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.
npx agentmods add skills/ory/claude-plugins/ory-auth-setupnpx skills add ory/claude-plugins --skill ory-auth-setupgit clone --depth 1 https://github.com/ory/claude-pluginsWhat 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 | $0.00090 | $0.04891 |
| Opus 5 | $0.00045 | $0.02446 |
| Sonnet 5 | $0.00018 | $0.00978 |
| Haiku 4.5 | $0.00009 | $0.00489 |
Grade A, and why
ory-auth-setup scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -i "$NEXT_PUBLIC_ORY_SDK_URL/self-service/login/browser" 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.nodesto 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.
- 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 — neverhttps://<slug>.projects.oryapis.comdirectly:- Local dev against Ory Network — run
ory tunneland 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 tolocalhost). Usehttp://localhost, not127.0.0.1. - Production — serve Ory from your own domain via an Ory Network custom
domain (CNAME) or the
@ory/nextjsproxy, and set the SDK URL to that.
- Local dev against Ory Network — run
- 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/loginbut 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/nextjsUI-path config, the project'sselfservice.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. - Server-side session/flow calls must forward the request cookies, or they
500/401. A
FrontendApibuilt withcredentials: "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/nextjsserver helpers do this for you. Reusing the browser client on the server is the single most common 500. See Step 7. - 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 withundefined. See Step 4.
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.
- 2d ago First seen · 440 lines · 90 tokens per session scan A 3ec0f6dc5eb5
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
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.
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.
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…