labview-mcp: Agent for Claude Code

.claude/agents/labview-lunit-unit-test.md

labview-lunit-unit-test is an agent for Claude Code from Zuehlke/labview-mcp. It costs 406 tokens per session (5,537 once invoked), scanned A, original, MIT.

An agent scaffold intended to write and run LUnit unit tests for LabVIEW code. Unit tests check small pieces of a program independently; LabVIEW is a visual programming environment.

In plain words
What is it for?
Use it only for explicitly requested LUnit tests in LabVIEW; otherwise, the input identifies a different agent for the repository’s default Caraya framework.
Why use it?
The provided information says LUnit is not installed on the referenced station and that this agent should be used only when LUnit is explicitly requested.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is Zuehlke/labview-mcp's own configuration. It tells Claude Code how to work on labview-mcp 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 labview-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Zuehlke/labview-mcp. 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/Zuehlke/labview-mcp/main/.claude/agents/labview-lunit-unit-test.md
Clone the repo
git clone --depth 1 https://github.com/Zuehlke/labview-mcp

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 labview-lunit-unit-test

README.md
[![agentmods](https://agentmods.dev/badge/agents/zuehlke/labview-mcp/labview-lunit-unit-test.svg)](https://agentmods.dev/agents/zuehlke/labview-mcp/labview-lunit-unit-test)
Your own site
<a href="https://agentmods.dev/agents/zuehlke/labview-mcp/labview-lunit-unit-test"><img src="https://agentmods.dev/badge/agents/zuehlke/labview-mcp/labview-lunit-unit-test.svg" alt="Measured on agentmods" height="20"></a>
Per session 406 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,537 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 $0.00406 $0.05537
Opus 5 $0.00203 $0.02769
Sonnet 5 $0.00081 $0.01107
Haiku 4.5 $0.00041 $0.00554

Measured 2d ago against content hash 1d4a04202fa3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

labview-lunit-unit-test 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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/agents/labview-lunit-unit-test.md · 297 lines

How it starts

The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LabVIEW LUnit Unit Test Agent

LUnit IS INSTALLED AND THE ROUTE IS MEASURED END TO END. Installed 2026-09-01 into C:\Program Files (x86)\National Instruments\LabVIEW 2026 — the 32-bit tree. A class was built from nothing that day, two test methods were added, and LUnit ran them: one Passed, one deliberately wrong one Failed, All Passed? = false, JUnit XML report written.

This file said the opposite until then — "SCAFFOLD, AND THE FRAMEWORK IS NOT ON THIS STATION", from a 2026-08-29 sweep of the 64-bit path that legitimately found nothing. Do not re-derive that conclusion: resolve the install root from the running process (Get-Process LabVIEW | Select-Object Path), never from a guess.

The full recipe, with every measurement, is docs/labview-lunit-testing.md. Read it before Phase 1 — this file is the workflow, that one is the evidence.

🧭 Caraya is the default framework. If the user did not explicitly ask for LUnit, you are the wrong agent — labview-caraya-unit-test is the one to use, and it costs far fewer calls.

Phase 0 — Confirm the station, then read the reference

  1. lvai_status. Then confirm the install root from the running process rather than assuming it:

    powershell -Command "Get-Process LabVIEW | Select-Object -ExpandProperty Path"
    

    There is no 64-bit LabVIEW on this machine. C:\Program Files\National Instruments\ LabVIEW {2023,2024,2025,2026} all exist and each holds exactly one entry, resource — no LabVIEW.exe, no vi.lib, no user.lib. Sweeping them for a toolkit reads exactly like "not installed", and that is how LUnit was once wrongly reported missing.

Read the full file on GitHub · 297 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. 2d ago Changed 1d4a04202fa3
  2. 4d ago Changed · +138 lines · +109 tokens per session eae3ebbf28ab
  3. 8d ago First seen · 159 lines · 297 tokens per session scan A 2ea1bc4f8c22

Subscribe to this mod's changes

labview-lunit-unit-test is an agent published in the GitHub repository Zuehlke/labview-mcp (22 stars, last pushed today), licensed MIT. It adds 406 tokens to every session and 5,537 once invoked, about $0.0020 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.