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.
git clone --depth 1 https://github.com/neurawork-git/n8n-autopilotWrote 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/agents/neurawork-git/n8n-autopilot/n8n-stack-architect)<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>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 5.1 | $0.00094 | $0.01416 |
| Opus 5 | $0.00047 | $0.00708 |
| Sonnet 5 | $0.00019 | $0.00283 |
| Haiku 4.5 | $0.00009 | $0.00142 |
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.
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-patternsis your source of truth for decomposition (fan-out/fan-in, sub-WF via Execute Workflow, fast-return webhook, DataTable fan-in).n8n-structured-extractioninforms 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_ENVIRONMENTsession variable. Never add--env, never runnpx 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)
- Single responsibility per leaf — one external system OR one cohesive transformation; independently testable.
- Triggers at the edges — the top orchestrator owns the entry trigger (webhook/schedule); leaves use an
executeWorkflowTrigger. - Reusability boundary — a unit used by >1 parent, or independently runnable, becomes its own sub-WF.
- Fan-out / fan-in — list processing: orchestrator splits → per-item sub-WF in parallel → fan-in (DataTable or merge).
- Fast-return webhook — a webhook that would block for minutes responds immediately, hands off to an async sub-WF.
- Error boundary — failure-prone external calls isolated in their own sub-WF, contained + retryable, explicit error branch.
- Memory / large-data boundary — heavy DB/file/batch work in its own sub-WF with
splitInBatches/pagination, never inline in a hot path. - Shallow over deep — prefer orchestrator → leaves; avoid nesting deeper than ~2–3 levels.
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.
- 8d ago First seen · 85 lines · 94 tokens per session scan A 2f680d59ba28
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.
Other agents, from other repositories
workflow-optimizer
Optimizes n8n workflows for performance and reliability. Analyzes structure, reduces complexity, improves error handling. Use for workflow review and optimization.
workflow-planner
Plans n8n workflow automation. Analyzes requirements, searches templates, designs node structure. Use PROACTIVELY when users need new workflows or automation.
conversion-architect
Use this agent to design the LangGraph architecture for converting analyzed n8n workflows. Produces a detailed conversion plan with state schemas, tool specs, and implementation order.
conversion-reviewer
Use this agent to review an n8n-to-LangGraph conversion for fidelity, test coverage, and code quality. Compares implementation against original workflows.
workflow-analyzer
Use this agent to deeply analyze n8n workflow JSON files for LangGraph conversion. Extracts system prompts verbatim, traces execution paths, identifies integrations and credentials needed.
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.