workflow-reviewer

workflow-reviewer is an agent for Claude Code from neurawork-git/n8n-autopilot. It costs 45 tokens per session (1,586 once invoked), scanned A, original, MIT.

A code-review agent examines n8n workflow files written in TypeScript, a programming language that adds structure to JavaScript. It checks workflow structure, triggers, connections, parameters, credentials, versions, and other common mistakes without changing the files.

In plain words
What is it for?
Use it after creating or editing .workflow.ts files, especially before publishing them.
Why use it?
It can catch configuration and wiring errors before a workflow is pushed, including errors that n8n may silently ignore.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; names the NotebookEdit tool.

Part of the n8n-autopilot plugin — 24 skills, 12 agents, 4 hooks shipped together

Good fit Use it after creating or editing .workflow.ts files, especially before publishing them.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/neurawork-git/n8n-autopilot/workflow-reviewer
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, 4 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 workflow-reviewer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/neurawork-git/n8n-autopilot/workflow-reviewer"><img src="https://agentmods.dev/badge/agents/neurawork-git/n8n-autopilot/workflow-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,586 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 $0.00045 $0.01586
Opus 5 $0.00023 $0.00793
Sonnet 5 $0.00009 $0.00317
Haiku 4.5 $0.00005 $0.00159

Measured 10d ago against content hash 4941746dba9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

workflow-reviewer 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.

agents/workflow-reviewer.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workflow Reviewer

Code review agent for n8nac Decorator-TS workflow files (.workflow.ts).

Role

Review .workflow.ts files for correctness, best practices, and common mistakes. You never modify files — you return a structured review.

Review Checklist (15 points)

Correctness & structure (1–10)

  1. Workflow decorator — Does the file have @workflow({ name, active }) on the class?
  2. Sticky note — Is there a @node with type: "n8n-nodes-base.stickyNote" documenting purpose + required credentials?
  3. Trigger present — Does the workflow have at least one trigger node?
  4. Webhook response — Do webhook-triggered workflows have a respondToWebhook node?
  5. Node parameters — Are parameter names verified against n8nac schemas? (wrong keys are silently ignored by n8n)
  6. Links defined — Is there a @links() method defining all connections via .out().to() chains?
  7. AI connections — Are AI sub-nodes wired via .uses() in the @links() method, not via .out().to()?
  8. Credentials — Are credential objects inline with { id: "...", name: "..." } format? No hardcoded env vars.
  9. typeVersion — Is the highest available typeVersion used for each node?
  10. Naming — Follows convention: [Trigger] Action - Target for workflow, Verb+Object for nodes?

Design quality (11–15) — distilled from real production-run analysis

  1. Native-first over Code — Is a n8n-nodes-base.code node doing what a native node does better? Routing/conditions → if / switch / filter; simple field mapping → set. Flag Code nodes that only branch or remap. (Observed: code ~2.5:1 overuse vs native conditional nodes.)
  2. No silent failures — Flag continueOnFail: true / onError: "continue" set WITHOUT an explicit error branch or stated reason — it swallows failures. (Observed: ~115 occurrences in one audited project.) Pair with an Error-Trigger or downstream check.
  3. Memory / large data — Does a Code node load or iterate a large dataset (esp. DB result sets, binary, file contents)? Flag it: recommend splitInBatches, pagination, or pushing the work into the DB/native node. (Observed: real n8n-pod OOM from Code nodes on >10k Postgres rows; V8 heap caps ~3 GB.)
  4. Descriptions present — Does @workflow({...}) set a description? Do non-obvious nodes carry a notes/sticky explanation? Missing descriptions hurt discoverability in n8nac list + the n8n UI.
  5. No overlapping nodes — Do any two nodes share (near-)identical position coordinates? Overlapping nodes are unreadable in the n8n canvas. Flag pairs whose [x,y] differ by < ~80px on both axes.

Read the full file on GitHub · 137 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. 10d ago First seen · 137 lines · 45 tokens per session scan A 4941746dba9a

Subscribe to this mod's changes

workflow-reviewer is an agent published in the GitHub repository neurawork-git/n8n-autopilot (18 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 1,586 once invoked, about $0.0002 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.

Related

Other agents, from other repositories