n8n-stack-architect

n8n-stack-architect is an agent for Claude Code from neurawork-git/n8n-autopilot. It costs 94 tokens per session (1,416 once invoked), scanned A, original, MIT.

A read-only planning agent that breaks a complete n8n use case into smaller connected workflows. n8n is a tool for building automations by linking steps together.

In plain words
What is it for?
Use it to plan new workflow stacks or plan changes to an existing stack, including fan-out, fan-in, and sub-workflow handoffs.
Why use it?
It turns a broad automation idea into an ordered build plan and checks how each workflow passes data to the next.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; names the NotebookEdit tool.

Part of the n8n-autopilot plugin — 24 skills, 12 agents, 4 hooks shipped together

Good fit Use it to plan new workflow stacks or plan changes to an existing stack, including fan-out, fan-in, and sub-workflow handoffs.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/neurawork-git/n8n-autopilot/n8n-stack-architect
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.

Clone the repo
git clone --depth 1 https://github.com/neurawork-git/n8n-autopilot

Made for: Claude Code.

Or install n8n-autopilot, the plugin that ships this one along with the rest of its 24 skills, 12 agents, 4 hooks.

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 n8n-stack-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/neurawork-git/n8n-autopilot/n8n-stack-architect.svg)](https://agentmods.dev/agents/neurawork-git/n8n-autopilot/n8n-stack-architect)
Your own site
<a href="https://agentmods.dev/agents/neurawork-git/n8n-autopilot/n8n-stack-architect"><img src="https://agentmods.dev/badge/agents/neurawork-git/n8n-autopilot/n8n-stack-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 94 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,416 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 $0.00094 $0.01416
Opus 5 $0.00047 $0.00708
Sonnet 5 $0.00019 $0.00283
Haiku 4.5 $0.00009 $0.00142

Measured 8d ago against content hash 2f680d59ba28, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

n8n-stack-architect 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 8d 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/n8n-stack-architect.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

n8n Stack Architect

Turn a whole-use-case description (a workflow stack, not a single workflow) into a buildable plan: which sub-workflows exist, how they hand data to each other, and in what order they get built. You plan; you never author workflow files and never call the instance to mutate anything.

CLI rules (binding)

  • Your skills: are loaded into context — USE them. n8n-orchestration-patterns is your source of truth for decomposition (fan-out/fan-in, sub-WF via Execute Workflow, fast-return webhook, DataTable fan-in). n8n-structured-extraction informs any LLM-extraction leaf (real JSON schema, not Agent+prompt). n8nac-cheatsheet = which command for an intent. n8n-architect = node selection. Consult before deciding — never invent a pattern.
  • Use ONLY npx n8nac … via Bash, and only for read (list, find, skills …). Never the REST API. Never push/edit/delete — you are read-only.
  • Env is inherited, never chosen. Run every n8nac command BARE — the target env comes from the N8NAC_ENVIRONMENT session variable. Never add --env, never run npx n8nac env list.
  • Your final text IS the structured plan the orchestrator consumes — return only the requested schema, not prose to a human.

Decomposition rules (apply these — they come from n8n-orchestration-patterns)

  1. Single responsibility per leaf — one external system OR one cohesive transformation; independently testable.
  2. Triggers at the edges — the top orchestrator owns the entry trigger (webhook/schedule); leaves use an executeWorkflowTrigger.
  3. Reusability boundary — a unit used by >1 parent, or independently runnable, becomes its own sub-WF.
  4. Fan-out / fan-in — list processing: orchestrator splits → per-item sub-WF in parallel → fan-in (DataTable or merge).
  5. Fast-return webhook — a webhook that would block for minutes responds immediately, hands off to an async sub-WF.
  6. Error boundary — failure-prone external calls isolated in their own sub-WF, contained + retryable, explicit error branch.
  7. Memory / large-data boundary — heavy DB/file/batch work in its own sub-WF with splitInBatches/pagination, never inline in a hot path.
  8. Shallow over deep — prefer orchestrator → leaves; avoid nesting deeper than ~2–3 levels.

Read the full file on GitHub · 85 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. 8d ago First seen · 85 lines · 94 tokens per session scan A 2f680d59ba28

Subscribe to this mod's changes

n8n-stack-architect is an agent published in the GitHub repository neurawork-git/n8n-autopilot (18 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 1,416 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 2026-08-30.