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-refinery-crude-processinggit 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-refinery-crude-processing)<a href="https://agentmods.dev/skills/equinor/neqsim/neqsim-refinery-crude-processing"><img src="https://agentmods.dev/badge/skills/equinor/neqsim/neqsim-refinery-crude-processing/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-refinery-crude-processing"><img src="https://agentmods.dev/badge/skills/equinor/neqsim/neqsim-refinery-crude-processing.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 | $0.00104 | $0.04728 |
| Opus 5.5 | $0.00042 | $0.01891 |
| Sonnet 5.5 | $0.00021 | $0.00946 |
| Haiku 4.5 | $0.00010 | $0.00473 |
Grade A, and why
neqsim-refinery-crude-processing 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refinery Crude Processing
When to use this
Use this skill for NeqSim's existing crude-assay, petroleum-cut, refinery blend, crude-fractionation reference-case, product-boiling-range, and hydrotreating balance APIs. Treat the APIs as connected building blocks, not as one turnkey refinery simulator.
The useful data flow is:
assay data -> OilAssayCharacterisation -> pseudo-component fluid -> blend plan/batch -> equilibrium column or hydrotreating balances -> operating/economics receipts
Use neqsim-distillation-design for equilibrium-column setup and convergence details. Use neqsim-eos-regression when the job is to fit an EOS to measured PVT rather than convert an assay. The Doe Big Hill and Sarir classes are case-specific reference scenarios; reuse their construction pattern with a user-provided assay and operating basis instead of treating their constants as a general crude-unit design.
Class map
| Class | Package | What it does | Verified API surface |
|---|---|---|---|
OilAssayCharacterisation / nested AssayCut |
thermo.characterization |
Holds mass- or volume-yield cuts and applies them as petroleum pseudo-components. | system.getOilAssayCharacterisation(), clearCuts(), addCut(AssayCut), getCuts(), getResolvedMassFractions(), apply(); AssayCut(String), fluent withMassFraction(double), withWeightPercent(double), withVolumeFraction(double), withSpecificGravity(double), withApiGravity(double), withAverageBoilingPointCelsius(double), withMolarMassKgPerMol(double), withSulfurMassFraction(double), withNitrogenMassFraction(double). |
DoeBigHillSweetAssay |
thermo.characterization |
Supplies a named, fixed sweet-crude assay and a qualified vacuum-screening subset. | create(SystemInterface), create(SystemInterface, double), createVacuumScreeningFeed(SystemInterface, double). |
AlDiwiniyaAtmosphericReference |
thermo.characterization |
Stores published/reference atmospheric crude feed, products, TBP points, and measured reference properties. | getTbpCumulativeVolumePercent(), getTbpTemperatureCelsius(), getProducts(), getCrudeFeedRateM3PerHour(), getCrudeApiGravityAt15C(). |
RefineryAssayBlend / RefineryViscosityBlend |
thermo.characterization |
Reconstructs bulk density/API/sulfur/nitrogen and viscosity blend properties without mutating source systems. | fromAssays(OilAssayCharacterisation[], double[]), fromBulkProperties(double[], double[]) or the four-array quality overload; getters include getMassFractions(), getSpecificGravity(), getApiGravity(), getSulfurMassFraction(), getNitrogenMassFraction(). |
RefineryLinearBlendOptimizer |
thermo.characterization |
Minimizes source cost subject to API, sulfur, nitrogen, and viscosity bounds. | optimizeMinimumCost(double[] costs, double[] specificGravities, double[] sulfurFractions, double[] nitrogenFractions, double[] viscositiesCSt, double temperatureCelsius, double minimumApi, double maximumApi, double maximumSulfur, double maximumNitrogen, double minimumViscosityCSt, double maximumViscosityCSt); result getters include getSourceMassFractions(), getAssayBlend(), getViscosityBlend(), getUnitCostPerMass(), getQualityConstraintReceipt(). |
RefineryBinaryBlendEnvelope |
thermo.characterization |
Evaluates feasible first-source fractions for two-source quality constraints. | fromQualityConstraints(...), getMinimumFirstSourceMassFraction(), getMaximumFirstSourceMassFraction(), evaluateAtFirstSourceMassFraction(...). |
RefineryBlendBatch, RefineryBlendOptimizationPlan, RefineryBlendSourceLedger |
thermo.characterization |
