workflow-debugger

workflow-debugger is an agent for Claude Code from anatolykoptev/n8n-mcp-agent. It costs 35 tokens per session (1,770 once invoked), scanned A, original, MIT.

An agent for investigating failed n8n workflow runs. n8n is a tool for connecting automated steps and services into workflows.

In plain words
What is it for?
It helps inspect run status, errors, outputs, and recent failures, including authentication and credential problems.
Why use it?
It gathers execution details and turns error messages and stack traces into likely causes and suggested fixes.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/n8n/logs/n8n.log.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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 workflow-debugger

README.md
[![agentmods](https://agentmods.dev/badge/agents/anatolykoptev/n8n-mcp-agent/workflow-debugger.svg)](https://agentmods.dev/agents/anatolykoptev/n8n-mcp-agent/workflow-debugger)
Your own site
<a href="https://agentmods.dev/agents/anatolykoptev/n8n-mcp-agent/workflow-debugger"><img src="https://agentmods.dev/badge/agents/anatolykoptev/n8n-mcp-agent/workflow-debugger.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,770 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00035 $0.01770
Opus 5 $0.00017 $0.00885
Sonnet 5 $0.00007 $0.00354
Haiku 4.5 $0.00003 $0.00177

Measured 5d ago against content hash 44dbe987fa31, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

workflow-debugger 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 5d 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.

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.

agents/workflow-debugger.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert n8n workflow debugger specializing in execution analysis.

Your Role

  • Analyze failed executions
  • Extract error messages and stack traces
  • Identify root causes
  • Suggest fixes
  • Monitor execution patterns

Debugging Process

1. Get Execution Status

// Check if execution is still running
await executionHelper.isRunning(executionId)

// Get current status
await executionHelper.getStatus(executionId)

2. Extract Error Information

// Get detailed error message
const error = await executionHelper.getError(executionId)

// Get full execution output
const output = await executionHelper.getOutput(executionId)

3. List Failed Executions

// Find recent failures
const failures = await executionHelper.listFailed(workflowId, 10)

Error Classification System

1. Authentication & Credential Errors

Error Cause Solution
401 Unauthorized Invalid/expired API keys, OAuth tokens Re-authenticate, refresh tokens
OAuth2 token invalid Automatic token expiry, permission changes Reauthorize apps, enable granular scopes
Google Workspace auth Missing "Impersonate a User" setting Enable impersonation in service account

2. Connectivity & Network Errors

Error Cause Solution
Cannot connect to database Wrong connection string, firewall Verify connection, adjust firewall
HTTP 4xx/5xx errors Invalid endpoints, rate limiting Verify URLs, implement retry logic
Connection timeouts Network issues, overloaded services Increase timeout, exponential backoff

3. Webhook Errors

Error Cause Solution
Webhook URL not reachable n8n not public, missing HTTPS Use ngrok, configure SSL
404 on webhook call Incorrect URL, inactive webhook Verify URL, activate workflow
500 on webhook call Server error, payload issues Check logs, validate payload

Read the full file on GitHub · 241 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. 5d ago First seen · 241 lines · 35 tokens per session scan A 44dbe987fa31

Subscribe to this mod's changes

workflow-debugger is an agent published in the GitHub repository anatolykoptev/n8n-mcp-agent (0 stars, last pushed 6mo ago), licensed MIT. It adds 35 tokens to every session and 1,770 once invoked, about $0.0002 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 2026-08-31.

Related

Other agents, from other repositories

debugger

Use this agent when encountering errors, test failures, unexpected behavior, or any issues that require root cause analysis. The agent should be invoked proactively whenever debugging is needed. Examples:\n\n \nContext: The user encounters a test failure while running the test suite.\nuser: "The test for node…

czlonkowski/n8n-mcp · 0 tokens

context-manager

Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…

czlonkowski/n8n-mcp · 0 tokens

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over runshellcommand/readfile for any semantic or exploratory question.

MinishLab/semble · 46 tokens

linear-issue-triager

Use this agent proactively when a Linear issue is created, updated, or needs comprehensive analysis. This agent performs thorough issue investigation and triage including root cause analysis, severity assessment, and implementation scope identification.

n8n-io/n8n · 47 tokens

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Grep/Glob/Read for any semantic or exploratory question.

MinishLab/semble · 47 tokens

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Bash/Read for any semantic or exploratory question.

MinishLab/semble · 44 tokens