n8n Skills is a set of agent skills, reference material, and hooks for building and editing workflows in an n8n instance through its instance-level MCP server. Coding agents use it to manage workflows, projects, sub-workflows, data, debugging, credentials, and n8n Agents, while the catalogue entries provide the packaged workflow guidance and integrations.
Borrowing it
Nothing to install: this file belongs to n8n-io/skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/n8n-io/skills/main/CLAUDE.mdgit clone --depth 1 https://github.com/n8n-io/skillsWrote 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/instructions/n8n-io/skills/claude-md)<a href="https://agentmods.dev/instructions/n8n-io/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/n8n-io/skills/claude-md/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.
<a href="https://agentmods.dev/instructions/n8n-io/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/n8n-io/skills/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01914 | $0.01914 |
| Opus 5 | $0.00957 | $0.00957 |
| Sonnet 5 | $0.00383 | $0.00383 |
| Haiku 4.5 | $0.00191 | $0.00191 |
Grade A, and why
skills CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
The contributing guide for everyone editing this repo: humans, AI agents, both. The rules apply regardless of who's writing.
Open an issue first
Before writing any code, open an issue describing what you want to change and why. PRs without a linked issue get closed without review.
The earn-its-place test
Every word in a skill costs context for the LLM that reads it. Keep a sentence only if it does at least one of these:
- Constrains the meaning of a term used later. Example: "in n8n, an agent specifically means the LangChain Agent node with its four sub-node slots." Disambiguates a polysemous word the rest of the doc relies on.
- Flags a load-bearing assumption. A non-obvious constraint, invariant, platform quirk, or workaround a reader would not derive from the surrounding code.
- Explains the why behind a rule. The why is what lets the model judge edge cases. "Use credentials, not text fields" is a rule. "Because text fields are stored in plaintext in workflow exports" is the why.
If a sentence does none of those, cut it.
What to cut, aggressively
- Things frontier models already know. Generic definitions ("a webhook is..."), textbook framings of well-known concepts, basic programming explanations. Keep n8n-specific or project-specific framings, but cut the textbook part.
- Restated content. Anything restated from the frontmatter
description, anything said twice across sections, "as mentioned above" callbacks. - Useless intros. "This skill covers X." "In this guide we will..." "The goal of this document..." The body is loaded only when the skill triggers, by which point the description has already framed the scope. Re-announcing the description in the body is structurally redundant.
- Fluff. Filler transitions, hedging that doesn't change behavior, motivational preamble without concrete consequence, "remember to be careful" without specifics.
What to preserve
- Examples that anchor an abstract rule. Cutting an example to shorten a rule usually loses more than it saves.
- Non-obvious gotchas, even ones that read as basic. "The UI shows 'no items exist' when items do exist" sounds trivial, but it saves an hour of debugging.
- The why behind every rule. If a rule has no why, write the why or cut the rule.
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.
- 9d ago First seen · 94 lines · 1,914 tokens per session scan A 4e86a9f34432
skills CLAUDE.md is an instructions file published in the GitHub repository n8n-io/skills (482 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,914 tokens to every session, about $0.0096 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.