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.
npx agentmods add instructions/czlonkowski/n8n-skills/claude-mdgit clone --depth 1 https://github.com/czlonkowski/n8n-skillsWhat 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 | $0.02609 | $0.02609 |
| Opus 5 | $0.01305 | $0.01305 |
| Sonnet 5 | $0.00522 | $0.00522 |
| Haiku 4.5 | $0.00261 | $0.00261 |
Grade A, and why
n8n-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 yesterday.
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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This is the n8n-skills repository - a collection of Claude Code skills designed to teach AI assistants how to build flawless n8n workflows using the n8n-mcp MCP server.
Repository: https://github.com/czlonkowski/n8n-skills
Purpose: 14 complementary skills that provide expert guidance on using n8n-mcp MCP tools effectively for building n8n workflows, plus deploying the self-hosted n8n that runs them.
Architecture:
- n8n-mcp MCP Server: Provides data access (800+ nodes, validation, templates, workflow management)
- Claude Skills: Provides expert guidance on HOW to use MCP tools
- Together: Expert workflow builder with progressive disclosure
Repository Structure
n8n-skills/
├── README.md # Project overview with video
├── LICENSE # MIT License
├── skills/ # Individual skill implementations
│ ├── n8n-expression-syntax/
│ ├── n8n-mcp-tools-expert/
│ ├── n8n-workflow-patterns/
│ ├── n8n-validation-expert/
│ ├── n8n-node-configuration/
│ ├── n8n-code-javascript/
│ ├── n8n-code-python/
│ ├── n8n-code-tool/
│ ├── n8n-error-handling/
│ ├── n8n-binary-and-data/
│ ├── n8n-subworkflows/
│ ├── n8n-agents/
│ ├── n8n-multi-instance/
│ ├── n8n-self-hosting/ # Deployment/ops skill (deploy n8n to a VM); not in the router/hooks flow
│ └── using-n8n-mcp-skills/ # Always-on router skill (loaded by SessionStart hook)
├── hooks/ # Enforcement layer: hooks.json + SessionStart/PreToolUse/PostToolUse scripts
├── evaluations/ # Test scenarios for each skill
├── docs/ # Documentation
├── dist/ # Build output (gitignored — zips ship as GitHub Release assets, never committed; committed zips broke Desktop/Cowork plugin installs)
├── NOTICES # Attribution for Apache-2.0 material adapted from n8n-io/skills
└── .claude-plugin/ # Claude Code plugin configuration
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.
- yesterday First seen · 224 lines · 2,609 tokens per session scan A 2a78bab91866
n8n-skills CLAUDE.md is an instructions file published in the GitHub repository czlonkowski/n8n-skills (6,153 stars, last pushed 3d ago), licensed MIT. It adds 2,609 tokens to every session, about $0.0130 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
n8n-starter CLAUDE.md
Instructions for gabry-ts/n8n-starter, covering claude.md, project overview, repository structure, workflow files and credential management.
n8n-autopilot CLAUDE.md
Instructions for neurawork-git/n8n-autopilot, covering n8n workflow development — n8n-autopilot plugin, knowledge skills — read before inventing cli surface, cheat-sheet — user asks x → run y, hook gates (enforced by pretooluse) and setup.
Tutorial_AwesomeModernCPP AGENTS.md
Instructions for Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPP, covering agents.md, 这是什么, 通用 essentials(所有 agent 必读) and 你来做什么?(按场景路由).
ab900 CLAUDE.md
Instructions for timothywarner-org/ab900, covering claude.md, repository purpose, architecture, commands and 2. non-ascii punctuation -- must return zero.
agentconfig.org AGENTS.md
Instructions for agentconfig/agentconfig.org, covering agent instructions for agentconfig.org, project overview, target audience, site structure and tech stack.
canvas-lms-mcp AGENTS.md
Instructions for bruchris/canvas-lms-mcp, covering agents.md — canvas lms mcp server, quick start, run with npx (no install needed), or install globally and architecture.