n8n-multi-instance

n8n-multi-instance is a skill for Claude Code from czlonkowski/n8n-skills. It costs 181 tokens per session (3,169 once invoked), scanned A, a copy of n8n-multi-instance, MIT.

Guidance for working with more than one n8n installation through n8n-mcp, such as separate production and staging environments. It explains how to identify and switch the installation that receives each request.

In plain words
What is it for?
Listing available n8n installations, switching between client, team, staging, and production environments, and safely targeting workflow, database, credential, or execution operations.
Why use it?
A read or change sent to the wrong installation can affect the wrong workflows, data, or credentials without an obvious error. Deliberate instance selection prevents these mix-ups.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the n8n-mcp-skills plugin — 15 skills shipped together , and of n8n-mcp-skills

Good fit Listing available n8n installations, switching between client, team, staging, and production environments, and safely targeting workflow, database, credential, or execution operations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/czlonkowski/n8n-skills/n8n-multi-instance
About the project

n8n-skills is a collection of Claude Code skills and hooks that guide AI assistants in creating, validating, and deploying n8n workflows through the n8n-mcp server. Developers use it to automate workflow construction, configure nodes and expressions, resolve validation errors, and operate self-hosted n8n. The catalogue entries are its skills, hooks, plugins, and instruction.

czlonkowski/n8n-skills · 6,205 stars · on GitHub · n8n-skills.com

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 czlonkowski/n8n-skills --skill n8n-multi-instance
Clone the repo
git clone --depth 1 https://github.com/czlonkowski/n8n-skills

Made for: Claude Code.

Or install n8n-mcp-skills, the plugin that ships this one along with the rest of its 15 skills.

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-multi-instance

README.md
[![agentmods](https://agentmods.dev/badge/skills/czlonkowski/n8n-skills/n8n-multi-instance/github.svg)](https://agentmods.dev/skills/czlonkowski/n8n-skills/n8n-multi-instance)
Your own site
<a href="https://agentmods.dev/skills/czlonkowski/n8n-skills/n8n-multi-instance"><img src="https://agentmods.dev/badge/skills/czlonkowski/n8n-skills/n8n-multi-instance/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-multi-instance

Your own site · 80×15
<a href="https://agentmods.dev/skills/czlonkowski/n8n-skills/n8n-multi-instance"><img src="https://agentmods.dev/badge/skills/czlonkowski/n8n-skills/n8n-multi-instance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 181 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,169 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. Third-party audits
  • Socket pass 18 Jun 2026
  • Snyk pass 18 Jun 2026
How audits are shown
Origin 100% copy Near-identical to another mod 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 $0.00181 $0.03169
Opus 5 $0.00090 $0.01584
Sonnet 5 $0.00036 $0.00634
Haiku 4.5 $0.00018 $0.00317

Measured 9d ago against content hash 1995cb03cb89, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

n8n-multi-instance 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 9d 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.

Origin

This is a copy

100% identical to n8n-multi-instance — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/n8n-multi-instance/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working with multiple n8n instances over MCP

When the n8n_instances tool is available, the user has multi-instance mode on: one MCP connection can reach several n8n instances (e.g. prod, staging, or one per client/team). Every other n8n tool (n8n_get_workflow, n8n_list_workflows, n8n_update_partial_workflow, n8n_manage_datatable, n8n_manage_credentials, n8n_executions, n8n_test_workflow, …) runs against whichever instance this session is currently targeting. There is no per-call instance argument: you change the target only by switching. Target the wrong instance and a read returns the wrong data and a write lands in the wrong place — usually with no error (the one exception is an ambiguous credential write, which fails closed; see below). So target deliberately.

If the n8n_instances tool is not present, the account is single-instance: ignore this skill and use the n8n tools directly.

Golden rules

Six rules. Each prevents a class of silent misroute.

  1. Discover first. Call n8n_instances({mode:"list"}) before acting so you know the instance names and which one is current.
  2. Switch by name to your target before doing work on a non-default instance: n8n_instances({mode:"switch", name:"<instance name>"}). The match is case-insensitive.
  3. Switch in its own turn. Never put a switch and a dependent operation in the same parallel tool-call batch. Calls in one batch have no guaranteed order, so the dependent call can be resolved against the previous instance before the switch's session state is visible. Switch, let it return, then operate.
  4. Verify before high-stakes ops. Immediately before creating/updating/deleting credentials (and before destructive workflow edits), confirm current is the instance you intend — primary check is n8n_instances({mode:"list"}). The system fail-closes only the ambiguous credential case (rule 6); an explicit switch to the wrong instance still writes there silently, so this check is on you.
  5. An unexpected NOT_FOUND is almost always a wrong-instance misroute, not a deletion. Don't recreate the object. Re-check the current instance and retry (see Recovery).
  6. On INSTANCE_AMBIGUOUS, switch on this session, then retry. The system is refusing to write a secret because this session never picked a target itself. Comply — run switch here to confirm the instance, then retry the write. Don't work around it or retry blindly.

Read the full file on GitHub · 189 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 189 lines · 181 tokens per session scan A 1995cb03cb89

Subscribe to this mod's changes

n8n-multi-instance is a skill published in the GitHub repository czlonkowski/n8n-skills (6,205 stars, last pushed 6d ago), licensed MIT. It adds 181 tokens to every session and 3,169 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to n8n-multi-instance, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

build-workflow

Full 3-phase pipeline (Research → Write+Validate → Deploy+Test) for shipping an n8n workflow end-to-end. Wraps Etienne's n8n-as-code:n8n-architect skill for schema research + authoring, adds repo-scoped orchestration — community-template lookup, validate-push-test loop, mcpTrigger publish gate, execution inspection…

neurawork-git/n8n-autopilot · 85 tokens

build-stack-v2

EXPERIMENTAL deterministic builder for a whole n8n workflow STACK (multiple sub-workflows wired via Execute Workflow), JS-orchestrated. Takes a PRP-style end-to-end use case, decomposes it into sub-workflows along known rules, fixes the handover contracts between them, documents the architecture (mermaid) in one…

neurawork-git/n8n-autopilot · 153 tokens

build-workflow-v2

EXPERIMENTAL deterministic variant of build-workflow + deploy, JS-orchestrated. Two modes: GREENFIELD (new workflow) and EDIT (change an existing one). Phase ordering, gate-checks (validate / drift-safe push --verify), and fix-loop limits are enforced by a Claude Code JS Workflow script instead of prose — gates become…

neurawork-git/n8n-autopilot · 116 tokens

deploy

Push a local .workflow.ts to n8n, verify remote state, and live-test (test URL by default; --activate --prod runs production test). Side-effecting — only invoked explicitly via /deploy.

neurawork-git/n8n-autopilot · 47 tokens

n8n-code-javascript

Write JavaScript code in n8n Code nodes. Use when writing JavaScript in n8n, using $input/$json/$node syntax, making HTTP requests with $helpers, working with dates using DateTime, troubleshooting Code node errors, or choosing between Code node modes.

neurawork-git/n8n-autopilot · 63 tokens

n8n-orchestration-patterns

Fan-out / fan-in, parallel sub-workflow execution, and batch-orchestrator patterns in n8n. Use when a workflow processes a LIST in parallel, calls sub-workflows, needs faster wall-clock on many items, has a webhook that would otherwise block for minutes, or asks "how do I run sub-workflows in parallel / fan out / fan…

neurawork-git/n8n-autopilot · 84 tokens