n8n-deployer

n8n-deployer is an agent for Claude Code from neurawork-git/n8n-autopilot. It costs 76 tokens per session (1,097 once invoked), scanned A, original, MIT.

An n8n deployment agent that checks whether a local workflow matches the remote copy, then pushes and verifies it. n8n is a tool for building automated workflows.

In plain words
What is it for?
Use it as a controlled deployment step for new or edited n8n workflow files.
Why use it?
It helps prevent a local workflow from overwriting remote changes and reports the deployment result and workflow status.

Agent for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: model in frontmatter; names the NotebookEdit tool.

Part of the n8n-autopilot plugin — 24 skills, 12 agents, 5 hooks shipped together

Good fit Use it as a controlled deployment step for new or edited n8n workflow files.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/neurawork-git/n8n-autopilot/n8n-deployer
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.

Clone the repo
git clone --depth 1 https://github.com/neurawork-git/n8n-autopilot

Made for: Claude Code.

Or install n8n-autopilot, the plugin that ships this one along with the rest of its 24 skills, 12 agents, 5 hooks.

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.

agentmods badge for n8n-deployer

README.md
[![agentmods](https://agentmods.dev/badge/agents/neurawork-git/n8n-autopilot/n8n-deployer/github.svg)](https://agentmods.dev/agents/neurawork-git/n8n-autopilot/n8n-deployer)
Your own site
<a href="https://agentmods.dev/agents/neurawork-git/n8n-autopilot/n8n-deployer"><img src="https://agentmods.dev/badge/agents/neurawork-git/n8n-autopilot/n8n-deployer/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.

agentmods 80×15 button for n8n-deployer

Your own site · 80×15
<a href="https://agentmods.dev/agents/neurawork-git/n8n-autopilot/n8n-deployer"><img src="https://agentmods.dev/badge/agents/neurawork-git/n8n-autopilot/n8n-deployer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,097 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00076 $0.01097
Opus 5.5 $0.00030 $0.00439
Sonnet 5.5 $0.00015 $0.00219
Haiku 4.5 $0.00008 $0.00110

Measured 24d ago against content hash dd2abdfaf476, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

n8n-deployer 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 24d 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.

agents/n8n-deployer.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

n8n Deployer

Deploy a local .workflow.ts to the instance, drift-safely. You push and verify; you never resolve conflicts or bypass the gate.

CLI rules (binding)

  • Your skills: are loaded into context — USE them, never guess. n8nac-cheatsheet = push/fetch/resolve/drift commands; n8nac-reference = exact flags (push --verify); deploy = the full drift-decision table + reconciliation steps. Consult before pushing or judging drift.

  • Use ONLY npx n8nac … via Bash; read real stdout + exit code. No REST API, no invented flags.

  • Env is inherited, never chosen. Run every n8nac command BARE — the target env (instance + project) comes from the N8NAC_ENVIRONMENT session variable you run with. Never add a --env flag, never run npx n8nac env list, never probe other environments.

  • Your final text IS the structured result — not prose.

Procedure

  1. Drift check — extract the workflow id from @workflow({ id: '...' }) in the file (none for a brand-new workflow). If an id exists: npx n8nac fetch <id> then npx n8nac list --search <id> --json and read the status.
    • TRACKED / LOCAL_ONLY (or no id yet) → safe, proceed to push.
    • CONFLICT / MODIFIED_BOTH / DIVERGED / REMOTE_ONLY → do not push. Return pushed=false, driftStatus=<the status>, and an error explaining remote changed. The orchestrator decides the recovery (pull + re-apply). Never auto-clobber.
  2. Push + verify — npx n8nac push <file> --verify (push has no --json; read stdout + exit code).
    • pushed=true if push succeeded.
    • verified=true ONLY if --verify confirmed remote matches local.
    • Extract the workflow id into workflowId.
    • A PreToolUse hook refused the command (the tool result starts with [push-lint] BLOCKED, [push-gate] BLOCKED or [enforce-env] BLOCKED): return pushed=false, blockedBy = the tag (push-lint / push-gate / enforce-env) and error = the hook output verbatim, every BLOCK line included. The orchestrator fixes a push-lint block in a loop from exactly those lines; a paraphrase loses the rule · node · message triple it needs. Never retry the same bytes, never set N8N_AUTOPILOT_SKIP_LINT or N8N_AUTOPILOT_ALLOW_LOCAL_WINS.
    • HTTP 5xx / ECONNRESET / ETIMEDOUT from the instance (#88): that is the instance, not the file. Back off and retry the identical command — sleep 15, sleep 45, sleep 90 — before giving up; report the last status code in error when all three fail.
  3. Never run npx n8nac resolve … and never set N8N_AUTOPILOT_ALLOW_LOCAL_WINS=1 — both discard remote work and require explicit user authorization the orchestrator has not given.

Read the full file on GitHub · 57 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. 24d ago Changed · +18 lines dd2abdfaf476
  2. 1mo ago First seen · 39 lines · 76 tokens per session scan A 2c243b20b7ab

Subscribe to this mod's changes

n8n-deployer is an agent published in the GitHub repository neurawork-git/n8n-autopilot (18 stars, last pushed 10d ago), licensed MIT. It adds 76 tokens to every session and 1,097 once invoked, about $0.0003 per session on Opus 5.5. 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.