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.
npx agentmods add instructions/macroman5/automationhelper_plugins/claude-mdgit clone --depth 1 https://github.com/MacroMan5/AutomationHelper_pluginsWrote 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.
[](https://agentmods.dev/instructions/macroman5/automationhelper_plugins/claude-md)<a href="https://agentmods.dev/instructions/macroman5/automationhelper_plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/macroman5/automationhelper_plugins/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.05852 | $0.05852 |
| Opus 5 | $0.02926 | $0.02926 |
| Sonnet 5 | $0.01170 | $0.01170 |
| Haiku 4.5 | $0.00585 | $0.00585 |
Grade A, and why
AutomationHelper_plugins CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 773 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
⚠️ Alpha Version - This plugin is in active development. Power Automate and n8n focus. Make/Zapier not yet supported.
Repository Purpose
Automation Helper: AI assistant for Power Automate and n8n workflows. Help design, build, debug, and refactor automation workflows.
⚠️ CRITICAL - Context Limits & Best Practices
When users provide large workflows (>300 lines), ALWAYS:
-
Ask them to section it: "This workflow is large. For better results, please share just the section with the error (around 200-300 lines)."
-
Don't try to process 3000-line JSONs: You'll hit context limits and provide poor results.
-
Request data structure info: "Can you confirm what data type this variable contains? Array of strings or array of objects?"
-
Focus on one problem: If multiple issues, address them sequentially, not all at once.
-
Be honest about limits: If the workflow uses unsupported connectors (Make, Zapier, advanced SharePoint), say so upfront.
Example response to large workflow:
"I see this is a large workflow (1500+ lines). For the best results, could you:
1. Share just the section with the error (the loop at lines 200-400)
2. Explain what that section should do
3. Tell me what data type the variable contains
This helps me provide accurate fixes instead of guessing from too much context."
NEVER: Try to debug 3000 lines of JSON at once. You'll fail.
What This Repository Provides
🎯 6 Specialized Skills (Automation Lifecycle)
- automation-brainstorm 💡 - Interactive workflow design advisor
- automation-build-flow 🏗️ - Complete workflow JSON generator
- automation-debugger 🔧 - Deep error analysis with fix generation
- automation-quick-fix ⚡ - Fast fixes for common error patterns
- automation-refactor 🔄 - Workflow optimization & best practices application
- automation-validator ✓ - Pre-deployment validation & quality checks
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.
- 5d ago First seen · 773 lines · 5,852 tokens per session scan A 179f8c38c945
AutomationHelper_plugins CLAUDE.md is an instructions file published in the GitHub repository MacroMan5/AutomationHelper_plugins (3 stars, last pushed 10mo ago), licensed MIT. It adds 5,852 tokens to every session, about $0.0293 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.
Other instructions, from other repositories
claude-calibration CLAUDE.md
Claude Code instructions for odere-pro/claude-calibration, covering claude-calibration — plugin development, what ships, what doesn't, pointers and agent routing.
mcp-bundle CLAUDE.md
Instructions for zircote/mcp-bundle, covering mcp-bundle, plugin structure, skills, /mcp-bundle:mcpb and testing.
neural-memory CLAUDE.md
Claude Code instructions for Yakoub-ai/neural-memory, covering neural memory plugin, quick start, how it works, mcp server and agent hook.
sftp-cc CLAUDE.md
Claude Code instructions for toohamster/sftp-cc, covering claude.md, project overview, architecture, key design decisions and testing changes.
ship-it open-pr.instructions.md
Instructions for khrichtchatyi/ship-it: When the user asks to open, create, or submit a pull request, follow the skill in skills/open-pr/SKILL.md in full: verify gh is authenticated, resolve the target repository and default branch, push the current branch, open one pull request with a title and body derived from the…
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).