add-auth

add-auth is a skill for Claude Code, Codex from T4LEL/Claude-Arsenal. It costs 44 tokens per session (698 once invoked), scanned A, original, MIT.

A workflow for adding user accounts to an application, including sign-up, sign-in, OAuth, protected pages, sessions, roles, and security checks. OAuth lets users sign in through an existing provider such as Google.

In plain words
What is it for?
Use it to plan and build email-password or Google sign-in, user profiles, protected routes, roles, sessions, and deny-by-default database access rules.
Why use it?
Authentication affects data access and page security, so incomplete setup can expose accounts or private information. The workflow makes requirements, database policies, implementation, verification, and security review explicit.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to plan and build email-password or Google sign-in, user profiles, protected routes, roles, sessions, and deny-by-default database access rules.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/t4lel/claude-arsenal/add-auth
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 T4LEL/Claude-Arsenal --skill add-auth
Clone the repo
git clone --depth 1 https://github.com/T4LEL/Claude-Arsenal

Made for: Claude Code, Codex.

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 add-auth

README.md
[![agentmods](https://agentmods.dev/badge/skills/t4lel/claude-arsenal/add-auth/github.svg)](https://agentmods.dev/skills/t4lel/claude-arsenal/add-auth)
Your own site
<a href="https://agentmods.dev/skills/t4lel/claude-arsenal/add-auth"><img src="https://agentmods.dev/badge/skills/t4lel/claude-arsenal/add-auth/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 add-auth

Your own site · 80×15
<a href="https://agentmods.dev/skills/t4lel/claude-arsenal/add-auth"><img src="https://agentmods.dev/badge/skills/t4lel/claude-arsenal/add-auth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 698 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00044 $0.00698
Opus 5 $0.00022 $0.00349
Sonnet 5 $0.00009 $0.00140
Haiku 4.5 $0.00004 $0.00070

Measured 10d ago against content hash 509baacdd58f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

add-auth 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 10d 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.

Exercise the real flow, not a mental walkthrough — use the playwright plugin or curl:
skills/add-auth/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add Auth

Add authentication to the default stack correctly the first time — auth bugs are security bugs.

Copy this checklist and check off items as you complete them:

Add-Auth Progress:
- [ ] Step 1: Requirements
- [ ] Step 2: Data (db-designer)
- [ ] Step 3: Implementation (backend-builder)
- [ ] Step 4: Verify (mandatory)
- [ ] Step 5: Audit (security-auditor)
- [ ] Report

Step 1 — Requirements

Confirm before building:

  • Sign-in methods: email/password, magic link, which OAuth providers.
  • Roles: does an admin/staff tier exist, or is every account equal?
  • Protected surface: which pages/routes require a session, which stay public.

Defaults when the user doesn't specify: email/password plus Google OAuth, a single user role, every app page protected except marketing pages (home, pricing, blog).

Step 2 — Data

Delegate to the db-designer agent with: a profiles table keyed to auth.users (1:1 on id), deny-by-default RLS policies (no table readable or writable without an explicit policy), and a trigger that creates the profile row on signup (on auth.users insert).

Step 3 — Implementation

Delegate to the backend-builder agent with: @supabase/ssr client and server helpers plus middleware, built against CURRENT docs fetched via the context7 MCP tools — the cookie/session-refresh pattern changes between package versions and stale patterns silently break sessions. Cover: login, signup, logout, the OAuth callback route, and protected-route handling (middleware redirect, not a client-side check alone). Keys and secrets stay in env vars, never printed or committed.

Step 4 — Verify (mandatory)

Exercise the real flow, not a mental walkthrough — use the playwright plugin or curl:

  1. Sign up a fresh user; confirm the profile row was created.
  2. Log in; confirm a session cookie is set.
  3. Load a protected page while authenticated; confirm it renders.
  4. Log out; confirm the session is cleared.
  5. Request a protected resource with no session (curl, no cookie) — it must fail (redirect or 401/403), not leak data.

Read the full file on GitHub · 63 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. 10d ago First seen · 63 lines · 44 tokens per session scan A 509baacdd58f

Subscribe to this mod's changes

add-auth is a skill published in the GitHub repository T4LEL/Claude-Arsenal (1 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 698 once invoked, about $0.0002 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.