netbox-mcp-server: Skill for Claude Code

.claude/skills/netbox-mcp-testing/SKILL.md

netbox-mcp-testing is a skill for Claude Code from netboxlabs/netbox-mcp-server. It costs 53 tokens per session (1,363 once invoked), scanned A, original, Apache-2.0.

A testing procedure for a NetBox MCP server, which lets an AI assistant work with NetBox, an infrastructure and network-management system. It checks the server’s tools against a live NetBox installation.

In plain words
What is it for?
Use it to verify MCP tools, test common server functions, investigate failures, and report measurable results from a live NetBox environment.
Why use it?
It helps reveal whether the server and its tools work after code or configuration changes. It also focuses on finding causes of failures and recording response times, data sizes, and error counts.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is netboxlabs/netbox-mcp-server's own configuration. It tells Claude Code how to work on netbox-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything netbox-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to netboxlabs/netbox-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/netboxlabs/netbox-mcp-server/main/.claude/skills/netbox-mcp-testing/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/netboxlabs/netbox-mcp-server

Made for: Claude Code.

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 netbox-mcp-testing

README.md
[![agentmods](https://agentmods.dev/badge/skills/netboxlabs/netbox-mcp-server/netbox-mcp-testing.svg)](https://agentmods.dev/skills/netboxlabs/netbox-mcp-server/netbox-mcp-testing)
Your own site
<a href="https://agentmods.dev/skills/netboxlabs/netbox-mcp-server/netbox-mcp-testing"><img src="https://agentmods.dev/badge/skills/netboxlabs/netbox-mcp-server/netbox-mcp-testing.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,363 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00053 $0.01363
Opus 5 $0.00026 $0.00681
Sonnet 5 $0.00011 $0.00273
Haiku 4.5 $0.00005 $0.00136

Measured 8d ago against content hash 5ce6c7a2ef12, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

netbox-mcp-testing 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 8d 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.

.claude/skills/netbox-mcp-testing/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NetBox MCP Testing

When to Use

Use this skill when:

  • After code/configuration changes or new tool additions
  • Validating MCP server functionality with NetBox instance

Prerequisites Check

Before testing, verify:

  1. NetBox MCP server is connected (run /mcp command)
  2. Access to a live NetBox instance with test data exists
  3. NETBOX_URL and NETBOX_TOKEN environment variables are configured

If prerequisites aren't met, testing cannot proceed reliably.

Testing Approach

Execute comprehensive test scenarios autonomously, prioritizing high-value tests first.

Core Testing Mindset

  • Provide clear, actionable feedback - Include specific metrics whenever possible (response times, data sizes, error counts)
  • Investigate immediately - When encountering issues, don't just report symptoms, immediately investigate root causes and propose solutions
  • Be metrics-driven - Quantify results wherever possible rather than relying on qualitative assessments

Core Testing Protocol

1. Pre-Test Analysis

Before beginning testing, assess the current state:

  • Identify what has changed (if this is post-code-change validation)
  • Determine testing scope (all tools vs. specific tools)
  • Establish baseline expectations (what should work?)
  • Note any known issues or limitations in the environment

2. Tool Discovery & Documentation

Discover available NetBox MCP tools by listing them. For each tool, document:

  • Tool name and purpose
  • Expected parameters (required and optional)
  • Return data structure
  • Error conditions

3. Systematic Testing with Performance Monitoring

Apply systematic testing to each discovered tool. Capture response times and metrics throughout.

For each tool, test:

  1. Valid inputs - Execute with typical, valid parameters

    • Verify returns expected data structure
    • Confirm data is from NetBox instance
    • Record response time for baseline
  2. Invalid inputs - Execute with incorrect parameters

    • Verify proper error messages
    • Ensure errors are informative (not generic)
    • Confirm server doesn't crash
    • Note error handling performance

Read the full file on GitHub · 177 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. 8d ago First seen · 177 lines · 53 tokens per session scan A 5ce6c7a2ef12

Subscribe to this mod's changes

netbox-mcp-testing is a skill published in the GitHub repository netboxlabs/netbox-mcp-server (224 stars, last pushed 3d ago), licensed Apache-2.0. It adds 53 tokens to every session and 1,363 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.

Related

Other skills, from other repositories