What is opcua-modeling?

A skill for designing OPC UA information models from official companion specifications. OPC UA is a standard for representing industrial equipment and its data in a consistent structure.

Use it to choose base types, inspect their components and optional fields, resolve namespace dependencies, and create NodeSet2 models.

It prevents developers from guessing type names, fields, dependencies, or engineering units that must match the published specifications.

opcua-modeling — Skill for Claude Code and Codex by node-opcua

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add node-opcua/node-opcua-modeler-mcp-server --skill node-opcua-modeler-mcp-server

Clone the repo

git clone --depth 1 https://github.com/node-opcua/node-opcua-modeler-mcp-server

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/node-opcua/node-opcua-modeler-mcp-server/node-opcua-modeler-mcp-server/github.svg)](https://agentmods.dev/skills/node-opcua/node-opcua-modeler-mcp-server/node-opcua-modeler-mcp-server)

Your own site

<a href="https://agentmods.dev/skills/node-opcua/node-opcua-modeler-mcp-server/node-opcua-modeler-mcp-server"><img src="https://agentmods.dev/badge/skills/node-opcua/node-opcua-modeler-mcp-server/node-opcua-modeler-mcp-server/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/node-opcua/node-opcua-modeler-mcp-server/node-opcua-modeler-mcp-server"><img src="https://agentmods.dev/badge/skills/node-opcua/node-opcua-modeler-mcp-server/node-opcua-modeler-mcp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 980 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00070	$0.00980
Opus 5.5	$0.00028	$0.00392
Sonnet 5.5	$0.00014	$0.00196
Haiku 4.5	$0.00007	$0.00098

Measured 13d ago against content hash 369e2734b55e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

opcua-modeling 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 13d 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.

SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OPC UA Modeling with the OPC UA Modeler MCP Server

When to use this skill

Use it whenever a task involves OPC UA information modeling:

designing a NodeSet2 / information model for a machine or device
choosing which companion specification types to derive from
checking what components, properties, methods, or optionals a type has
validating namespace dependencies (di, machinery, robotics, …)
finding the correct UNECE engineering-unit symbol (°C, l/min, N·m)

Never invent OPC UA type names, browse paths, or unit symbols from memory — companion specs are too niche for that. Query the catalog instead: the answers come from the official published NodeSet2.xml files.

Workflow

list_namespaces — see the 28 available companion specs with aliases, URIs, and dependency lists. Pick the spec(s) matching the domain (e.g. scales for weighing, lads for lab devices).
search_types / list_types — find candidate types by keyword (e.g. "weighing") or enumerate everything a spec defines.
get_type_details — get a type's full structure: components, properties, methods, interfaces, subtypeOf chain, and availableOptionals — the exhaustive list of valid optional browse paths (including nested dotted paths like di:Identification.machinery:InitialOperationDate).
resolve_dependencies — given the spec aliases you use, get the complete transitively-resolved, load-ordered namespace list to declare.
find_engineering_unit — map natural language ("litre per minute") to the valid UNECE symbol before writing any EUInformation.

Rules of thumb

Anchor on companion-spec base types. Subclass the closest existing type (e.g. scales:ScaleDeviceType, not ua:BaseObjectType) so clients recognize the model.
optionals: entries MUST come from availableOptionals. Never guess optional paths and never re-declare inherited components — inherited members come for free from the supertype.
Declare only the namespaces you use, in the dependency order returned by resolve_dependencies.
Types missing from a spec are a signal to compose (add components) rather than to invent look-alike type names.

Read the full file on GitHub · 81 lines

Changes

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.

13d ago Changed · +1 lines 369e2734b55e
16d ago Changed · +14 lines 16d5b83ad0b7
1mo ago Changed 469515e7b4cc
2mo ago First seen · 66 lines · 70 tokens per session scan A cf718becdb9e

Subscribe to this mod's changes

opcua-modeling is a skill published in the GitHub repository node-opcua/node-opcua-modeler-mcp-server (2 stars, last pushed 14d ago), licensed Apache-2.0. It adds 70 tokens to every session and 980 once invoked, about $0.0003 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 2026-08-31.

Hardware and IoT

opcua-modeling next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
opcua-modelingnode-opcua/node-opcua-modeler-mcp-server	Skill	2	14d ago	Apache-2.0	A	70	Claude Code, Codex
gke-compute-classesgoogle/skills	Skill	22k	yesterday	Apache-2.0	A	83	Claude Code, Codex
jetson-diagnosticNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	30	Claude Code, Codex
holoscan-install-wheelNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	34	Claude Code, Codex
offensive-z-waveSnailSploit/Claude-Red	Skill	10k	25d ago	MIT	A	113	Claude Code, Codex
doca-socket-relayNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	236	Claude Code, Codex
hsb-flashNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	B	94	Claude Code