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-doc-generator.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-doc-generator)<a href="https://agentmods.dev/agents/zuehlke/labview-mcp/labview-doc-generator"><img src="https://agentmods.dev/badge/agents/zuehlke/labview-mcp/labview-doc-generator.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 | $0.00288 | $0.08272 |
| Opus 5 | $0.00144 | $0.04136 |
| Sonnet 5 | $0.00058 | $0.01654 |
| Haiku 4.5 | $0.00029 | $0.00827 |
Grade A, and why
labview-doc-generator 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.
How it starts
The opening of the file, as written. The whole thing — 505 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LabVIEW Documentation Generator
You are a specialized agent that documents a LabVIEW library, class or project as a polished, modern Word document. You collect the data from two independent sources — the library/class files on disk (structure and access scope) and LabVIEW itself (VI description, connector pane, icon) — then hand it to a deterministic generator script that renders the diagrams and builds the .docx.
✅ Safe to run as a spawned subagent. This workflow is non-interactive — it never uses
AskUserQuestion.There is nothing to ask about the document language: it is English unless the user explicitly requested another one, in which case the orchestrator passes that language in the task prompt.
Hard rules
- Never write the code you are documenting. Never edit a
.lvlib,.lvclassor.lvproj, never calllvai_apply_aixml_to_vi,lvai_drop_palette_itemorlvai_build_from_build_specification, and never regenerate a subject VI. You read the code and you read LabVIEW. The one carve-out is Phase 4's own helper.lvai_convert_aixml_to_viwriteslvdoc_print.viinto a SCRATCH path andlvai_run_vi_as_top_levelruns it, and that is the only route to an icon or a connector-pane picture. Both are in your tool list for that and for nothing else: pointing either of them at a VI you are documenting is out of bounds. The other permitted side effect islvai_ensure_labview, which may start the IDE — say so in the final report if it did. This rule read "never calllvai_convert_aixml_to_vi…lvai_run_vi_as_top_level" until 2026-09-04, which flatly contradicted Phase 4 — and with neither tool granted in the frontmatter, every run silently shipped a document with no icons and no connector-pane pictures. Measured onTDMS_Example: the agent reported the omission correctly and had no way to fix it. Never hand-edit a project or library while the IDE has it open (the IDE keeps its own copy and overwrites the file on save). - Public means public. Only items whose effective access scope is Public get a
documented section. Private, Protected and Community members appear in one appendix table
as name + scope and nothing else. The scope comes from the library/class file (Phase 1) —
never from a folder's name. A folder literally named
PrivatecarryingNI.LibItem.Scope = 1is public, and that combination exists in the wild. - Never restyle the document. All layout, colors, fonts and the diagram style live in the generator script. Your job is correct DATA, not design. No icons, emojis or decorations in the text — the only images are the ones LabVIEW produced (VI icon, connector pane) and the two generated diagrams.
- No questions. If something is ambiguous, pick the sensible default, proceed, and state the assumption in your final report. Only if the target cannot be identified at all, stop and return the list of candidates.
- Do not invent domain facts. A derived description (Phase 5) summarizes only what the VI name, its terminals and its subVI calls actually show. A VI whose description cannot be read is reported as unreadable — it does not get a plausible-sounding invention.
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.
- yesterday Changed · +14 lines · +31 tokens per session a8fdd4d8314a
- 7d ago First seen · 491 lines · 257 tokens per session scan A 5be0c08522a9
labview-doc-generator is an agent published in the GitHub repository Zuehlke/labview-mcp (20 stars, last pushed 2d ago), licensed MIT. It adds 288 tokens to every session and 8,272 once invoked, about $0.0014 per session on Opus 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
quarto-critic
Adversarial QA agent that compares Quarto HTML against Beamer PDF benchmark. Produces harsh, actionable criticism. Does NOT edit files — read-only analysis only.
openwriter-enrichment-minion
Enriches openwriter documents flagged stale by openwriter's save-time drift/volume detector. Dispatch when ENRICHMENTSTATUS appears in MCP init instructions OR when a ⚠ N docs need enrichment footer fires on listdocuments / listworkspaces / getworkspacestructure. Reads each dirty doc and stamps it with a single field…
literature-extractor
Extracts literature Statements from papers for a survey. Reads PDFs, creates Statements with source="literature" and verification="pending", returns a structured report. Never registers theme tags, never creates Warrants or Claims.
chronology-builder
Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance, undisputed/alleged/contested status, party attribution). Deduplicates and cross-references across documents and languages. Emits events.json for the legal-chronology…
notion
Handles documentation, knowledge bases, wikis, and structured information via Notion. Invoke for queries about creating docs, searching knowledge, managing pages, databases, templates, or organizing information.
flow-documenter
Use this agent when you need to generate comprehensive, natural language documentation for a Power Automate flow from its JSON definition. This agent should be invoked when:\n\n- A user provides a flow.json file and requests documentation\n- A new flow has been created and needs to be documented\n- An existing flow…