Turns blend fractions into a mass/volume batch, links optimizer outputs to source identifiers, and preserves a source receipt ledger. | fromMassFractions(double, double[], double[]), batch fromOptimization(double, RefineryLinearBlendOptimizer.Result, double[]), plan fromOptimization(String[], double, double[], double[], RefineryLinearBlendOptimizer.Result), and ledger fromBatch(String[], RefineryBlendBatch); plan getters getOptimization(), getBatch(), getSourceLedger(), getSourceCostReceipts(). |
RefineryHydrotreatingSulfurNitrogenBalance |
thermo.characterization |
Closes screening-level sulfur/nitrogen removal, hydrogen consumption, H2S/NH3 production, and product mass. | calculate(double, double, double, double, double, double, double) or calculateForAssay(double, OilAssayCharacterisation, double, double, double, double); getters include getFeedMassKg(), getSulfurRemovedMassKg(), getNitrogenRemovedMassKg(), getProductMassKg(), getTotalMassBalanceResidualKg(). |
RefineryHydrotreating*Balance family |
thermo.characterization |
Carries staged hydrogen supply/recycle, utility, fired-heater, emissions, thermal-duty, throughput, sulfur, and nitrogen balance calculations. | Read each immutable result object's get... API; examples include RefineryHydrotreatingSulfurNitrogenThermalDutyBalance.calculate(...) and getSensibleHeatingDutyMegaWatt(). |
RefineryHydrotreating*Receipt family |
thermo.characterization |
Builds operating, product-distribution, net-intensity, and scenario-economics receipts from upstream balances. | RefineryHydrotreatingSulfurNitrogenOperatingReceipt.calculate(emissionsBalance); getFeedMassFlowKgPerHour(), getFreshHydrogenMassFlowKgPerHour(), getFreshHydrogenEnergyMWhPerTonneFeed(), getTotalScenarioCostPerHour(). |
DoeBigHillVacuumFractionationCase, SarirAtmosphericFractionationCase |
process.equipment.distillation |
Reproducible, data-bounded vacuum/atmospheric reference cases that assemble a DistillationColumn. |
Doe create(String, double, OperatingInputs); Sarir create(String, double[], double[], OperatingInputs) or createFromHeatingCase(String, SarirAtmosphericCrudeHeatingCase, OperatingInputs); case getters include getFeedStream(), getColumn(), getOperatingInputs(), and Sarir run(UUID). Inputs are case-specific. |
SarirAtmosphericPumparoundScreen, SarirAtmosphericSideStripperContactScreen |
process.equipment.distillation |
Evaluates explicitly mapped Sarir pumparound settings and a bounded side-stripper contact screen. | Pumparound configure(...); side-stripper class JavaDoc describes a single-contact screen, not a multistage column model. |
ProductBoilingPointDistribution |
process.equipment.distillation |
Reports a discrete mole-based normal-boiling-point distribution from a product stream's pseudo-components. | from(StreamInterface), getBoilingPointTemperaturesKelvin(), getCumulativeMoleFractions(), getMeanNormalBoilingPointKelvin(), getNormalBoilingPointQuantileKelvin(...). |
Standard_ASTM_D86, RiaziDaubertDistillationConversion |
standards.oilquality |
Calculates NeqSim's ASTM D86-style curve and exposes a published-point D86/TBP conversion. | new Standard_ASTM_D86(SystemInterface), calculate(), getDistillationCurve(), getTBPCurve(), getQualifiedD86Temperature(...); conversion methods convertD86ToTbpC(...), convertTbpToD86C(...). |
AsphalteneCharacterization, PedersenAsphalteneCharacterization, PedersenPlusModelSolver |
thermo.characterization |
Provides SARA/pseudocomponent or Pedersen-style heavy-end/asphaltene characterization and stability screening. | setSARAFractions(...), setC7plusProperties(...), evaluateStability(); Pedersen API includes characterize(), addAsphalteneToSystem(...), calculateOnsetPressure(...). |
BioFeedstock |
thermo.characterization |
Describes solids, elemental, lignocellulosic, digestion, and handling properties for biomass feedstocks; this is adjacent to refinery work, not a petroleum assay. | library(String), setElementalAnalysis(...), setSolidsAnalysis(...), validate(), toMap(). |
CharacterizationOptions, CharacterizationValidationReport |
thermo.characterization |
Configures supported characterization/recharacterization behavior and compares source/reference characterization results. | CharacterizationOptions.builder(), getNamingScheme(), isNormalizeComposition(), CharacterizationValidationReport.generate(...), isValid(), getWarnings(), getMassDifferencePercent(). |
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 · 175 lines · 104 tokens per session scan A 0d731989aebd
neqsim-refinery-crude-processing is a skill published in the GitHub repository equinor/neqsim (156 stars, last pushed today), licensed Apache-2.0. It adds 104 tokens to every session and 4,728 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…