A guided check for n8n workflows that start from a schedule, manual action, or error event instead of an HTTP request. It helps you start the workflow in n8n's web interface and then inspect its run.

Use it to test a non-HTTP n8n workflow and inspect the resulting execution without changing the n8n instance.

The command-line tester cannot start these kinds of workflows, so testing normally requires finding the right web page and run identifier by hand.

test-manual — Skill for Claude Code by neurawork-git

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.

Any agent

npx skills add neurawork-git/n8n-autopilot --skill test-manual

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/neurawork-git/n8n-autopilot/test-manual/github.svg)](https://agentmods.dev/skills/neurawork-git/n8n-autopilot/test-manual)

Your own site

<a href="https://agentmods.dev/skills/neurawork-git/n8n-autopilot/test-manual"><img src="https://agentmods.dev/badge/skills/neurawork-git/n8n-autopilot/test-manual/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/neurawork-git/n8n-autopilot/test-manual"><img src="https://agentmods.dev/badge/skills/neurawork-git/n8n-autopilot/test-manual.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 706 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.

Model	Per session	Once invoked
Fable 5.1	$0.00063	$0.00706
Opus 5	$0.00032	$0.00353
Sonnet 5	$0.00013	$0.00141
Haiku 4.5	$0.00006	$0.00071

Measured 12d ago against content hash e0354e9e2d87, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

test-manual 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 12d 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.

skills/test-manual/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test a Non-HTTP-Trigger Workflow

npx n8nac test can only fire webhook / chat / form triggers. For schedule, manual, and errorTrigger workflows the run must be started in the n8n UI. This skill packages that detour into one flow so you do not have to hand-assemble the URL and the execution get command each time.

Why this exists: non-HTTP manual-test detours were the single most frequent friction observed in real production runs.

Steps

1. Resolve the workflow id

Use $ARGUMENTS as the workflow id. If empty, ask the user (or extract it from the .workflow.ts they name: grep -oE "id:[[:space:]]*['\"][A-Za-z0-9]{10,}['\"]" <file> | head -1).

2. Confirm it really is a non-HTTP trigger

npx n8nac test-plan <workflowId> --json

If triggerType is webhook / chat / form (i.e. testable: true) → STOP and tell the user to use npx n8nac test <workflowId> (or /n8n-autopilot:deploy) instead — no manual step needed.
If schedule / manual / errorTrigger → continue.

3. Resolve the UI URL (never string-concat the host)

npx n8nac workflow present <workflowId> --json

Surface a clear instruction to the user with the URL from the output:

▶  MANUAL EXECUTION REQUIRED — <triggerType> trigger (n8nac cannot fire it)

Open n8n UI:  <url from `n8nac workflow present`>
Click:        "Execute Workflow"
Then paste the execution-id here (top of the execution, or from the URL).

4. Wait for the execution-id

Stop and wait for the user to report the execution-id. Do not fabricate one.

5. Inspect the run

npx n8nac execution get <executionId> --include-data

Read the output and report: success/failure, which node failed (if any), and the relevant output/error data. If it failed on a wiring error, hand back to /n8n-autopilot:deploy's fix loop.

Notes

Read-only against the instance — this skill only resolves URLs and reads execution data. The actual run is started by the user in the UI.
If the user reports no execution-id (the run did not start), re-check the URL and that the user clicked "Execute Workflow" (not "Save").

Read the full file on GitHub · 70 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.

12d ago First seen · 70 lines · 63 tokens per session scan A e0354e9e2d87

Subscribe to this mod's changes

test-manual is a skill published in the GitHub repository neurawork-git/n8n-autopilot (18 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 706 once invoked, about $0.0003 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.

Claude Code Testing Workflow Automation claude-code-plugin mcp n8n n8nac

test-workflow

Universal n8n workflow testing via webhook or sub-workflow pattern.

anatolykoptev/n8n-mcp-agent · 17 tokens

n8n-testing

Testing workflow for n8n. Use before activating workflows in production. Covers manual testing, data pinning, execution modes, and validation.

anatolykoptev/n8n-mcp-agent · 33 tokens

live-preview

Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.

SethGammon/Citadel · 40 tokens

brooks-sweep

Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…

hyhmrright/brooks-lint · 178 tokens

api-testing

HTTP API testing for TypeScript (Supertest) and Python (httpx, pytest). Test REST APIs, GraphQL, request/response validation, authentication, and error handling.

secondsky/claude-skills · 39 tokens

bun-jest-migration

Use when migrating from Jest to Bun's test runner, import compatibility, mocks, and config.

secondsky/claude-skills · 25 tokens