labview-mcp: Agent for Claude Code

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

labview-vitester-unit-test is an agent for Claude Code from Zuehlke/labview-mcp. It costs 293 tokens per session (3,325 once invoked), scanned A, a copy of labview-lunit-unit-test, MIT.

An agent that writes and runs unit tests with JKI VI Tester, a LabVIEW testing framework. It is an experimental scaffold and first checks whether VI Tester is usable on the computer.

In plain words
What is it for?
Use it only when VI Tester tests are explicitly requested, after checking LabVIEW status and the framework files.
Why use it?
It prevents work from proceeding when the requested testing framework is not installed or usable, and avoids confusing it with Caraya, the project’s default framework.

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-vitester-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-vitester-unit-test

README.md
[![agentmods](https://agentmods.dev/badge/agents/zuehlke/labview-mcp/labview-vitester-unit-test/github.svg)](https://agentmods.dev/agents/zuehlke/labview-mcp/labview-vitester-unit-test)
Your own site
<a href="https://agentmods.dev/agents/zuehlke/labview-mcp/labview-vitester-unit-test"><img src="https://agentmods.dev/badge/agents/zuehlke/labview-mcp/labview-vitester-unit-test/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.

agentmods 80×15 button for labview-vitester-unit-test

Your own site · 80×15
<a href="https://agentmods.dev/agents/zuehlke/labview-mcp/labview-vitester-unit-test"><img src="https://agentmods.dev/badge/agents/zuehlke/labview-mcp/labview-vitester-unit-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 293 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,325 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 88% copy Near-identical to another mod 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 $0.00293 $0.03325
Opus 5 $0.00147 $0.01663
Sonnet 5 $0.00059 $0.00665
Haiku 4.5 $0.00029 $0.00332

Measured yesterday against content hash 41e202a7f40e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

labview-vitester-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 yesterday.

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

This is a copy

88% identical to labview-lunit-unit-test — 292 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/labview-vitester-unit-test.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LabVIEW VI Tester Unit Test Agent

🚧 THIS IS A SCAFFOLD. Nothing below the framework-independent rules has been measured. docs/labview-unit-testing.md §5 records the state plainly: "VI Tester was not tried." The user stated on 2026-08-29 that it is not installed on this station. Files do sit under vi.lib\addons\_JKI Toolkits\VI Tester (TestCase.llb, TestRunner.llb, VI Tester API.llb, palette .mnu files), which is consistent with §5's note that both JKI frameworks ship there — shipping and being usable are different things, and Phase 0 settles which this is.

Do not treat any target spelling, class name or terminal name in this file as verified. There are deliberately almost none.

🧭 Caraya is the default framework. If the user did not explicitly ask for VI Tester, you are the wrong agent — labview-caraya-unit-test is the one to use.

Phase 0 — Is this framework usable at all? STOP if not.

Do this before writing a single line of AIXML. It is cheap and it is the whole reason this file exists as a scaffold rather than a recipe.

  1. lvai_status, then confirm the framework's files are present: vi.lib\addons\_JKI Toolkits\VI Tester.
  2. Presence is not availability. Establish that a VI in it can actually be called — one throwaway lvai_validate_aixml with a Call to a VI Tester target. An unresolvable target is named in the message; a resolved one only complains about unwired terminals.
  3. Expect the palette index to miss it. lvai_palette_index scans menus\ and LVAddons\; JKI's .mnu files live under vi.lib\addons\_JKI Toolkits\dynamic_palette\, which is neither. A miss there is not proof a call is illegal — measured for Caraya, and the same applies here.
  4. The .llb problem is the one to expect, and it is measured. CLAUDE.md §9 of the AIXML reference: a VI inside an .llb does not resolve by bare name. VI Tester ships as .llbs (TestCase.llb, TestRunner.llb, …), where Caraya ships as a .lvlib whose members resolve by their Caraya.lvlib\3A… qualifier. So the first thing to find out is what qualifier, if any, reaches a VI Tester VI. Get it the way the Caraya spellings were got: export a shipped example that already calls it with lvai_convert_vi_to_aixml and copy target= verbatim.

Read the full file on GitHub · 179 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. yesterday Changed · +12 lines 41e202a7f40e
  2. 5d ago Changed 9bd43256ce26
  3. 10d ago First seen · 167 lines · 293 tokens per session scan A 60613498e2c1

Subscribe to this mod's changes

labview-vitester-unit-test is an agent published in the GitHub repository Zuehlke/labview-mcp (24 stars, last pushed 2d ago), licensed MIT. It adds 293 tokens to every session and 3,325 once invoked, about $0.0015 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to labview-lunit-unit-test, differing in 292 lines, and is treated as a copy.

Related

Other agents, from other repositories