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 anatolykoptev/n8n-mcp-agent --skill n8n-testinggit clone --depth 1 https://github.com/anatolykoptev/n8n-mcp-agentWrote 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/anatolykoptev/n8n-mcp-agent/n8n-testing)<a href="https://agentmods.dev/skills/anatolykoptev/n8n-mcp-agent/n8n-testing"><img src="https://agentmods.dev/badge/skills/anatolykoptev/n8n-mcp-agent/n8n-testing/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/anatolykoptev/n8n-mcp-agent/n8n-testing"><img src="https://agentmods.dev/badge/skills/anatolykoptev/n8n-mcp-agent/n8n-testing.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 | $0.00033 | $0.01541 |
| Opus 5 | $0.00016 | $0.00771 |
| Sonnet 5 | $0.00007 | $0.00308 |
| Haiku 4.5 | $0.00003 | $0.00154 |
Grade A, and why
n8n-testing scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST https://your-n8n.com/webhook/test-path \ How it starts
The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
n8n Testing Skill
This skill ensures workflows are thoroughly tested before production activation.
When to Activate
- Before activating any workflow
- After making changes to existing workflows
- When debugging failed executions
- Before deploying to production environment
Execution Modes
Manual Execution (Development)
Use for testing during development:
- Run workflows with "Execute Workflow" button
- Keep workflow Inactive while developing
- Iterate and test node by node
- See data transformations in real-time
Production Execution (Live)
Workflows run automatically when:
- Set to Active
- Triggered by webhooks, schedules, or events
Rule: Never develop on Active workflows.
Testing Workflow
1. Data Pinning
Pin data to ensure consistent testing:
Benefits:
- Avoid repeated requests to external systems
- Save API rate limits during development
- Consistent data for all test runs
- No need to trigger external events
How to Pin:
- Execute node once to get real data
- Click "Pin" on node output
- Future executions use pinned data
Limitations:
- Only for nodes with single main output
- Not available in production executions
- Development feature only
2. Node-by-Node Testing
Test each node individually:
Step 1: Test Trigger node
↓ Verify output
Step 2: Test Processing node
↓ Verify transformation
Step 3: Test Output node
↓ Verify final result
3. Test with Sample Data
Create test data in Code node:
// Test data for development
return [
{
json: {
id: 'test-001',
email: '[email protected]',
amount: 100,
status: 'pending'
}
},
{
json: {
id: 'test-002',
email: 'invalid-email', // Test validation
amount: -50, // Test edge case
status: 'active'
}
}
];
4. Edge Case Testing
Test these scenarios:
| Scenario | Test Data | Expected |
|---|---|---|
| Empty input | [] |
Graceful handling |
| Null values | { email: null } |
Validation error |
| Large payload | 1000+ items | No timeout |
| Invalid format | { email: 'not-email' } |
Rejection |
| Missing fields | { id: '1' } |
Validation error |
| Special characters | { name: '<script>' } |
Sanitized |
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 · 301 lines · 33 tokens per session scan A c67904202882
n8n-testing is a skill published in the GitHub repository anatolykoptev/n8n-mcp-agent (0 stars, last pushed 6mo ago), licensed MIT. It adds 33 tokens to every session and 1,541 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
plugin-testing
The ONLY supported way to test changes to the n8n-autopilot plugin itself: commit → push to the private repo → install FROM that repo → restart → verify registration. Use whenever a plugin change (agent, skill, hook, script) must be exercised in a real session. Hard rule: no cache hand-copying, no directory-pointer…
test-manual
Test a non-HTTP-trigger workflow (schedule, manual, errorTrigger) that n8nac cannot fire from the CLI. Resolves the n8n UI URL, waits for you to run it and report the execution-id, then inspects the run. Read-only against the instance.
api-testing
Testing patterns for MCP tool/resource handlers using createMockContext and Vitest. Covers mock context options, handler testing, McpError assertions, format testing, Vitest config setup, and test isolation conventions.
field-test
Exercise tools, resources, and prompts against a live HTTP server via MCP JSON-RPC over curl. Starts the server, surfaces the catalog, runs real and adversarial inputs, and produces a tight report with concrete findings and numbered follow-up options. Use after adding or modifying definitions, or when the user asks to…
add-test
Scaffold a test file for an existing tool, resource, or service. Use when the user asks to add tests, improve coverage, or when a definition exists without a matching test file.
n8n-agents
Design n8n AI agents the right way. Use when building or editing any @n8n/n8n-nodes-langchain. AI node — an AI Agent, LLM chain, Text Classifier, or Information Extractor — and whenever the user mentions AI agents, LLM with tools, tool calling, $fromAI, system prompts, agent memory, sessionId, structured/JSON output…