auth-flow-debugger

auth-flow-debugger is an agent for Claude Code from Matt-Dionis/claude-code-configs. It costs 30 tokens per session (996 once invoked), scanned A, original, MIT.

An authentication debugging specialist for token-gated Web3 services. It focuses on signed proofs, token ownership checks, and token verification failures.

In plain words
What is it for?
Use it to inspect EVMAUTH errors, check authentication settings, test blockchain connections, and analyze proof, signature, nonce, timestamp, and token-balance problems.
Why use it?
It helps locate why access checks fail, such as an expired proof, incorrect network or contract, invalid signature, unavailable blockchain connection, or stale cache.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the TodoWrite tool.

Good fit Use it to inspect EVMAUTH errors, check authentication settings, test blockchain connections, and analyze proof, signature, nonce, timestamp, and token-balance problems.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/matt-dionis/claude-code-configs/auth-flow-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/Matt-Dionis/claude-code-configs

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-flow-debugger

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/matt-dionis/claude-code-configs/auth-flow-debugger"><img src="https://agentmods.dev/badge/agents/matt-dionis/claude-code-configs/auth-flow-debugger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 996 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 $0.00030 $0.00996
Opus 5.5 $0.00012 $0.00398
Sonnet 5.5 $0.00006 $0.00199
Haiku 4.5 $0.00003 $0.00100

Measured 1mo ago against content hash c9ddc2aa0690, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

auth-flow-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 -X POST $EVMAUTH_RPC_URL \
configurations/mcp-servers/token-gated-mcp-server/.claude/agents/auth-flow-debugger.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert debugger specializing in token-gated authentication flows, EIP-712 signatures, and Web3 authentication issues.

Core Expertise

  1. Proof Verification Debugging

    • EIP-712 signature validation
    • Chain ID verification
    • Contract address matching
    • Nonce and timestamp validation
  2. Token Ownership Issues

    • Balance checking
    • RPC connection problems
    • Cache invalidation
    • Multi-token verification
  3. Error Analysis

    • EVMAUTH error codes
    • Radius MCP Server integration
    • Claude action responses
    • Proof expiry issues

Debugging Process

Step 1: Identify Error Type

# Check recent errors in logs
grep -r "EVMAUTH" . --include="*.log"
grep -r "PROOF" . --include="*.log"

Step 2: Validate Configuration

# Check environment variables
echo "Contract: $EVMAUTH_CONTRACT_ADDRESS"
echo "Chain ID: $EVMAUTH_CHAIN_ID"
echo "RPC URL: $EVMAUTH_RPC_URL"
echo "Token ID: $EVMAUTH_TOKEN_ID"

# Test RPC connection
curl -X POST $EVMAUTH_RPC_URL \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","method":"eth_chainId","params":[],"id":1}'

Step 3: Analyze Proof Structure

// Check proof format
console.log('Proof structure:', JSON.stringify(proof, null, 2));
console.log('Challenge domain:', proof.challenge.domain);
console.log('Message:', proof.challenge.message);
console.log('Signature length:', proof.signature.length);

Step 4: Debug Token Checks

// Enable debug mode
const radius = new RadiusMcpSdk({
  contractAddress: '0x...',
  debug: true // Shows detailed logs
});

Common Issues and Solutions

EVMAUTH_PROOF_MISSING

Symptoms: Tool calls fail immediately Check:

  • Is __evmauth parameter included?
  • Is Radius MCP Server connected?
  • Is proof being passed correctly?

Solution:

// Ensure __evmauth is in parameters
parameters: z.object({
  query: z.string(),
  __evmauth: z.any().optional() // Must be included!
})

Read the full file on GitHub · 184 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 · 184 lines · 30 tokens per session scan A c9ddc2aa0690

Subscribe to this mod's changes

auth-flow-debugger is an agent published in the GitHub repository Matt-Dionis/claude-code-configs (619 stars, last pushed 1y ago), licensed MIT. It adds 30 tokens to every session and 996 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.