n8n-decanter AGENTS.md

The main instruction guide for the n8n-decanter CLI project. It is the single source for how coding agents should work, while PLAN.md describes what the CLI is.

In plain words
What is it for?
Use it when changing n8n-decanter to follow its response style, permission checks, session labels, planning process, documentation duties, commands, and repository workflow.
Why use it?
It prevents rules from being duplicated or drifting between agent-specific files and keeps work practices separate from the product design.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/buttjer/n8n-decanter/agents-md
Clone the repo
git clone --depth 1 https://github.com/buttjer/n8n-decanter

Made for: Codex, OpenCode.

Per session 14,018 This file is loaded in full into every session.
When invoked 14,018 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.14018 $0.14018
Opus 5 $0.07009 $0.07009
Sonnet 5 $0.02804 $0.02804
Haiku 4.5 $0.01402 $0.01402

Measured yesterday against content hash 383e6514b2c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

n8n-decanter AGENTS.md scanned grade A 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

directory in one call — `curl -sL "https://api.github.com/repos/n8n-io/n8n/contents/<dir>?ref=<tag>" | jq -r '.[].name'` — instead of looping `curl … -w %{http_code}` over guessed paths.
AGENTS.md · 819 lines

How it starts

The opening of the file, as written. The whole thing — 819 lines — stays where its author put it; the contents beside it link to each section on GitHub.

n8n-decanter — agent & project guide (single source of truth)

This file is the single source of truth for coding agents working on the n8n-decanter CLI itself (not on a synced workflow dir — that's the template's AGENTS.md). It is tool-agnostic: Codex and opencode read it natively, and Claude Code reads it through a one-line import in CLAUDE.md. Everything — response style, project rules, changelog/docs/backlog duties, git workflow, commands, architecture, and the shared recipes — lives here; keep the rules in one place and let the per-agent files stay thin pointers.

PLAN.md is a separate, complementary source of truth: it is the CLI's design document (data model, flows, past decisions). This file governs how to work on the repo; PLAN.md governs what the CLI is. Keep both current and don't let either drift from the code.

Response style

  • Very compact — no long conclusions or wrap-up prose.
  • Prefer bullet points over paragraphs.
  • Highlight important things and decisions so they stand out.

Session labels: [NN] short name (plan work) / [MISC] short name

Every session gets a label so concurrent sessions stay legible:

  • Task maps to a numbered backlog Plan → [NN] <name> — the bare plan number in brackets (e.g. [30] agent ergonomics).
  • Task has no plan → [MISC] <name> (e.g. [MISC] plans reorg).

<name> is very short and precise — 2–5 words describing the actual work.

An agent can't rename its own session — there is no model-invokable rename in Claude Code (/rename is a human-only slash command). So the agent's job is to surface the exact command for the user to paste: as soon as the label is known, print a one-liner such as — Run /rename [30] agent ergonomics — so the human can apply it in one keystroke. Re-prompt when the work shifts enough that the name no longer fits.

What this is

Standalone CLI that keeps the Code-node source of n8n workflows in git in a folder-per-workflow layout: Code node sources become individual .js/.ts files, synced with the instance over n8n's built-in MCP server (Plan 32 — draft-first, code-only; workflow structure stays n8n's job, mirrored into a read-only workflow.json snapshot). PLAN.md is the design document and source of truth — it also records past decisions/observations so the project could be rebuilt from it.

Read the full file on GitHub · 819 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.

  1. yesterday First seen · 819 lines · 14,018 tokens per session scan A 383e6514b2c4

Subscribe to this mod's changes

n8n-decanter AGENTS.md is an instructions file published in the GitHub repository buttjer/n8n-decanter (2 stars, last pushed yesterday), licensed MIT. It adds 14,018 tokens to every session, about $0.0701 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.