setup

An interactive wizard for setting up user authentication, the part of an application that handles sign-in and identity. It supports Better Auth and Firebase Auth projects using Next.js, a React web framework.

In plain words
What is it for?
For detecting a project's framework, database, existing auth setup, and package manager, then configuring authentication and generating the needed files.
Why use it?
It guides the configuration of login providers, OAuth social sign-in, email authentication, database schemas, and related interface components.

Command

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.

agentmods
npx agentmods add commands/shipwithai/shipwithai-plugins/setup
Clone the repo
git clone --depth 1 https://github.com/ShipWithAI/shipwithai-plugins
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,382 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00025 $0.04382
Opus 5 $0.00013 $0.02191
Sonnet 5 $0.00005 $0.00876
Haiku 4.5 $0.00003 $0.00438

Measured 2d ago against content hash 83fb7d16bea0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup 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 2d 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.

plugins/auth/commands/setup.md · 345 lines

How it starts

The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auth Setup Wizard

You are an expert authentication engineer. Guide the user through setting up production-ready auth for their project.

BEFORE ANYTHING ELSE: Read the skill at skills/auth-setup/SKILL.md for the full decision framework, file creation checklists, and critical warnings. Also read skills/auth-setup/references/09-common-pitfalls.md to avoid known issues.

Step 0: Auto-Discover Project Stack (SILENT)

Before asking ANY questions, silently scan the project. Follow skills/auth-setup/SKILL.md → Step 0 exactly.

Scan for:

  1. Frameworknext.config.* → Next.js (check version: 14/15/16+)
  2. Routerapp/ → App Router | pages/ → Pages Router (❌ block if no App Router)
  3. Version compat — React ≥18, Node ≥18. Block if incompatible.
  4. ORMdrizzle.config.ts → Drizzle | prisma/schema.prisma → Prisma | deps fallback
  5. Existing authbetter-auth, firebase, @clerk/nextjs, next-auth, @supabase/ssr in deps
  6. Existing pages(auth)/login/, api/auth/, middleware.ts, README.md at project root (used by Step 2m)
  7. Package manager — lockfile detection (pnpm/yarn/bun/npm)
  8. UI librarycomponents.json → shadcn/ui | Tailwind | MUI/Chakra/Mantine
  9. Design system — existing globals.css with shadcn CSS vars → Scenario A

Show summary to user (see SKILL.md for format). If critical issues found → STOP.

If existing auth detected → warn and suggest /shipwithai-auth:doctor first. Only proceed if user confirms.

Store all results — use them to skip questions and adapt code generation below.

Step 1: Gather Requirements

If $ARGUMENTS specifies a provider, skip Question 1.

Smart skipping based on Step 0:

  • If ORM detected → pre-fill Question 3, ask user to confirm instead of choosing
  • If existing auth detected → warn about conflict before Question 1
  • If shadcn/ui detected → Scenario A confirmed, skip Question 5

Ask questions ONE AT A TIME using AskUserQuestion:

Read the full file on GitHub · 345 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. 2d ago First seen · 345 lines · 25 tokens per session scan A 83fb7d16bea0

Subscribe to this mod's changes

setup is a command published in the GitHub repository ShipWithAI/shipwithai-plugins (10 stars, last pushed 20d ago), licensed MIT. It adds 25 tokens to every session and 4,382 once invoked, about $0.0001 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 2026-08-31.