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.
npx skills add equinor/neqsim --skill neqsim-advanced-control-mpc-and-virtual-sensinggit clone --depth 1 https://github.com/equinor/neqsimWrote 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/skills/equinor/neqsim/neqsim-advanced-control-mpc-and-virtual-sensing)<a href="https://agentmods.dev/skills/equinor/neqsim/neqsim-advanced-control-mpc-and-virtual-sensing"><img src="https://agentmods.dev/badge/skills/equinor/neqsim/neqsim-advanced-control-mpc-and-virtual-sensing/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/skills/equinor/neqsim/neqsim-advanced-control-mpc-and-virtual-sensing"><img src="https://agentmods.dev/badge/skills/equinor/neqsim/neqsim-advanced-control-mpc-and-virtual-sensing.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 | $0.00089 | $0.03358 |
| Opus 5.5 | $0.00036 | $0.01343 |
| Sonnet 5.5 | $0.00018 | $0.00672 |
| Haiku 4.5 | $0.00009 | $0.00336 |
Grade A, and why
neqsim-advanced-control-mpc-and-virtual-sensing 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 12d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Advanced Control, MPC, and Virtual Sensing
When to use this
Use this skill when NeqSim's existing dynamic/process model needs a controller-facing model, bounded receding-horizon control, a physics-based soft measurement, or steady-state data reconciliation.
ProcessLinkedMPClinks configured manipulated, controlled, disturbance, and state variables to one existingProcessSystem; it identifies local dynamics and computes/apply moves.ProcessLinearizer,StepResponseGenerator,StateSpaceExporter,IndustrialMPCExporter, andSubrModlExportercreate model-identification and integration artifacts.ModelPredictiveControlleris a controller-device implementation with a first-order prediction model, constraints, feed-quality prediction, and optional moving-horizon estimation. It is not a DCS emulator.VirtualFlowMeterandSoftSensorestimate quantities/properties from a stream's fluid and supplied operating conditions. They are screening/model estimates, not custody-transfer instruments.SteadyStateDetectorandDataReconciliationEnginescreen input data and reconcile measured values against declared linear balance constraints.
Keep each layer distinct: dynamic simulation models process response (neqsim-dynamic-simulation); controllability/operability maps feasible envelopes (neqsim-controllability-operability); calibration and plant-data workflows select and qualify measurements (neqsim-model-calibration-and-data-reconciliation, neqsim-plant-data). Compressor minimum-speed/recycle coordination belongs to neqsim-compressor-antisurge-recycle.
Class map
| Class or family | Package | What it does | Key methods verified |
|---|---|---|---|
ProcessLinkedMPC |
neqsim.process.mpc |
Binds MVs/CVs/DVs/SVRs to a ProcessSystem, identifies its model and performs repeated control calculations. |
Constructor (String, ProcessSystem); addMV, addCV, addCVZone, addDV, addSVR, identifyModel, calculate, applyMoves, getLastMoves, getLinearizationResult, exportModel |
ProcessLinearizer, variable classes |
neqsim.process.mpc |
Computes local finite-difference gains for configured manipulated/controlled/disturbance variables. | ProcessLinearizer(ProcessSystem), addMV, addCV, addDV, linearize, setDefaultPerturbationSize |
StepResponseGenerator, StepResponse, NonlinearPredictor, derivative calculator |
neqsim.process.mpc |
Builds step-response models, finite-difference process responses, and optional nonlinear prediction inputs. | StepResponse constructor and response getters are documented in MPCIntegrationTest; verify a generator method before use |
| State-space and industrial exporters | neqsim.process.mpc |
Exports local linear model to discrete state-space, Industrial MPC, SubrModl, soft-sensor, and controller data-exchange formats. | StateSpaceExporter(LinearizationResult), toDiscreteStateSpace, getA, getB, getC, getD; createIndustrialExporter, createSubrModlExporter |
ModelPredictiveController |
neqsim.process.controllerdevice |
Standalone first-order, receding-horizon controller device with linear quality constraints and feed disturbance handling. | Constructors (), (String); setPredictionHorizon, setControllerSetPoint, setTransmitter, getResponse |
| Controller benchmarks and metrics/events | neqsim.process.controllerdevice |
Records controller benchmark scenarios, performance metrics, and events for comparative assessment. | APIs vary by object; inspect source before assuming metric units or benchmark acceptance |
| Logic/sequence/transfer-function blocks | neqsim.process.controllerdevice |
Provides logic blocks, sequential function charts, and transfer-function structures. | Use their public interfaces and transition/update APIs from source; these are not a plant DCS runtime |
| Cascade, feed-forward, override, ratio, split-range, minimum-speed recycle | neqsim.process.controllerdevice.structure |
Composes controller outputs for common multiloop, selector, and recycle-coordination patterns. | Minimum-speed integration is detailed in neqsim-compressor-antisurge-recycle |
VirtualFlowMeter, VFMResult, UncertaintyBounds |
neqsim.process.measurementdevice.vfm |
Estimates gas/oil/water rates and simple uncertainty bounds from stream fluid, pressure drop, choke opening, and calibration factor. | VirtualFlowMeter(String, StreamInterface), calculateFlowRates, setMeasurementUncertainties; getOilFlowRate, getGasFlowRate, getWaterFlowRate, getQuality, uncertainty getters |
SoftSensor |
neqsim.process.measurementdevice.vfm |
Estimates supported fluid properties by flashing a cloned stream fluid at supplied P/T. | SoftSensor(String, StreamInterface, PropertyType), setInput, setInputs, estimate |
SteadyStateDetector, SteadyStateVariable |
neqsim.process.util.reconciliation |
Tests incoming variable histories with a sliding-window steady-state detector before reconciliation/calibration. | SteadyStateDetector(int), addVariable, updateVariable, evaluate |
DataReconciliationEngine, ReconciliationVariable, ReconciliationResult |
neqsim.process.util.reconciliation |
Applies weighted least squares to measurement values under caller-defined linear equality balances; reports statistical flags. | addVariable, addConstraint(double[]), setGrossErrorThreshold, reconcile; isConverged, getErrorMessage, getVariables, getChiSquareStatistic, getGrossErrors |
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.
- 12d ago First seen · 169 lines · 89 tokens per session scan A 45fef1161a16
neqsim-advanced-control-mpc-and-virtual-sensing is a skill published in the GitHub repository equinor/neqsim (156 stars, last pushed today), licensed Apache-2.0. It adds 89 tokens to every session and 3,358 once invoked, about $0.0004 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 2026-10-05.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…