automation-engineer

automation-engineer is a skill for Claude Code, Codex from genudo-ai/genudo_mcp. It costs 82 tokens per session (385 once invoked), scanned A, original, MIT.

A guide for connecting a Genudo conversation pipeline to outside services such as Zapier, Make, n8n, customer-management systems, or Google Sheets.

In plain words
What is it for?
Registering leads, sending mapped data to webhooks, creating variables, and chaining automated actions between conversation stages.
Why use it?
It organizes data, webhooks, and pipeline stages so external actions use the right values and the agent reports success or failure correctly.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Registering leads, sending mapped data to webhooks, creating variables, and chaining automated actions between conversation stages.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/genudo-ai/genudo_mcp/automation-engineer
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.

Any agent
npx skills add genudo-ai/genudo_mcp --skill automation-engineer
Clone the repo
git clone --depth 1 https://github.com/genudo-ai/genudo_mcp

Made for: Claude Code, Codex.

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-engineer

README.md
[![agentmods](https://agentmods.dev/badge/skills/genudo-ai/genudo_mcp/automation-engineer/github.svg)](https://agentmods.dev/skills/genudo-ai/genudo_mcp/automation-engineer)
Your own site
<a href="https://agentmods.dev/skills/genudo-ai/genudo_mcp/automation-engineer"><img src="https://agentmods.dev/badge/skills/genudo-ai/genudo_mcp/automation-engineer/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 automation-engineer

Your own site · 80×15
<a href="https://agentmods.dev/skills/genudo-ai/genudo_mcp/automation-engineer"><img src="https://agentmods.dev/badge/skills/genudo-ai/genudo_mcp/automation-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 385 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00082 $0.00385
Opus 5 $0.00041 $0.00192
Sonnet 5 $0.00016 $0.00077
Haiku 4.5 $0.00008 $0.00038

Measured 11d ago against content hash ecf244881c4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

automation-engineer 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 11d 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.

chatgpt/genudo-chatgpt-plugin/skills/automation-engineer/SKILL.md · 26 lines

What it actually says

You are the Genudo Automation Engineer. You wire agents to external systems reliably and safely.

Operating procedure:

  1. Understand the rule — which stage, what data, which external tool, and the success/ failure messaging the customer should see.
  2. Variables first — run manage-pipeline-variables: discover existing (list_variables), then create any missing. Choose the right type: from_system (opportunity/contact fields), from_ai (profiled from the chat), from_action (chain a prior action's output), fixed. Never inline raw {{opportunity.*}} — always route through a named variable.
  3. Action — run build-action-webhook: method, URL, headers, payload mapped to variables, fixed_trigger, stage placement, when-to-call instructions, and a response_example when a later action chains on this one.
  4. Wire the flow — run wire-stage-automation to make the stage instructions reference the action: collect → fire → confirm on success → recover on failure.

Rules:

  • Provision variables before the action that references them.
  • fixed_trigger is set at creation (only → on_user_message/custom on update) — choose correctly.
  • The agent must never tell a customer an action succeeded without a confirming response.
  • Confirm every create/update with the user before writing.
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. 11d ago First seen · 26 lines · 82 tokens per session scan A ecf244881c4d

Subscribe to this mod's changes

automation-engineer is a skill published in the GitHub repository genudo-ai/genudo_mcp (0 stars, last pushed 11d ago), licensed MIT. It adds 82 tokens to every session and 385 once invoked, about $0.0004 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.