better-auth-debugger

better-auth-debugger is an agent for Claude Code from secondsky/claude-skills. It costs 32 tokens per session (1,728 once invoked), scanned A, original, MIT.

An autonomous troubleshooting agent for Better Auth, a TypeScript framework for adding user authentication to applications. It examines configuration, OAuth callback addresses, endpoints, sessions, databases, and cross-origin access settings.

In plain words
What is it for?
Use it to inspect Better Auth setup, test authentication endpoints, validate OAuth callbacks, and identify specific fixes.
Why use it?
It helps locate the configuration errors behind failed logins, broken redirects, missing sessions, database errors, CORS problems, and unauthorized responses.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the better-auth plugin — 1 skill, 4 commands, 1 agent shipped together

Good fit Use it to inspect Better Auth setup, test authentication endpoints, validate OAuth callbacks, and identify specific fixes.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/secondsky/claude-skills/better-auth-debugger
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.

Clone the repo
git clone --depth 1 https://github.com/secondsky/claude-skills

Made for: Claude Code.

Or install better-auth, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 1 agent.

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 better-auth-debugger

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/secondsky/claude-skills/better-auth-debugger"><img src="https://agentmods.dev/badge/agents/secondsky/claude-skills/better-auth-debugger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,728 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 $0.00032 $0.01728
Opus 5.5 $0.00013 $0.00691
Sonnet 5.5 $0.00006 $0.00346
Haiku 4.5 $0.00003 $0.00173

Measured 1mo ago against content hash ab59e0868cec, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

better-auth-debugger 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 1mo 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.

curl -s http://localhost:3000/api/auth/session | jq
plugins/better-auth/agents/better-auth-debugger.md · 323 lines

How it starts

The opening of the file, as written. The whole thing — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.

better-auth Debugger Agent

Autonomously diagnose and fix better-auth authentication issues.

Trigger Conditions

Use this agent when user reports:

  • Authentication not working
  • OAuth redirect issues
  • Session problems
  • Database connection errors
  • CORS issues
  • "Unauthorized" responses
  • Configuration errors

Diagnostic Process

Phase 1: Locate Configuration

Search for auth configuration files:

Glob patterns:
- **/auth.ts
- **/auth.config.ts
- **/lib/auth.ts
- **/server/auth.ts

Search for client configuration:

Glob patterns:
- **/auth-client.ts
- **/lib/auth-client.ts

Phase 2: Configuration Analysis

Read the auth configuration and check for common issues:

Critical Issues
  1. Missing or Invalid Secret

    // BAD: Hardcoded or missing
    secret: "my-secret"
    secret: undefined
    
    // GOOD: From environment
    secret: process.env.BETTER_AUTH_SECRET!
    
  2. Wrong Adapter Import

    // BAD: Cloudflare D1
    import { d1Adapter } from "better-auth/adapters"  // Wrong!
    
    // GOOD: Cloudflare D1
    import { drizzleAdapter } from "better-auth/adapters/drizzle"
    
  3. Typos in Config

    // BAD
    emailAndPassowrd: { enabled: true }  // Typo!
    forgetPassword: { enabled: true }     // Wrong name!
    
    // GOOD
    emailAndPassword: { enabled: true }
    
  4. Missing baseURL

    // BAD: Not set or wrong
    baseURL: "localhost:3000"  // Missing protocol
    
    // GOOD
    baseURL: process.env.APP_URL  // e.g., "http://localhost:3000"
    
  5. CommonJS in ESM Project

    // BAD
    const { betterAuth } = require("better-auth")
    
    // GOOD
    import { betterAuth } from "better-auth"
    

Phase 3: Database Validation

Cloudflare D1

Check wrangler.jsonc for D1 binding:

{
  "d1_databases": [
    {
      "binding": "DB",
      "database_name": "auth-db",
      "database_id": "xxx"
    }
  ]
}

Verify binding name matches code:

database: drizzleAdapter(drizzle(env.DB), { provider: "sqlite" })

Read the full file on GitHub · 323 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. 1mo ago First seen · 323 lines · 32 tokens per session scan A ab59e0868cec

Subscribe to this mod's changes

better-auth-debugger is an agent published in the GitHub repository secondsky/claude-skills (231 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 1,728 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.