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 skills add T4LEL/Claude-Arsenal --skill add-authgit clone --depth 1 https://github.com/T4LEL/Claude-ArsenalWrote 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.
[](https://agentmods.dev/skills/t4lel/claude-arsenal/add-auth)<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.
<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>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.
| Model | Per session | Once 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 |
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: 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:
- Sign up a fresh user; confirm the profile row was created.
- Log in; confirm a session cookie is set.
- Load a protected page while authenticated; confirm it renders.
- Log out; confirm the session is cleared.
- Request a protected resource with no session (curl, no cookie) — it must fail (redirect or 401/403), not leak data.
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.
- 10d ago First seen · 63 lines · 44 tokens per session scan A 509baacdd58f
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.
Other skills, from other repositories
sandbox-stable
Build or maintain Cloudflare Sandbox apps on the stable @cloudflare/sandbox package. Use sandbox-next for preview apps and sandbox-migrate-to-next for stable-to-preview migrations.
durable-objects
Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.
sandbox-next
Build or maintain Cloudflare Sandbox apps on @cloudflare/sandbox@next (SDK 1.0 preview). Use sandbox-migrate-to-next when porting a stable app.
cloudflare
Discover and choose Cloudflare products for apps, APIs, AI agents, storage, networking, and security. Use for architecture and product selection, including when the user describes a need without naming a Cloudflare product; then find the relevant skill or documentation.
cloudflare-email-service
Implement or troubleshoot Cloudflare Email Sending and Email Routing integrations and their delivery configuration.
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.