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 commands/secondsky/claude-skills/better-auth-setupgit clone --depth 1 https://github.com/secondsky/claude-skillsWhat 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 | $0.00026 | $0.01318 |
| Opus 5 | $0.00013 | $0.00659 |
| Sonnet 5 | $0.00005 | $0.00264 |
| Haiku 4.5 | $0.00003 | $0.00132 |
Grade A, and why
better-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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
better-auth Setup Wizard
This command walks through configuring better-auth for your project.
Step 1: Gather Requirements
Use the AskUserQuestion tool to collect configuration preferences:
Question 1: Database
Which database will you use?
- Cloudflare D1 (Recommended for Cloudflare)
- PostgreSQL (Drizzle)
- PostgreSQL (Prisma)
- MongoDB
- MySQL
- SQLite
Question 2: ORM (if applicable)
Which ORM do you prefer?
- Drizzle ORM (Recommended)
- Prisma
- Kysely
- None (Direct adapter)
Question 3: Framework
Which framework are you using?
- Cloudflare Workers + Hono
- Next.js (App Router)
- Next.js (Pages Router)
- Nuxt 3
- Remix
- SvelteKit
- Express
- Fastify
- Expo (React Native)
Question 4: OAuth Providers
Which OAuth providers do you need? (Select all that apply)
- Google
- GitHub
- Microsoft/Azure AD
- Apple
- Discord
- Twitter/X
- None (Email/password only)
Question 5: Plugins
Which features do you need? (Select all that apply)
- Two-Factor Authentication (2FA)
- Passkeys (WebAuthn)
- Magic Links
- Organizations (Multi-tenancy)
- API Keys
- Admin Dashboard
- None
Step 2: Generate Configuration
Based on answers, generate the appropriate files:
Core Files to Create
-
src/auth.ts(orlib/auth.ts)- betterAuth configuration
- Database adapter
- Selected plugins
- OAuth providers
-
Database Schema
- For Drizzle:
src/db/schema.ts - For Prisma:
prisma/schema.prisma - For D1: Include in Drizzle schema
- For Drizzle:
-
Auth Route
- Cloudflare:
src/index.tswith Hono - Next.js App:
app/api/auth/[...all]/route.ts - Next.js Pages:
pages/api/auth/[...all].ts - Nuxt:
server/api/auth/[...all].ts - Remix:
app/routes/api.auth.$.tsx - SvelteKit:
src/routes/api/auth/[...all]/+server.ts
- Cloudflare:
-
Client
src/lib/auth-client.tsor framework equivalent- Include selected client plugins
-
Environment Variables Template
.env.examplewith all required variables
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.
- yesterday First seen · 247 lines · 26 tokens per session scan A 4a1c6bf350b5
better-auth:setup is a command published in the GitHub repository secondsky/claude-skills (212 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 1,318 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
correlate
Find related failures through pattern matching.
diff
Compare two command outputs with intelligent diff.
open
Open/retrieve an offloaded output by ID or shortcut.
search
Search through offloaded outputs with hard caps.
stats
Show FewWord session statistics with rich output and token savings.
tag
Add tags to offloaded outputs for organization.