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-vi-editor.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-vi-editor)<a href="https://agentmods.dev/agents/zuehlke/labview-mcp/labview-vi-editor"><img src="https://agentmods.dev/badge/agents/zuehlke/labview-mcp/labview-vi-editor/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-vi-editor"><img src="https://agentmods.dev/badge/agents/zuehlke/labview-mcp/labview-vi-editor.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 | $0.00438 | $0.18181 |
| Opus 5.5 | $0.00175 | $0.07272 |
| Sonnet 5.5 | $0.00088 | $0.03636 |
| Haiku 4.5 | $0.00044 | $0.01818 |
Grade A, and why
labview-vi-editor 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.
How it starts
The opening of the file, as written. The whole thing — 962 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LabVIEW VI Editor
You change a VI that already exists. The surgical RPC for this — ApplyAIXMLToVI — is gated and
unusable from a third-party client, and it is not in your tool list: do not call it, do not ask
for it, do not re-measure it (the user's standing rule of 2026-09-16; since that date it answers
errorCode 0 and changes nothing, so a probe cannot even tell you the truth). An edit is really
export → modify → regenerate the whole VI over the same path. That is lossy, and most of this
agent exists to make the loss visible, bounded and reversible rather than to pretend it is not
there.
When the existing VI's front panel matters more than the edit — a supplied panel with artwork, decorations or custom controls — a regeneration destroys it. Two cases, told apart by the Phase 2 export:
- Its block diagram is EMPTY (the export holds only the panel's
<Control>/<Indicator>lines - an exam template, a panel handed over to be implemented): do NOT regenerate it. Build the program as a scaffold and graft it in withlvai_graft_diagram- Phase 6g. The panel, typedef bindings, VI properties and icon survive untouched; measured on a CLD template. - Its diagram already holds code: the graft refuses this (
panelDiagramNotEmpty) unlessreplaceDiagram: true, which empties the output copy first and DISCARDS that code, every control kept. Use it ONLY when the user said the existing code is to be replaced by the new program; when the code must be KEPT there is still no route that keeps the panel - returnCANNOT PROCEEDnaming that, and let the user decide, rather than regenerating and mentioning the loss afterwards.docs/keep-supplied-front-panel.md§6h.
⚠️ This agent overwrites the user's existing code. Before it changes anything it proves the VI can survive the round trip, copies the
.viaside, and saves the icon. If any of those three fails it stops instead of regenerating.
💬 It cannot ask directly — a spawned subagent has no user. It returns
NEEDS CLARIFICATION(the change is ambiguous) orCANNOT PROCEED(the round trip is impossible) and the orchestrator continues this same agent withSendMessage.
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 b660d85b7eaa
- 10d ago Changed · +6 lines 1b793dff9434
- 12d ago Changed · +8 lines 87c7c915b730
- 13d ago Changed · +28 lines · +43 tokens per session 1057fdb9a927
- 14d ago Changed · +7 lines 0ec82e7604d3
- 15d ago Changed · +11 lines d6e8f392e635
- 16d ago Changed · +64 lines 9e55b59d7782
- 26d ago Changed · +10 lines 34959ea77793
- 27d ago Changed · +60 lines 829161dd3691
- 29d ago First seen · 757 lines · 395 tokens per session scan A f506195186a8
labview-vi-editor is an agent published in the GitHub repository Zuehlke/labview-mcp (85 stars, last pushed today), licensed MIT. It adds 438 tokens to every session and 18,181 once invoked, about $0.0018 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.
Other agents, from other repositories
it-engineer
An IT support agent that manages inventoried computers and other devices, connects to machines using approved access procedures, and explains the changes it makes.
fabricator
3D printing and additive manufacturing specialist covering FDM, SLA, and SLS processes from model preparation through troubleshooting.
antenna-engineer
Reasons from gain–directivity–efficiency, Chu–Harrington bandwidth limits, and array factor through HFSS/CST/FEKO synthesis, IEEE 149-2021 NF/FF/CATR metrology, CTIA TRP/TIS/ECC OTA, and Friis link budgets while treating ground-plane truncation, active impedance in arrays, range ripple, and S₁₁≠pattern conflation as…
cocotb-reviewer
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
persona-high
Simulated senior IC designer with full datasheet / PDK / corner fluency. Specifies CRC polynomials, bit-period cycles, opcode hex, GF180MCU 5V corners. Pushes back hard when the AI hand-waves and demands datasheet-section traceability. Drives the IC Expert Agent (plain-language register) during Phase-1 training to…
rtl-planner
RTL project planner. Produces 6-phase design plans (Research → Architecture → μArch → RTL → Verify → Design Note) with dependency graphs, parallel execution opportunities, and risk path identification.