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.
curl -O https://raw.githubusercontent.com/Zuehlke/labview-mcp/main/.claude/agents/labview-vitester-unit-test.mdgit clone --depth 1 https://github.com/Zuehlke/labview-mcpWrote 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/agents/zuehlke/labview-mcp/labview-vitester-unit-test)<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.
<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>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 | $0.00320 | $0.07137 |
| Opus 5.5 | $0.00128 | $0.02855 |
| Sonnet 5.5 | $0.00064 | $0.01427 |
| Haiku 4.5 | $0.00032 | $0.00714 |
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 9d 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.
This is a copy
88% identical to labview-lunit-unit-test — 296 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.
How it starts
The opening of the file, as written. The whole thing — 358 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 undervi.lib\addons\_JKI Toolkits\VI Tester(TestCase.llb,TestRunner.llb,VI Tester API.llb, palette.mnufiles), 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-testis 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.
lvai_status, then confirm the framework's files are present:vi.lib\addons\_JKI Toolkits\VI Tester.- Presence is not availability. Establish that a VI in it can actually be called — one
throwaway
lvai_validate_aixmlwith aCallto a VI Tester target. An unresolvable target is named in the message; a resolved one only complains about unwired terminals. - Expect the palette index to miss it.
lvai_palette_indexscansmenus\andLVAddons\; JKI's.mnufiles live undervi.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. - The
.llbis NOT the obstacle - the library inside it is. Measured 2026-10-15. VI Tester ships as.llbFILES (TestCase.llb,VI Tester API.llb, …), and the.lvlibs that own its VIs are stored INSIDE them. On gRPCRun Tests (Path).viby bare name isUnsupported SubVI, andVI Tester API.lvlib\3ARun Tests (Path).viRESOLVES (required input 'Test Path' is not wired) - the same rule as Caraya'sCaraya.lvlib\3A…. An.llbis never a qualifier. So find each target's OWNING LIBRARY: the.lvlibnames are readable from the.llbfile (grep -aoE '[^/\\]+\.lvlib' "VI Tester API.llb"), or export a shipped example that already calls it and copytarget=verbatim. Thepylabviewbackend resolves both spellings - its composer opens an.llbfile on a miss and links the bare name under the qualified one - so the qualifier matters only ongrpc. CLAUDE.md, "A VI INSIDE AN.llb".
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.
- 9d ago Changed · +11 lines 4b734eba13fc
- 14d ago Changed · +5 lines 0e6550a35134
- 15d ago Changed · +11 lines c28e6ba0ee9d
- 16d ago Changed · +46 lines 5fafa6f644be
- 1mo ago Changed · +27 tokens per session 609979ca37ed
- 1mo ago Changed · +23 lines 250468537aad
- 1mo ago Changed · +13 lines 36161c7859c7
- 1mo ago Changed · +42 lines cbf5f4a7e684
- 1mo ago Changed · +28 lines e94a2306537c
- 1mo ago First seen · 179 lines · 293 tokens per session scan A 19bc695876f3
labview-vitester-unit-test is an agent published in the GitHub repository Zuehlke/labview-mcp (85 stars, last pushed today), licensed MIT. It adds 320 tokens to every session and 7,137 once invoked, about $0.0013 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to labview-lunit-unit-test, differing in 296 lines, and is treated as a copy.
Other agents, from other repositories
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
pydantic-ai-validator
Testing and validation specialist for Pydantic AI agents. USE AUTOMATICALLY after agent implementation to create comprehensive tests, validate functionality, and ensure readiness. Uses TestModel and FunctionModel for thorough validation.
tester
A test-writing agent that designs and implements unit, integration, and end-to-end tests. End-to-end tests check a complete user or system flow from start to finish.
verify-app
Full verification - unit tests, migration check, lint, types.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
test-engineer
Expert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.