nosia: Skill for Claude Code

.claude/skills/auth-setup/SKILL.md

auth-setup is a skill for Claude Code from dilolabs/nosia. It costs 88 tokens per session (2,834 once invoked), scanned A, a copy of auth-setup, MIT.

A Rails authentication implementation that provides passwordless sign-in without Devise, a commonly used Rails authentication library. It uses passkeys first and magic links as a fallback.

In plain words
What is it for?
Use it to set up passkey sign-in, magic-link login, session management, password resets, and the supporting identity, credential, and session records.
Why use it?
It gives a Rails application a focused login and session system without relying on a large authentication package or its extra conventions.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is dilolabs/nosia's own configuration. It tells Claude Code how to work on nosia itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nosia configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dilolabs/nosia. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dilolabs/nosia/main/.claude/skills/auth-setup/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dilolabs/nosia

Made for: Claude Code.

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 auth-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/dilolabs/nosia/auth-setup/github.svg)](https://agentmods.dev/skills/dilolabs/nosia/auth-setup)
Your own site
<a href="https://agentmods.dev/skills/dilolabs/nosia/auth-setup"><img src="https://agentmods.dev/badge/skills/dilolabs/nosia/auth-setup/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for auth-setup

Your own site · 80×15
<a href="https://agentmods.dev/skills/dilolabs/nosia/auth-setup"><img src="https://agentmods.dev/badge/skills/dilolabs/nosia/auth-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,834 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 100% copy Near-identical to another mod 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 $0.00088 $0.02834
Opus 5.5 $0.00035 $0.01134
Sonnet 5.5 $0.00018 $0.00567
Haiku 4.5 $0.00009 $0.00283

Measured 2mo ago against content hash 6f2bd22e5f42, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

auth-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 2mo 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.

Origin

This is a copy

100% identical to auth-setup — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/auth-setup/SKILL.md · 362 lines

How it starts

The opening of the file, as written. The whole thing — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert Rails authentication architect specializing in building auth from scratch.

Your role

  • Build custom authentication systems without Devise or other auth gems
  • Implement passkey (WebAuthn) authentication as the primary sign-in method
  • Implement passwordless magic link authentication as the fallback
  • Keep auth simple: ~200 lines of code total
  • Output: Clean session management, passkeys, magic links, and Current attributes setup

Core philosophy

Auth is simple. Don't use Devise. A basic auth system is ~200 lines of code. You get full control, no bloat, easier modifications, and no gem version conflicts.

What you actually need (not Devise's 50+ columns):

  • Identity model (email + has_passkeys + optional password hash)
  • Passkey model (WebAuthn credentials, via ActionPack::Passkey)
  • Session model (token-based, database-stored)
  • Magic link model (passwordless login fallback)
  • Authentication concern (~100 lines)
  • Current attributes (request context)

Project knowledge

Tech Stack: Rails 8.2 (edge), ActionPack::Passkey (built-in WebAuthn), BCrypt for passwords (optional), has_secure_token Pattern: Passkeys (WebAuthn) primary, magic links fallback, password optional for APIs Session storage: Database (not cookies), token-based

Commands

  • bin/rails generate model Identity email_address:string password_digest:string
  • bin/rails test test/controllers/sessions_controller_test.rb
  • bin/rails console then Identity.authenticate_by(email_address: "[email protected]")

Architecture overview

Identity (email, has_passkeys, optional password)
  |-- has_many :passkeys (WebAuthn credentials, primary auth)
  |-- has_many :sessions (token-based, database)
  |-- has_many :magic_links (passwordless login fallback)
  |-- has_one :user (app-specific profile data)

ActionPack::Passkey (credential_id, public_key, sign_count, transports)
Session (has_secure_token, 30-day expiry)
MagicLink (6-char code, 15-min expiry, one-time use)
Current (session, identity, user, account context)

Read the full file on GitHub · 362 lines

Files

What ships with it

2 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. 2mo ago First seen · 362 lines · 88 tokens per session scan A 6f2bd22e5f42

Subscribe to this mod's changes

auth-setup is a skill published in the GitHub repository dilolabs/nosia (211 stars, last pushed 3d ago), licensed MIT. It adds 88 tokens to every session and 2,834 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to auth-setup, differing in 0 lines, and is treated as a copy.

Related

auth-setup compared with skills from other repositories

auth-setup next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
auth-setupdilolabs/nosiaSkill2113d agoMITA88Claude Code
mem0-statusmem0ai/mem0Skill68k2d agoApache-2.0A44Claude Code, Codex
statusmem0ai/mem0Skill68k2d agoApache-2.0A54Claude Code
mem0-test-integrationmem0ai/mem0Skill68k2d agoApache-2.0A207Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0Skill68k2d agoApache-2.0A217Claude Code, Codex
browserwing-executorMemTensor/MemOSSkill12k2d agoApache-2.0A42Claude Code, Codex
deep-researchxerrors/YuxiSkill7.6kyesterdayMITA69Claude Code, Codex