ory-auth-setup

A guide for adding complete Ory Network authentication to a web app with Ory Elements. Authentication covers user sign-in, registration, recovery, verification, account settings, and sessions.

In plain words
What is it for?
Use it to add login, sign-up, password recovery, email verification, account settings, multi-factor authentication, and session management.
Why use it?
It lays out the surrounding setup needed for the authentication flows to work, including the user interface and session handling.

Skill for Claude CodeCodex

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 skills/ory/claude-plugins/ory-auth-setup
Any agent
npx skills add ory/claude-plugins --skill ory-auth-setup
Clone the repo
git clone --depth 1 https://github.com/ory/claude-plugins

Made for: Claude Code, Codex.

Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,891 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00090 $0.04891
Opus 5 $0.00045 $0.02446
Sonnet 5 $0.00018 $0.00978
Haiku 4.5 $0.00009 $0.00489

Measured 2d ago against content hash 3ec0f6dc5eb5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ory-auth-setup scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -i "$NEXT_PUBLIC_ORY_SDK_URL/self-service/login/browser"
plugins/ory-agent-plugin/skills/ory-auth-setup/SKILL.md · 440 lines

How it starts

The opening of the file, as written. The whole thing — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Set up Ory Authentication with Ory Elements

You are setting up a complete authentication system using Ory Network and Ory Elements. Ory Elements is the default and strongly preferred UI layer for every flow (login, registration, recovery, verification, settings). Build the system with Ory Elements unless the user has an explicit, hard constraint that rules it out — and even then, propose Ory Elements first and confirm before choosing a different path.

Why Ory Elements is the default

  • Covers every self-service flow out of the box — login, registration, recovery, verification, settings, MFA — with a single component per flow.
  • Renders the flow's UI nodes for you. You do not need to map flow.ui.nodes to form fields, handle CSRF tokens, error messages, multi-step states, or method-specific logic by hand.
  • Social login and passkeys appear automatically as soon as they are enabled in the Ory project. No frontend changes needed.
  • Stays in sync with Ory's flow API — when Ory adds a node type or changes a contract, Ory Elements absorbs the change so your app does not break.
  • Themeable and accessible — the look-and-feel can be customized via the theme provider without rebuilding flow logic.

If you find yourself writing flow.ui.nodes.map(...) to render auth UI, stop and switch to Ory Elements. Custom node rendering is a fallback, not a parallel option.

Correctness contract — satisfy these or the app will 404 / 500 / CSRF

Almost every "Ory doesn't work" report comes from one of four wiring mistakes in the generated app — not from Ory itself and not from the agent plugin governing this session. Treat each as a hard requirement, and verify all four (Step 10) before telling the user the app is ready.

  1. Ory must be first-party (same site as your app), or every flow fails CSRF. Ory's browser flows depend on a CSRF cookie. If the browser calls Ory on a different site than your app, the browser drops that cookie and you get CSRF token mismatch, 403s, or redirect loops. So the browser SDK URL must be your own origin — never https://<slug>.projects.oryapis.com directly:
    • Local dev against Ory Network — run ory tunnel and point the SDK at the tunnel (http://localhost:4000). See Step 9.
    • Local dev against the local stack — the gateway is already on http://localhost:4000 (first-party to localhost). Use http://localhost, not 127.0.0.1.
    • Production — serve Ory from your own domain via an Ory Network custom domain (CNAME) or the @ory/nextjs proxy, and set the SDK URL to that.
  2. The app's routes must match what Ory redirects to, or you get 404s. Ory redirects the browser to the self-service UI URLs configured on the project (login, registration, recovery, verification, settings, error). If a page lives at /auth/login but the project points at /login, the redirect 404s. Pick one set of paths and make these four agree: the page files you create, the @ory/nextjs UI-path config, the project's selfservice.flows.*.ui_url (+ error.ui_url), and the middleware path lists. Always create an error page — Ory redirects there on any flow error. See Step 8.
  3. Server-side session/flow calls must forward the request cookies, or they 500/401. A FrontendApi built with credentials: "include" only sends cookies in the browser. In Next.js server components, route handlers, and middleware you must forward the incoming request's cookies — the @ory/nextjs server helpers do this for you. Reusing the browser client on the server is the single most common 500. See Step 7.
  4. The SDK URL env var must be set at runtime, or the SDK 500s on construction. Validate NEXT_PUBLIC_ORY_SDK_URL (browser) / ORY_SDK_URL (server) at startup and fail with a clear message instead of constructing the client with undefined. See Step 4.

Read the full file on GitHub · 440 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 · 440 lines · 90 tokens per session scan A 3ec0f6dc5eb5

Subscribe to this mod's changes

ory-auth-setup is a skill published in the GitHub repository ory/claude-plugins (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 90 tokens to every session and 4,891 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens