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.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/instructions/zuehlke/labview-mcp/claude-md)<a href="https://agentmods.dev/instructions/zuehlke/labview-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/zuehlke/labview-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.26405 | $0.26405 |
| Opus 5 | $0.13203 | $0.13203 |
| Sonnet 5 | $0.05281 | $0.05281 |
| Haiku 4.5 | $0.02641 | $0.02641 |
Grade C, and why
labview-mcp CLAUDE.md scanned grade C 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 today.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
**The recovery is `rm -rf src/LabVIEWMCP/obj src/LabVIEWMCP/bin tests/LabVIEWMCP.Tests/obj How it starts
The opening of the file, as written. The whole thing — 1,336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in this repository
Rules that came out of building this server, written down so they survive a new machine and a fresh session. They are not style preferences — each one is here because ignoring it cost real work.
Generating LabVIEW code
First decide what kind of thing you are looking for. This routing question comes before any lookup, and getting it wrong sends you to the wrong index and makes you conclude "there is no function for this":
| What you want | Construct | Where to look |
|---|---|---|
| a whole working diagram — a state machine, a producer/consumer, "how do I stream to TDMS" | a shipping example to read and adapt | lvai_example_index |
| a computation on data — read a file, sort, parse, compare | primitive Node, or a subVI Call |
lvai_palette_index; terminal names from an export |
| a property or action of a LabVIEW object — a VI, control, panel, project, the application | Property Node / Invoke Node |
lvai_vi_server_reference |
| a VI's icon | neither — AIXML cannot carry one | lvai_set_vi_icon, which drives VI Server for you |
The second row is the one that gets forgotten. "Get this VI's icon", "list a project's items", "is this VI broken", "read a control by name", "what does this VI call" are none of them functions and will never appear in a palette — they are properties and methods, and the catalogue is the only index for them.
Check whether NI already built it, before designing anything. lvai_example_index lists the
shipping examples of this installation with NI's own description and keywords, and needs no
running LabVIEW. It answers a different question from the palette index — that one says which VI
may I call, this one says is this whole diagram already written. Feed a hit's path to
lvai_convert_vi_to_aixml and read how NI wired it.
Two numbers worth knowing before you call it. 609 of the 951 examples are listed by default:
the rest need LabVIEW FPGA, LabVIEW Real-Time or a licensed toolkit, and a hit you cannot open is
worse than no hit. The count held back is always reported; includeSpecialised shows them.
And the index is cached on disk and warmed at start-up, so calls cost about 176 ms — but the
first ever build on a machine reads 2510 files and takes about 50 seconds. This file used to
claim 400 ms flatly; that was the warm figure, and before the cache existed every server restart
brought the full minute back.
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.
- today Changed · +133 lines · +2,785 tokens per session scan A → C 8ade8e7c16e2
- 3d ago Changed · +71 lines · +1,562 tokens per session c59b584f0e78
- 4d ago Changed · +104 lines · +2,193 tokens per session 120b0c011419
- 5d ago Changed · +112 lines · +2,406 tokens per session 7b68f5994b67
- 8d ago First seen · 916 lines · 17,459 tokens per session scan A 78d13f59ef5a
labview-mcp CLAUDE.md is an instructions file published in the GitHub repository Zuehlke/labview-mcp (22 stars, last pushed yesterday), licensed MIT. It adds 26,405 tokens to every session, about $0.1320 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.