What is n8n-pilot CLAUDE.md?

A set of instructions for a coding-agent framework built around Python utilities, automatic triggers, and separate Claude and Codex agents sharing state.

Use it to initialize sessions, run background protocol tasks, detect completed work, and return structured JSON results.

It gives the agents a defined startup and completion process while reducing unnecessary terminal output.

How AI-agents-incubator/n8n-pilot configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to AI-agents-incubator/n8n-pilot. 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/AI-agents-incubator/n8n-pilot/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/AI-agents-incubator/n8n-pilot

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/ai-agents-incubator/n8n-pilot/claude-md/github.svg)](https://agentmods.dev/instructions/ai-agents-incubator/n8n-pilot/claude-md)

Your own site

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

Per session 2,965 This file is loaded in full into every session.

When invoked 2,965 The same file — it is already loaded in full.

Security scan B 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.

Model	Per session	Once invoked
Fable 5.1	$0.02965	$0.02965
Opus 5.5	$0.01186	$0.01186
Sonnet 5.5	$0.00593	$0.00593
Haiku 4.5	$0.00297	$0.00297

Measured 2mo ago against content hash 5abd1255a2b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

n8n-pilot CLAUDE.md scanned grade B 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 2mo 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat .claude/migration-context.json 2>/dev/null

CLAUDE.md · 380 lines

How it starts

The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — AI Agent Instructions

Framework: Claude Code Starter v4.0.2 Type: Meta-framework extending Claude Code capabilities

Architecture: Python Framework Core + Silent Mode Protocols

NEW in v4.0.0: Dual-agent architecture (Claude + Codex) with shared state contract and additive adapters.

Previous versions:

v2.4.1-v2.5.1: Modular protocol files (5-6 min, verbose output)
v2.6.0: Optimized protocols (15-30s, compact output)
v2.7.0: True silent mode (bash background tasks)

Why Python utility:

Bash = 10 separate commands = terminal spam (task notifications)
Python = 1 command, structured JSON output, true silent execution
Faster: 359ms vs minutes (1000x+ improvement)
Better: parallel execution, easy debugging, cross-platform

Protocol Files:

.claude/protocols/cold-start-silent.md — Invisible session initialization
.claude/protocols/completion-silent.md — Invisible sprint finalization
.claude/protocols/auto-triggers.md — Automatic task completion detection

Python Utility:

src/framework-core/main.py — CLI entry point
python3 src/framework-core/main.py cold-start — Execute all tasks
Returns JSON to stdout (AI parses, user sees nothing)
Logs to .claude/logs/framework-core/

Key improvements in v4.0.0:

Zero terminal noise: JSON output instead of task notifications
1000x faster: 359ms vs minutes execution time
True silent mode: User sees NOTHING unless error/confirmation needed
Parallel execution: Python threading for all tasks
Cross-platform: Works on Windows native (no WSL)
Easy debugging: Proper code structure vs bash scripts

Triggers

"start", "начать": → Execute Cold Start Protocol (silent mode)

Manual Completion: "/fi", "заверши", "завершить", "finish": → Execute Completion Protocol (silent mode)

Auto-Trigger Detection (NEW in v2.7.0): Framework automatically detects task completion and triggers Completion Protocol:

Explicit keywords (instant trigger):

"готово", "сделано", "завершил", "закончил", "done", "completed"
Framework runs Completion automatically (or asks once, based on config)

Read the full file on GitHub · 380 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.

2mo ago First seen · 380 lines · 2,965 tokens per session scan B 5abd1255a2b5

Subscribe to this mod's changes

n8n-pilot CLAUDE.md is an instructions file published in the GitHub repository AI-agents-incubator/n8n-pilot (30 stars, last pushed 29d ago), licensed MIT. It adds 2,965 tokens to every session, about $0.0119 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.

Building agents

n8n-pilot CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
n8n-pilot CLAUDE.mdAI-agents-incubator/n8n-pilot	Instructions file	30	29d ago	MIT	B	2,965	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

n8n-pilot: Instructions file for Claude Code