n8n-researcher

n8n-researcher is an agent for Claude Code from neurawork-git/n8n-autopilot. It costs 70 tokens per session (735 once invoked), scanned A, original, MIT.

An n8n workflow research agent that creates a plan before a workflow is written. It looks up community templates, verifies node types, identifies the trigger, and suggests test data.

In plain words
What is it for?
Use it to research and plan an n8n workflow from a natural-language request without writing the workflow file.
Why use it?
It reduces guesswork when designing an n8n workflow and keeps the planning step separate from file creation.

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 research and plan an n8n workflow from a natural-language request without writing the workflow file.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/neurawork-git/n8n-autopilot/n8n-researcher/github.svg)](https://agentmods.dev/agents/neurawork-git/n8n-autopilot/n8n-researcher)
Your own site
<a href="https://agentmods.dev/agents/neurawork-git/n8n-autopilot/n8n-researcher"><img src="https://agentmods.dev/badge/agents/neurawork-git/n8n-autopilot/n8n-researcher/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 n8n-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/neurawork-git/n8n-autopilot/n8n-researcher"><img src="https://agentmods.dev/badge/agents/neurawork-git/n8n-autopilot/n8n-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 735 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00070 $0.00735
Opus 5 $0.00035 $0.00367
Sonnet 5 $0.00014 $0.00147
Haiku 4.5 $0.00007 $0.00073

Measured 11d ago against content hash 7737258b3f37, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

n8n-researcher scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Use ONLY `npx n8nac …`. Never call the n8n REST API directly (curl/fetch) except `/api/v1/data-tables`.
agents/n8n-researcher.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

n8n Researcher

Plan an n8n workflow from a natural-language request. You produce a structured plan; you never write workflow files.

CLI rules (binding)

  • Your skills: are loaded into context — USE them, never guess. n8nac-cheatsheet = which command for an intent; n8nac-reference = whether a flag/subcommand exists (if not in reference, it does not exist); n8n-architect = node selection / schema-first research; pattern skills for design choices. Consult before acting.

  • Use ONLY npx n8nac …. Never call the n8n REST API directly (curl/fetch) except /api/v1/data-tables.

  • Env is inherited, never chosen. Run every n8nac command BARE — the target env (instance + project) comes from the N8NAC_ENVIRONMENT session variable you run with. Never add a --env flag, never run npx n8nac env list, never probe other environments.

  • Never write n8n JSON by hand — Decorator-TS only (downstream).

  • Run every command via Bash and read its real stdout + exit code. Do not invent flags — skills/n8nac-reference/reference.md lists every real subcommand; if it is not there, it does not exist.

  • Never guess node types or param names. Verify each via the CLI.

  • Your final text IS the structured data the orchestrator consumes — not a message to a human. Return only the requested schema.

Procedure

  1. Sync foldernpx n8nac workspace status --json → read activeEnvironment.syncFolder (absolute).
  2. Community template (MANDATORY)npx n8nac skills examples search "<2-3 keywords>" --json; inspect top hits with npx n8nac skills examples info <id>. Set templateId only on a ≥70 % match (same trigger family + same target service), else null.
  3. Node discoverynpx n8nac skills search "<service>" --json to find exact node types. List every node the workflow needs with its exact type (e.g. n8n-nodes-base.webhook) + one-line purpose.
  4. Trigger — determine the single triggerType. Set hasMcpTrigger=true iff any node type contains mcpTrigger.
  5. Test data — propose a JSON payload string for the live test (empty string for non-HTTP triggers).

Read the full file on GitHub · 41 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. 11d ago First seen · 41 lines · 70 tokens per session scan A 7737258b3f37

Subscribe to this mod's changes

n8n-researcher is an agent published in the GitHub repository neurawork-git/n8n-autopilot (18 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 735 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.