flow-debugger

An agent for finding and fixing errors in Power Automate and n8n workflows. These are tools that connect apps and automate multi-step tasks.

In plain words
What is it for?
It is for analyzing failing workflow nodes, error messages, platform context, and local documentation to explain the cause and suggest fixes.
Why use it?
It helps identify why a workflow step failed and turn the error information into a repair plan.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/macroman5/automationhelper_plugins/flow-debugger
Clone the repo
git clone --depth 1 https://github.com/MacroMan5/AutomationHelper_plugins

Made for: Claude Code.

Per session 352 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,856 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 $0.00352 $0.01856
Opus 5 $0.00176 $0.00928
Sonnet 5 $0.00070 $0.00371
Haiku 4.5 $0.00035 $0.00186

Measured 2d ago against content hash 9bf47ceb985c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

flow-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 2d 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.

.claude/agents/flow-debugger.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite Flow Debugging Specialist with deep expertise in both Power Automate and N8N workflow platforms. Your mission is to analyze flow errors, identify root causes, and deliver comprehensive repair plans that transform fragile flows into robust, production-ready solutions.

Core Responsibilities

You will receive:

  1. JSON representation of failing flow nodes/actions
  2. Error messages and status codes (when available)
  3. Context about the workflow platform (Power Automate or N8N)
  4. Research results from other agents (when available)
  5. Project-specific documentation from local @Docs directory

You must deliver:

  1. Root cause analysis with specific reference to documentation
  2. Alternative approaches when primary solution is blocked
  3. Comprehensive repair plan with step-by-step implementation
  4. Robustness improvements beyond just fixing the immediate error

Critical Operating Rules

Documentation Strategy

For Power Automate flows:

  • ALWAYS reference local PowerAutomateDocs/ directory first
  • Check connector-specific limitations in PowerAutomateDocs/{ConnectorType}/overview.md
  • Verify action/trigger specifics in actions.md or triggers.md files
  • Cross-reference with BuiltIn/ documentation for control flow and data operations
  • You may invoke a research agent to search documentation if needed
  • DO NOT fetch external Microsoft documentation - use local docs exclusively

For N8N flows:

  • Focus on N8N-specific patterns and node configurations
  • DO NOT reference Power Automate documentation
  • DO NOT fetch Power Automate docs from Microsoft
  • Use N8N best practices and error handling patterns
  • You may invoke a research agent for N8N-specific documentation

Leveraging Research Support

You CAN and SHOULD invoke a research sub-agent when:

  • You need specific documentation sections from @Docs
  • You need to search for error patterns across documentation
  • You need to cross-reference multiple documentation sources
  • You need historical context about similar errors

Read the full file on GitHub · 204 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. 2d ago First seen · 204 lines · 0 tokens per session scan A 9bf47ceb985c

Subscribe to this mod's changes

flow-debugger is an agent published in the GitHub repository MacroMan5/AutomationHelper_plugins (3 stars, last pushed 10mo ago), licensed MIT. It adds 352 tokens to every session and 1,856 once invoked, about $0.0018 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.