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.
npx skills add masteranime/n8n-claude-skills --skill workflow-architectgit clone --depth 1 https://github.com/masteranime/n8n-claude-skillsWrote 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/skills/masteranime/n8n-claude-skills/workflow-architect)<a href="https://agentmods.dev/skills/masteranime/n8n-claude-skills/workflow-architect"><img src="https://agentmods.dev/badge/skills/masteranime/n8n-claude-skills/workflow-architect/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/skills/masteranime/n8n-claude-skills/workflow-architect"><img src="https://agentmods.dev/badge/skills/masteranime/n8n-claude-skills/workflow-architect.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 | $0.00151 | $0.01486 |
| Opus 5 | $0.00076 | $0.00743 |
| Sonnet 5 | $0.00030 | $0.00297 |
| Haiku 4.5 | $0.00015 | $0.00149 |
Grade A, and why
workflow-architect 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
n8n Workflow Architect
You are designing a production n8n workflow, not a demo. The workflow must survive real data, real failures, and real volume.
Core principles (apply every time)
-
Real node names, not guesses. n8n is strict about capitalization and spacing. Use
Google SheetsnotGooglesheets.HTTP RequestnotHttpRequest.Webhooknotwebhook trigger. If unsure, say so — don't invent. -
Expression syntax is
={{ $json.field }}. The leading=marks the whole field as an expression. Without it, n8n treats the value as a literal string. This is the #1 hallucination source. -
Every external call needs an error branch. Wrap API calls in an
IFor usecontinueOnFail: true+ a downstreamIFthat checks{{ $json.error }}. Never assume third parties don't fail. -
Idempotency by default. If the workflow could be retriggered (webhook, cron, polling), include a checkpoint — a MySQL/Postgres lookup on a natural key, or a
Google Sheetsrow check. Reference themysql-checkpointingskill for the pattern. -
Sub-workflows for reuse. If logic exceeds ~8 nodes or is called from multiple places (e.g., error handling, notifications), extract into an
Execute Workflowsub-workflow.
Workflow design process
Follow these steps in order. Skipping steps produces demo-quality output.
Step 1: Clarify the trigger
Ask (or infer) exactly ONE trigger type:
| Trigger | Use when |
|---|---|
Webhook |
External system pushes events (Stripe, Meta, custom APIs) |
Schedule Trigger |
Recurring jobs (daily reports, hourly polls) |
Manual Trigger |
Admin-triggered, testing |
Form Trigger |
User-facing intake |
Chat Trigger |
Conversational agents |
Execute Workflow Trigger |
Called by another workflow |
Webhooks in production need: signature verification (HMAC), idempotency key extraction, and a 200 response within 3s (use Respond to Webhook early, process async).
Step 2: Map the happy path
Draft the node sequence as a numbered list BEFORE writing JSON. Each node gets:
- Node type (exact n8n name)
- Purpose (one sentence)
- Key config (the one or two parameters that matter)
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 122 lines · 151 tokens per session scan A aca3df9658d9
workflow-architect is a skill published in the GitHub repository masteranime/n8n-claude-skills (32 stars, last pushed 4mo ago), licensed MIT. It adds 151 tokens to every session and 1,486 once invoked, about $0.0008 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.
Other skills, from other repositories
site-audit
Use when user asks to audit a website, review all pages, check for broken links, capture full site state, or do a comprehensive product review.
kaboom-connection-guard
Use when a tool call fails with "extension not connected", the daemon is unreachable, or browser telemetry stops arriving.
regression-test
Use when user has fixed a bug and needs a test that proves it stays fixed, or when a failure needs to be captured as a reproducible test case.
ux-audit
Use when user asks to review UX quality, check accessibility compliance, audit visual hierarchy, or evaluate information architecture on a page.
automate
Use when user asks to automate browser actions, click buttons, fill forms, navigate pages, run a sequence of browser steps, or build a repeatable workflow.
performance
Use when user reports slow page load, asks about Core Web Vitals, wants before/after performance comparison, or needs to profile a specific interaction.