produces, when it is done, what each product shape skips, and which capability to propose next when its trigger fires. It takes the accepted artifact from the `product` pack's `propose` as its first stages.
- **saas-authorization** — Who may do what in a multi-tenant app: workspaces, the three functions every route goes through, permissions vs roles vs entitlements, invariants as database constraints, and the threat model every app has.
- **supabase-production** — The choices Supabase's own skill can't make: the server as the only database client, RLS on with zero policies, migrations by CLI with the target spelled out, each database reached only by its own connection string and the CLI never linked, and how to tell whether a push applies migrations.
- **clerk-production** — The choices Clerk's own skills can't make: verify never decode, sign-in landing, organizations and billing, the CSP header, MCP OAuth, the authenticated test mile and the gotchas that failed silently.
- **environments** — Development and production kept apart: the verified mapping, branches, the migrations window, variables and secrets (with a schema that runs at build), backups, incidents, the domain and the agent's access to each provider, and showing development to the owner.
- **ui-design** — How product UI is designed, built and judged: the method every kit and screen satisfies, which design skill collection leads at each stage, what a screen may claim, and reviewing the look with its owner.
- **mcp-server** — Shipping a remote MCP server right the first time: authentication, the route, tool descriptions and schemas held by tests, directory listings and what each requires, verified clients, and a companion package.
- **chatgpt-plugin** — Getting a plugin into OpenAI's plugin directory through review the first time, on any stack: the authentication decided before the first upload, the package and a script that checks it, ChatGPT's OAuth client and request metadata, the data and annotation rules review enforces, the reviewer account, the portal's traps, rejection, and what changes after publication.
- **embedded-agents-messages-api** — Embedding Claude agents in the app on the Claude API — the default: one wrapper, agents as directories, exactly the tools the app gives them, streamed to a chat UI.
- **embedded-agents-agent-sdk** — The same agent directories on the Claude Agent SDK, for an agent that needs Claude Code's built-in tools.
- **transactional-email** — Sending email from the app through a provider: an outbox, durable receipts and reconciliation instead of a promise of exactly-once, one-click unsubscribe, and a provider server per environment.
- **uptime-monitoring** — Knowing the app is down before its users do, on any monitoring service: content checks instead of status codes, confirmation from a second location, heartbeats for scheduled jobs, monitoring that doesn't run on what it monitors, and an alert route proven by a controlled failure. The default service is Staygreen, made by this collection's author, and its adapter is included; a service you already use stays.
- **product-analytics** — What people did, without analytics cookies: session recordings and heatmaps from Microsoft Clarity with cookies off by default, PostHog for events on the landing page, the data read back by the agent through each vendor's MCP server, and what changes (a banner, a policy line, the owner's dashboard steps) when a cookie comes in.
- **legal-pages** — Terms, a privacy policy and consent at sign-up, drafted from what the code collects and sends while it is built, held to it by a test, with the facts only the owner has and the owner's approval.

## Author

Paweł Huryn — [The Product Compass](https://www.productcompass.pm)

© Paweł Huryn · MIT · phuryn/product-engineering

Similar plugins

All plugins for Backend and APIs →

From the same set51

The whole set →
app-lifecycle The app-lifecycle skill for Claude Code and Codex maps a SaaS product’s path from idea to production into stages with completion criteria. It activates for questions about the current stage, next steps, or whether a stage is done. CX Codex +1 ★ 741repo stars codex-agents The codex-agents Claude Code skill brings Codex CLI in as a second agent for implementation and independent review. It responds to requests to consult Codex and to decisions with competing options. CX Codex +1 ★ 741repo stars independent-review The independent-review Claude Code skill runs an independent code review before a release and after fixes. The reviewer must start in a session that did not build the change. CX Codex +1 ★ 741repo stars work-humanizer work-humanizer is a Claude Code plugin that revises work writing with an AI-like tone while preserving its meaning. It can also interview the writer and shape a piece from their answers. ★ 741repo stars agent-harness The agent-harness Claude Code plugin organizes agent instructions, hooks, and persistent work status. Its skills handle session handovers and turn session friction into setup changes. ★ 741repo stars agent-teams The agent-teams Claude Code plugin guides task delegation and lets coding agents act as peers, builders, or independent reviewers. Use it to brief a delegate or work with Codex CLI, Grok CLI, or headless Claude Code. ★ 741repo stars ai-shipping The ai-shipping Claude Code plugin documents AI-built apps and checks changes before release. Its ship-check command brings documentation, reviews, and test coverage into one workflow. ★ 741repo stars product This Claude Code plugin helps decide what to build before development starts. It turns idea research, hypotheses and key screens into a draft for the product owner to review. ★ 741repo stars

Project sponsors

Companies that keep this analytics open