What is n8n-nodes-claudecode CLAUDE.md?

Repository instructions for developing an n8n community node that connects the Claude Code SDK to n8n workflows. n8n is a tool for connecting automated steps, while the SDK provides the node’s Claude Code integration.

Use them when developing, building, checking, or locally testing the Claude Code n8n node.

They collect the project’s build, formatting, linting, local installation, debugging, and architecture details in one place. This reduces guesswork when changing or testing the node.

How holt-web-ai/n8n-nodes-claudecode configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to holt-web-ai/n8n-nodes-claudecode. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/holt-web-ai/n8n-nodes-claudecode/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/holt-web-ai/n8n-nodes-claudecode

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/holt-web-ai/n8n-nodes-claudecode/claude-md/github.svg)](https://agentmods.dev/instructions/holt-web-ai/n8n-nodes-claudecode/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/holt-web-ai/n8n-nodes-claudecode/claude-md"><img src="https://agentmods.dev/badge/instructions/holt-web-ai/n8n-nodes-claudecode/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/holt-web-ai/n8n-nodes-claudecode/claude-md"><img src="https://agentmods.dev/badge/instructions/holt-web-ai/n8n-nodes-claudecode/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 744 This file is loaded in full into every session.

When invoked 744 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00744	$0.00744
Opus 5	$0.00372	$0.00372
Sonnet 5	$0.00149	$0.00149
Haiku 4.5	$0.00074	$0.00074

Measured 10d ago against content hash 07b18233b3c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

n8n-nodes-claudecode 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 10d 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.

CLAUDE.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 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.

Common Commands

Development

npm run dev - Run TypeScript compiler in watch mode for development
npm run build - Build the project (clean dist, compile TypeScript, copy icons)
npm run format - Format code using Prettier
npm run lint - Run ESLint to check code quality
npm run lintfix - Auto-fix linting issues where possible

n8n Integration

Install locally: npm link then n8n start to test the node
The node appears in n8n UI under "Claude Code" category
Debug output available when Debug option is enabled in node parameters

Architecture Overview

This is an n8n community node that integrates Claude Code SDK into n8n workflows. The architecture consists of:

Main Node Implementation (nodes/ClaudeCode/ClaudeCode.node.ts)
- Implements INodeType interface from n8n
- Provides Query and Continue operations
- Handles Claude Code SDK initialization and message processing
- Manages tool availability and project path configuration
Tool System
- Dynamic tool enabling/disabling based on user configuration
- Supports: Bash, Edit/MultiEdit, Read/Write, Web operations, Todo management
- MCP servers supported via Claude's native configuration system (.claude/settings.local.json)
Output Handling
- Multiple output formats: structured JSON, messages array, or plain text
- Streaming support with abort signal handling
- Debug mode for troubleshooting
Project Path Support (v0.2.0+)
- Configure working directory via projectPath parameter
- Allows Claude Code to run in specific project directories
- Enables access to code repositories without changing n8n's working directory

Key Development Patterns

n8n Node Structure

All node logic resides in ClaudeCode.node.ts
Parameters defined using n8n's declarative schema
Error handling follows n8n patterns with NodeOperationError
Supports both single execution and streaming responses

Read the full file on GitHub · 86 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.

10d ago First seen · 86 lines · 744 tokens per session scan A 07b18233b3c5

Subscribe to this mod's changes

n8n-nodes-claudecode CLAUDE.md is an instructions file published in the GitHub repository holt-web-ai/n8n-nodes-claudecode (98 stars, last pushed 3mo ago), licensed MIT. It adds 744 tokens to every session, about $0.0037 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.

Building agents

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

n8n-nodes-claudecode: Instructions file for Claude Code