automation-debugger

automation-debugger is a skill for Claude Code, Codex from MacroMan5/AutomationHelper_plugins. It costs 90 tokens per session (5,915 once invoked), scanned A, original, MIT.

A skill for diagnosing errors in automation workflows, including Power Automate, n8n, Make, and Zapier. These platforms connect apps and run tasks automatically.

In plain words
What is it for?
It is for analyzing error files and workflow definitions, checking platform documentation, and producing fixed JSON that can be copied back into the workflow.
Why use it?
It helps replace guesswork with a documented explanation of the failure and a complete corrected workflow.

Skill for Claude CodeCodex

Part of the automation-helper plugin — 6 skills, 5 agents shipped together

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 skills/macroman5/automationhelper_plugins/automation-debugger
Any agent
npx skills add MacroMan5/AutomationHelper_plugins --skill automation-debugger
Clone the repo
git clone --depth 1 https://github.com/MacroMan5/AutomationHelper_plugins

Made for: Claude Code, Codex.

Or install automation-helper, the plugin that ships this one along with the rest of its 6 skills, 5 agents.

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 automation-debugger

README.md
[![agentmods](https://agentmods.dev/badge/skills/macroman5/automationhelper_plugins/automation-debugger.svg)](https://agentmods.dev/skills/macroman5/automationhelper_plugins/automation-debugger)
Your own site
<a href="https://agentmods.dev/skills/macroman5/automationhelper_plugins/automation-debugger"><img src="https://agentmods.dev/badge/skills/macroman5/automationhelper_plugins/automation-debugger.svg" alt="Measured on agentmods" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,915 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 $0.00090 $0.05915
Opus 5 $0.00045 $0.02958
Sonnet 5 $0.00018 $0.01183
Haiku 4.5 $0.00009 $0.00592

Measured 5d ago against content hash 885987efa296, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

automation-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.

.claude/skills/automation-debugger/SKILL.md · 713 lines

How it starts

The opening of the file, as written. The whole thing — 713 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Automation Debugger

Expert system for debugging automation workflow errors across multiple platforms and generating production-ready fixes.

Supported Platforms

  • Power Automate (Microsoft)
  • n8n (Open-source automation)
  • Make (formerly Integromat)
  • Zapier
  • Other JSON-based workflow platforms

Purpose

This skill provides comprehensive debugging for automation workflows by:

  1. Analyzing error messages and failing JSON flow definitions
  2. Researching official documentation to find root causes (Docs/ directory)
  3. Generating complete, valid fixed JSON ready for copy-paste (outputs as fixed_flow.json or similar)
  4. Avoiding hallucinations by strictly referencing platform documentation
  5. Adapting solutions to platform-specific requirements

When This Skill Activates

Automatically activates when user provides:

  • Error JSON files - Any JSON file containing error information (examples: error.json, erreur.json, error_bloc.json, workflow_error.json)
  • Workflow JSON with errors - Flow/workflow JSON content with error description (any platform)
  • Error messages - Error messages from workflow runs, logs, or execution history
  • Debug requests - Explicit requests to "debug", "fix", "analyze", or "troubleshoot" automation errors
  • Status codes - HTTP status codes (401, 403, 404, 429, 500, etc.) with workflow context
  • Platform-specific errors - "Power Automate error", "n8n workflow failing", "Make scenario issue", "Zapier zap broken"
  • Failure descriptions - "My flow keeps failing", "this automation stopped working", "getting errors in workflow"

Common Pitfalls to AVOID

❌ CRITICAL ERROR #1: Assuming Data Structures (Most Common!)

The Mistake:

// You see a filter in the error flow
"where": "@contains(toLower(item()), 'keyword')"

// And you ASSUME it's filtering objects, so you fix with:
"value": "@items('Loop')?['PropertyName']"  // ← WRONG IF ARRAY OF STRINGS!

How to Avoid:

  1. ALWAYS analyze filter syntax first: item() vs item()?['Prop']
  2. item() without property → Array of primitives (strings/numbers)
  3. item()?['Property'] → Array of objects
  4. Ask user when uncertain - never guess data structures!
  5. Trace data sources back to understand actual types

Read the full file on GitHub · 713 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 713 lines · 90 tokens per session scan A 885987efa296

Subscribe to this mod's changes

automation-debugger is a skill published in the GitHub repository MacroMan5/AutomationHelper_plugins (3 stars, last pushed 10mo ago), licensed MIT. It adds 90 tokens to every session and 5,915 once invoked, about $0.0005 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 skills, from other repositories

deploy-setup

Wire up a freshly scaffolded Starter Series project for its first release — detect the template, register required GitHub secrets, set up OIDC trusted publishing where applicable, and trigger the first CD run. Pairs with the create skill (you scaffold first, then run this).

starter-series/create-starter · 61 tokens

create

Scaffold a new project from the Starter Series templates (MCP server, Discord/Telegram bot, VS Code / browser extension, Electron, React Native, Cloudflare Pages, npm package, Docker deploy).

starter-series/create-starter · 43 tokens

calibration

Discovery-friendly dispatcher above /calibrate. With no args, prints a menu of every calibration flow — the three /calibrate built-in modes (tighten / harden / cost), the two standalone convenience flows (audit, diff), and the per-feature shortcuts (skills / subagents / claude-md / rules / settings / hooks / mcp /…

odere-pro/claude-calibration · 144 tokens

calibration-flow

Evaluate the BEHAVIOUR of a multi-step workflow, not static config: does the chain deliver intent, and are its agent→agent / agent→skill handoffs sound? Drives a named workflow over a case set of golden fixtures (each /{input/,expected.md}), diffs what it finds against the oracle, and scores node recall/precision…

odere-pro/claude-calibration · 203 tokens

calibration-onboarding

First-time setup guide for claude-calibration and Claude Code config in general. Detects what config the project already has (CLAUDE.md, .claude/, settings.json, hooks, agents, skills, .mcp.json), names the minimal viable additions for this project's stack, and bridges into /claude-calibration:calibration-doctor…

odere-pro/claude-calibration · 142 tokens

calibrate-claude-md

Audits CLAUDE.md, CLAUDE.local.md, and every nested /CLAUDE.md across user / project scopes. Flags committed secrets, files over 200 / 400 effective lines, aspirational ("must" / "always" / "never") wording that should be a hook, vague rules without specifics, @-import chains > 5 hops, contradictions between nested…

odere-pro/claude-calibration · 185 tokens