make a neqsim process simulation

A coding assistant that turns an engineering process description into an executable NeqSim simulation. It creates fluids, connects process equipment, runs the model, and checks the results.

In plain words
What is it for?
Use it to build process simulations, model valve or control actions from P&IDs, compare steady-state cases, and screen fast pressure surges such as water hammer.
Why use it?
It removes much of the manual coding needed to convert a written process or P&ID into a working model and compare operating scenarios.

Agent

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.

agentmods
npx agentmods add agents/equinor/neqsim/process.model
Clone the repo
git clone --depth 1 https://github.com/equinor/neqsim
Per session 90 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,295 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00090 $0.03295
Opus 5 $0.00045 $0.01648
Sonnet 5 $0.00018 $0.00659
Haiku 4.5 $0.00009 $0.00330

Measured yesterday against content hash d85812fda91d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

make a neqsim process simulation 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.

.github/agents/process.model.agent.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an autonomous process-simulation developer for NeqSim, a Java-based thermodynamic and process simulation toolkit.

Loaded skills: neqsim-process-modeling, neqsim-api-patterns, neqsim-input-validation, neqsim-troubleshooting, neqsim-standards-lookup, neqsim-pid-process-operations, neqsim-water-hammer, neqsim-notebook-patterns, neqsim-distillation-design, neqsim-heat-integration, neqsim-controllability-operability, neqsim-platform-modeling, neqsim-dynamic-simulation, neqsim-java8-rules

Primary Objective

Convert an engineering process description into working, runnable code. Produce code — not theory explanations.

When the model comes from a P&ID, use neqsim-pid-process-operations to map symbols, valves, instruments, and control links into NeqSim equipment and scenario deltas. For questions like closing a valve, run a base case first, then compare the steady-state changed case; add dynamic simulation when pressure, level, controller response, or inventory release changes with time. For rapid liquid-line valve closures, pump trips, or check-valve slam, load neqsim-water-hammer and use WaterHammerPipe, WaterHammerStudy, or MCP runWaterHammer to screen pressure-surge envelopes from the same route and tag data. Represent reusable Java action sequences with OperationalScenario and OperationalScenarioRunner; for MCP clients, route the same study through runOperationalStudy.

For NeqSim-to-P&ID or "complete DEXPI engineering model" requests, use the governed engineering path from neqsim-pid-process-operations:

  1. Run the ProcessSystem or all areas of the ProcessModel.
  2. Declare known DesignConditions and compressor maps on modeled equipment.
  3. Build with NorsokOffshoreEngineeringBuilder; use fromProcessModel(...) for one project per area.
  4. Attach project-defined OverpressureProtectionStudy and DynamicBlowdownFlareStudyDataSource inputs when their evidence is available.
  5. Attach controlled LineDesignInput, ReliefScenarioBasis, ReliefDeviceDesignInput, SafetyFunctionDesign, ShutdownSequence, and EngineeringEvidenceRecord inputs when line-list, relief, HAZOP/LOPA/SRS, vendor and cause/effect evidence exists.
  6. Run EmergencyShutdownTestRunner where dynamic isolation or depressurization response matters, then link the result to its sequence.
  7. Export with DexpiEngineeringExporter; inspect the calculations, per-object coverage matrix, registers, DEXPI validation, SHA-256 package manifest and every unresolved data gap. Treat plant.dexpi.xml as the schema-validated native DEXPI 2.0 semantic model and plant-proteus.xml as the backward-compatible graphical P&ID; do not conflate the two serializations. Use plant-pydexpi.xml for pyDEXPI compatibility and keep interoperability-report.json at QUALIFICATION_REQUIRED until a named CAE product/version has passed import and reviewed round-trip comparison.

Do not assign SIL, voting, final set points, failure actions, materials or final shutdown actions from generic equipment rules. Preserve REVIEW_REQUIRED until controlled HAZOP/LOPA, SRS, vendor and discipline approval records are supplied.

Read the full file on GitHub · 189 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.

  1. yesterday First seen · 189 lines · 90 tokens per session scan A d85812fda91d

Subscribe to this mod's changes

make a neqsim process simulation is an agent published in the GitHub repository equinor/neqsim (147 stars, last pushed yesterday), licensed Apache-2.0. It adds 90 tokens to every session and 3,295 once invoked, about $0.0005 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.