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/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/instructions/zuehlke/labview-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/zuehlke/labview-mcp/claude-md.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 | $0.09188 | $0.09188 |
| Opus 5.5 | $0.03675 | $0.03675 |
| Sonnet 5.5 | $0.01838 | $0.01838 |
| Haiku 4.5 | $0.00919 | $0.00919 |
Grade A, and why
labview-mcp CLAUDE.md 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 512 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. Each one exists because ignoring it cost real work.
This file holds the RULES; the measurements, the history and the wrong turns behind them are in
docs/ (the pointer after each rule) and, verbatim as of 2026-11-01, in
docs/claude-md-archive.md. Read those when a rule's reason matters. Rules are stated as
measured: if a measurement contradicts one, fix the rule here and say what it claimed before.
Agents first
LabVIEW work is DELEGATED to the matching labview-* agent, not done in the main session.
The user's standing rule of 2026-09-27. Work directly only when the user asks for it.
| Request | Agent |
|---|---|
| a new VI | labview-vi-generator |
| implement a SUPPLIED VI whose front panel must be kept (exam template) | labview-vi-generator - pass the supplied VI; it grafts (Phase 6g) |
| change an existing VI | labview-vi-editor |
| a class, class hierarchy or interface | labview-class-generator |
a library (.lvlib), its members, description and icon |
labview-class-generator |
| unit tests (default framework) | labview-caraya-unit-test |
| LUnit / VI Tester tests, only when named | labview-lunit-unit-test / labview-vitester-unit-test |
| documentation | labview-doc-generator |
| a DQMH module or event | labview-dqmh-module |
The agent definitions carry rules a session working directly never reads. Relay an agent's
NEEDS CLARIFICATION block to the user verbatim and continue THAT agent via SendMessage; never
answer it on the user's behalf.
A plugin user's main session never sees this file: it reads docs/orchestrator-brief.md, the
server's MCP instructions. Keep that brief in step with every change to this section.
docs/server-instructions.md.
A MULTI-VI APPLICATION STARTS WITH A BUILD CONTRACT, written by the orchestrator BEFORE the first
agent (the user's decision of 2026-11-01). build-contract.json in the build folder names every
VI with its path, owner, builder, connector pane and callees; lvai_check_build_contract mode=plan
checks it without LabVIEW and answers the build WAVES. Every builder gets the contract path and
implements against it, the main-VI agent authors its scaffold in parallel with wave 0, and
mode=verify gates each wave before the next is built. docs/build-contract.md.
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 · +5 lines · +95 tokens per session 024e59070e51
- 4d ago Changed · -1,802 lines · -38,598 tokens per session scan C → A 50ff043e9313
- 1mo ago Changed · +116 lines · +2,370 tokens per session 54b162dd20f1
- 1mo ago Changed · +447 lines · +9,923 tokens per session 65e7c6966344
- 1mo ago Changed · +82 lines · +1,845 tokens per session ce86051fb1b3
- 1mo ago Changed · +167 lines · +3,655 tokens per session 60700c6a4e53
- 1mo ago Changed · +25 lines · +751 tokens per session 8256d64ff187
- 1mo ago Changed · +136 lines · +2,742 tokens per session 241863c5770c
- 2mo ago Changed · +133 lines · +2,785 tokens per session scan A → C 8ade8e7c16e2
- 2mo ago First seen · 1,203 lines · 23,620 tokens per session scan A c59b584f0e78
labview-mcp CLAUDE.md is an instructions file published in the GitHub repository Zuehlke/labview-mcp (114 stars, last pushed yesterday), licensed MIT. It adds 9,188 tokens to every session, about $0.0368 per session on Opus 5.5. 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.
labview-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| labview-mcp CLAUDE.mdZuehlke/labview-mcp | Instructions file | 114 | yesterday | MIT | A | 9,188 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |