n8n-as-code is a toolkit for building, editing, checking, deploying, and debugging n8n workflows from an editor or terminal. It helps developers and AI agents work with n8n workflows using node schemas, templates, version-controlled synchronization, and TypeScript files. Its catalogue add-ons help agents operate n8n and author workflows.
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.
git clone --depth 1 https://github.com/EtienneLescot/n8n-as-codeWrote 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/rules/etiennelescot/n8n-as-code/n8n-workflow-format)<a href="https://agentmods.dev/rules/etiennelescot/n8n-as-code/n8n-workflow-format"><img src="https://agentmods.dev/badge/rules/etiennelescot/n8n-as-code/n8n-workflow-format/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/rules/etiennelescot/n8n-as-code/n8n-workflow-format"><img src="https://agentmods.dev/badge/rules/etiennelescot/n8n-as-code/n8n-workflow-format.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 | $0.00000 | $0.00208 |
| Opus 5.5 | $0.00000 | $0.00083 |
| Sonnet 5.5 | $0.00000 | $0.00042 |
| Haiku 4.5 | $0.00000 | $0.00021 |
Grade A, and why
n8n-workflow-format 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 1mo 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.
What it actually says
When editing an n8n workflow file:
- Treat
.workflow.tsas the source of truth. - Keep the TypeScript decorator structure with
@workflow,@node, and@links. - Preserve the
<workflow-map>block at the top of the file. - Pull the workflow from n8n before editing when the workspace is initialized.
- Push the workflow back after editing.
- Use exact node schema information from
n8nac skills node-info <nodeName>or the equivalent MCP tool. - Never invent node parameters, connection types, or credential fields.
- Regular node connections use
.out(0).to(target.in(0)). - AI sub-node connections use
.uses(). ai_toolandai_documentvalues are arrays; most other AI connections are single refs.
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.
- 1mo ago First seen · 20 lines · 0 tokens per session scan A d307bc238228
n8n-workflow-format is a cursor rule published in the GitHub repository EtienneLescot/n8n-as-code (1,628 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 208 tokens. 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 cursor rules, from other repositories
bootstrap-alwayson
Minimal always-required LLM fixes.
cursor_rules
AI-powered development workflow and standards.
read-xlsx
Reading, writing, diffing, and repairing spreadsheets (.xlsx) for AI agents via the xfa MCP server.
ai-skills
Operate the AI-SKILLS library autonomously, selecting the right skill or prompt for each task.
team-auth
Agent-requested: invoke when working on team-auth. ContextOS rules for team-auth.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.