login-setup

login-setup is a skill for Claude Code, Cursor from xsolla/xsolla-ai-kit. It costs 332 tokens per session (3,283 once invoked), scanned A, original, MIT.

An integration for Xsolla Login, also called NewID, which manages player accounts and issues tokens that other Xsolla services can use. It covers both account setup and different sign-in methods.

In plain words
What is it for?
Use it to configure OAuth clients and callback URLs, add password, passwordless, social, device, or platform sign-in, validate tokens, and manage profiles, account linking, MFA, friends, and bans.
Why use it?
It removes the need to design the entire player identity flow from scratch before connecting a game to Xsolla’s store, payments, webhooks, or backend.

Skill for Claude CodeCursor

Written for Claude Code and Cursor: shipped in a Claude Code plugin, but also installed under .cursor/.

Part of the xsolla-ai-kit plugin — 8 skills, 1 MCP server shipped together

Good fit Use it to configure OAuth clients and callback URLs, add password, passwordless, social, device, or platform sign-in, validate tokens, and manage profiles, account linking, MFA, friends, and bans.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xsolla/xsolla-ai-kit/login-setup
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.

Any agent
npx skills add xsolla/xsolla-ai-kit --skill login-setup
Clone the repo
git clone --depth 1 https://github.com/xsolla/xsolla-ai-kit

Made for: Claude Code, Cursor.

Or install xsolla-ai-kit, the plugin that ships this one along with the rest of its 8 skills, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for login-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/xsolla/xsolla-ai-kit/login-setup.svg)](https://agentmods.dev/skills/xsolla/xsolla-ai-kit/login-setup)
Your own site
<a href="https://agentmods.dev/skills/xsolla/xsolla-ai-kit/login-setup"><img src="https://agentmods.dev/badge/skills/xsolla/xsolla-ai-kit/login-setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 332 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,283 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00332 $0.03283
Opus 5 $0.00166 $0.01641
Sonnet 5 $0.00066 $0.00657
Haiku 4.5 $0.00033 $0.00328

Measured 8d ago against content hash 1b7e8f2d9051, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

login-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 8d 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.

.cursor/skills/login-setup/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Status

This skill is a draft authored by the Login SME (@mohammed_abujalala).

Detailed material lives in references/:

  • references/setup-pa.md — Publisher Account configuration: standard vs shadow Login project, OAuth 2.0 clients (public, confidential, server), callback URLs, allowed origins (CORS), social providers, user data storage (Xsolla / PlayFab / Firebase / custom)
  • references/integration-modes.md — Login Widget vs Login API vs Xsolla SDKs; JWT vs OAuth 2.0 protocol; client-side vs server-side calls
  • references/auth-flows.md — every authentication method: classic (username/password), passwordless (email / SMS one-time code), social (browser redirect + native silent token), device ID, server custom ID, silent cross-platform (Steam / Xbox Live / Epic Games / PSN / Meta Horizon)
  • references/tokens-and-validation.md — user JWT vs server JWT, claims, expiration & refresh, JWKS validation, common errors, rate limits, IP allowlist
  • references/user-management.md — user profile, password reset, MFA, account linking, social linking, attributes, friends, search, ban/unban, export/import

When to use

Use this skill when the developer wants to:

  • Add user authentication to a game or web app — register/sign-in, "Continue with Google/Facebook/Steam/Epic/PSN/Xbox/Meta", passwordless email or SMS one-time code, device ID, custom ID
  • Configure a Login project in Publisher Account: OAuth 2.0 clients, callback URLs, social providers, MFA, password policy, rate limits, custom email/SMS templates
  • Pick between Login Widget, Login API, or an Xsolla SDK — and between JWT and OAuth 2.0 protocols
  • Issue and use a server JWT for server-to-server calls (create/import users, server-side attributes, etc.)
  • Validate a user JWT in their backend (signature, iss, exp, xsolla_login_project_id, groups, sub)
  • Manage users: link social accounts, reset password, enable MFA, edit profile, manage attributes, ban/unban, search, export/import
  • Build a shadow Login project for cross-platform accounts (main account ↔ Steam / Xbox / Epic / PSN platform accounts)
  • Provide a logged-in Bearer JWT to Store / cart / payment-token flows in catalog-design, Headless Checkout in headless-checkout-integration, or user.id to the handler in webhooks-impl
  • Style / theme / brand the Login UI so the widget matches the game — hand off to login-styling

Read the full file on GitHub · 102 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 102 lines · 332 tokens per session scan A 1b7e8f2d9051

Subscribe to this mod's changes

login-setup is a skill published in the GitHub repository xsolla/xsolla-ai-kit (3 stars, last pushed 19d ago), licensed MIT. It adds 332 tokens to every session and 3,283 once invoked, about $0.0017 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.