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-engineering-design-packagegit 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-engineering-design-package)<a href="https://agentmods.dev/skills/equinor/neqsim/neqsim-engineering-design-package"><img src="https://agentmods.dev/badge/skills/equinor/neqsim/neqsim-engineering-design-package/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-engineering-design-package"><img src="https://agentmods.dev/badge/skills/equinor/neqsim/neqsim-engineering-design-package.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 | $0.00095 | $0.03676 |
| Opus 5.5 | $0.00038 | $0.01470 |
| Sonnet 5.5 | $0.00019 | $0.00735 |
| Haiku 4.5 | $0.00010 | $0.00368 |
Grade A, and why
neqsim-engineering-design-package 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering Design Package
When to use this
Use this skill when the job is to coordinate existing NeqSim process engineering into a traceable design package. It covers engineering design cases and modules, generated P&ID proposals, engineering graph views, export/round-trip checks, numerical-health evidence, revision impact, and approval history.
Run stages in this order:
- Build or verify a solved
ProcessSystem, identify the controlled project revision, design basis, evidence, cases, limits, and data gaps. - Run the case envelope and the
EngineeringDesignLoopwith only the typed design modules needed for the question. - Synthesize P&ID proposals from the approved proposal profile; check references, coverage, and evidence completeness.
- Export native DEXPI and compatibility artifacts; separately qualify internal structural round-trip and any named external CAE import/export.
- Compile the coordinated package; inspect schema/topology and numerical-health results rather than treating generated files as proof of fitness.
- Diff the controlled revisions, propagate impact actions, then build the approval ledger with revision-aware invalidation.
For process topology construction, operating actions, and DEXPI context, use neqsim-pid-process-operations and neqsim-process-modeling. This skill adds the typed design loop, package coordination, qualification, change, and approval APIs; it does not replace those workflows.
Class map
| Class or family | Package | What it does | Key methods verified |
|---|---|---|---|
EngineeringProject, EngineeringDesignBasis, NorsokOffshoreEngineeringBuilder |
neqsim.process.engineering |
Binds the runnable process, requirements, standards, evidence, and revision into a governed project. | from, build, setRevision, validate, getEngineeringProcessSystem |
EngineeringDesignLoop, EngineeringDesignLoopOptions, EngineeringDesignLoopResult |
neqsim.process.engineering.design |
Executes case runs and module updates until design/process values and constraints converge or a fail reason occurs. | run, builder, maximumIterations, isConverged, getTerminationReason, getIterations, getDesignedProcess |
| Variables, constraints, dependency graph, convergence report, candidates | neqsim.process.engineering.design |
Carries unit-bearing design values, candidate choices, dependency order, conflict decisions, and per-iteration convergence evidence. | getKey, getUnit, getSelectedValue, getConvergenceReport, getOrderedModuleIds |
| Fifteen typed design modules: separator, line/network, valve, compressor/pump, exchanger, instrument, inventory, materials, mechanical, safety, relief, rated capacity | neqsim.process.engineering.design.modules |
Evaluate typed discipline design updates and constraints against governing case metrics. | EngineeringDesignModule.evaluate; SeparatorProcessDesignModule constructor; RatedCapacityDesignModule constructor |
| P&ID basis/model/synthesis, rule catalogs, tag allocator | neqsim.process.engineering.pid |
Generates deterministic control/safeguarding/instrument proposals and stable tags from process equipment and a proposal basis. | PidDesignSynthesizer.synthesize, PidDesignModel.getElements, getElementsByType, PidTagAllocator.allocate, reserve |
| P&ID completeness, HAZOP handoff, and materialization/export | neqsim.process.engineering.pid |
Checks proposal references/coverage and writes design model, completeness, HAZOP, and DEXPI sidecars. | PidCompletenessValidator.validate, PidEngineeringPackageExporter.export |
| Canonical engineering graph, calculation DAG, graph diff, diagram/stream/balance tables and graphical projections | neqsim.process.engineering.model |
Represents process, calculations, provenance, diagram tables and revision differences independently of XML rendering. | EngineeringGraphDiff.getImpactedNodeIds; graph API calls are deliberately kept behind the compiler in the sample |
| DEXPI engineering export/materialization/validation and round-trip qualifier | neqsim.process.engineering.dexpi |
Writes native DEXPI 2.0 plus Proteus/pyDEXPI compatibility and engineering sidecars; performs internal structural checks. | DexpiEngineeringExporter.export, refreshPackageManifest, EngineeringDexpiRoundTripQualifier.qualify |
| CFIHOS 2.0 staging handover | neqsim.process.engineering.handover |
Maps canonical graph nodes/properties/documents to a project-controlled reference-data mapping and emits gap findings. | Cfihos20HandoverExporter.export; result: getManifestFile, getAssessmentFile, getUnmappedFile, getReport |
| Package/schema/topology validation | neqsim.process.engineering.validation |
Validates generated engineering artifacts and topology against the schema catalog. | Validation is invoked by the compiler/export gates; do not infer a successful external import from schema validation |
| Numerical health | neqsim.process.engineering.numerics |
Reports process convergence, mass closure, supplied energy closure, equation residuals, and supplied Jacobian health. | analyze, addEnergyClosure, addEquationResidual, sensitivityJacobian |
| Compiler, discipline packages, automation plan, approval ledger | neqsim.process.engineering.deliverables |
Writes coordinated package artifacts, reports, and revision-aware approval state. | EngineeringDeliverableCompiler.compile; result path getters; EngineeringApprovalLedger.build |
| Generalized impact and lifecycle journal | neqsim.process.engineering.impact; neqsim.process.processmodel.lifecycle.event |
Propagates graph change events to recalculate, regenerate, revalidate, review, or reapprove affected objects; journals model changes. | GeneralizedImpactAnalyzer.analyze; event-subject analysis and changed-node analysis |
| Production vertical slice and preflight | neqsim.process.engineering.verticalslice |
Runs controlled inlet/compression/export scenarios with explicit policy and qualification gates. | ProductionVerticalSliceSimulator.runStrictAndCompile; run ProductionVerticalSlicePreflight first |
| Typed calculation kernel families | neqsim.process.engineering.calculation |
Kernel families cover DNV pipeline/pipe-soil/global buckling, API pump, ISO metering, NORSOK corrosion, equipment/mechanical, valve/instrument, relief, safety, and materials calculations. | Select the specific typed kernel and inspect its assessment/context contract before use |
| Production qualification and safety lifecycle families | neqsim.process.engineering.production; neqsim.process.engineering.safety.lifecycle |
Method applicability/benchmark qualification, production-readiness and external-evidence gates; HAZOP/LOPA/SRS workflow and change revalidation. | EngineeringMethodQualificationRegistry; HazopLopaSrsWorkflow; SafetyStudyRevalidationPlanner |
| Process topology graph, DEXPI process exchange, lifecycle state | neqsim.process.processmodel.graph; neqsim.process.processmodel.dexpi; neqsim.process.processmodel.lifecycle |
Provides process-level graph/XML and lifecycle foundations beneath the engineering-project layer. | Use Dexpi20XmlWriter for native process exchange; use the engineering exporter for governed packages |
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 · 178 lines · 95 tokens per session scan A 23861dbe1461
neqsim-engineering-design-package is a skill published in the GitHub repository equinor/neqsim (156 stars, last pushed today), licensed Apache-2.0. It adds 95 tokens to every session and 3,676 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…