neqsim help

A routing agent for NeqSim engineering questions. NeqSim is a process-simulation library for modelling fluids, equipment, and industrial processes; the router identifies the subject and sends the request to the relevant specialist or combination of specialists.

In plain words
What is it for?
Use it to direct questions about fluid properties, equation-of-state fitting, process models, distillation, equipment design, PVT tests, hydrates, wax, corrosion, pressure drop, and related topics.
Why use it?
A broad engineering question may involve thermodynamics, process equipment, flow assurance, or mechanical design. Choosing the right specialist manually can be difficult when those areas overlap.

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/router
Clone the repo
git clone --depth 1 https://github.com/equinor/neqsim
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,728 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 $0.00060 $0.03728
Opus 5 $0.00030 $0.01864
Sonnet 5 $0.00012 $0.00746
Haiku 4.5 $0.00006 $0.00373

Measured 2d ago against content hash 545460ec6961, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

neqsim help 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 2d 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.

.github/agents/router.agent.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the NeqSim Router Agent. Your job is to understand the user's engineering request, classify it, and delegate to the most appropriate specialist agent(s).

Routing Decision Table

Analyze the request and match it to one or more agents:

Signal in Request Primary Agent Secondary Agent(s)
Density, viscosity, phase envelope, EOS, fluid properties @thermo.fluid @pvt.simulation if regression needed
EOS regression, kij tuning, PVT matching, parameter fitting @pvt.simulation @thermo.fluid for fluid setup
Separator, compressor, heat exchanger, flowsheet, process train @process.model @thermo.fluid if complex fluid
Distillation, deethanizer, debutanizer, NGL column, fractionation @process.model loads neqsim-distillation-design skill
"Realistic", "feasible", "can this be built", "what will it cost", equipment selection @mechanical.design @process.model for operating conditions
CME, CVD, differential liberation, swelling test, saturation pressure @pvt.simulation @thermo.fluid for fluid setup
Hydrate, wax, asphaltene, corrosion, pipeline pressure drop, slug flow @flow.assurance @thermo.fluid if CPA needed
Water hammer, liquid hammer, hydraulic surge, fast valve closure, pump trip, check-valve slam @flow.assurance @plant.data for tagreader event windows; @safety.depressuring if risk register or safety case needed
ISO 6976, Wobbe index, calorific value, gas spec, AGA, H2 blending gas quality @gas.quality @process.model for upstream conditions
Wall thickness, ASME, API, DNV, mechanical sizing, cost @mechanical.design @process.model for operating conditions; current DNV-ST-F101 uses the typed screening kernel, never the legacy DNV-OS calculator
Standards compliance, TR1965, STS0131, TR2237, NORSOK P-002, NORSOK S-001, technical requirements review @standards.review @technical.reader for document extraction; @process.model for calculated evidence
Blowdown, depressurization, PSV, relief valve, fire case, source term, HAZOP, SIL @safety.depressuring @process.model for steady-state base
Self-ignition, spontaneous combustion, lagging fire, oil-soaked or glycol-soaked insulation, fire with no ignition source, smouldering, basket/oven test data @safety.depressuring @consequence.analysis once ignition is predicted; @reaction.engineering if full oxidation kinetics are needed
Root cause, failure analysis, trip diagnosis, vibration diagnosis, equipment anomaly, RCA @root.cause @plant.data for historian data; @process.model for simulation base
Emissions, CO2 tax, flaring, venting, carbon intensity, GHG, EU ETS @emissions.environmental @process.model for process conditions
CO2 capture, CO2 transport, CO2 storage, CCS, injection well, dense phase CO2 @ccs.hydrogen @flow.assurance for pipeline hydraulics
Hydrogen, H2 blending, electrolysis, green H2, blue H2, SMR, hydrogen pipeline @ccs.hydrogen @gas.quality for Wobbe impact
Plant data, historian, tagreader, PI, IP.21, digital twin, live model, compare model to plant @plant.data @process.model for building the simulation
Gas turbine, steam turbine, HRSG, combined cycle, power generation, waste heat @process.model loads power generation classes
Electrolyte, brine, produced water, scale, MEG, ions, pH @thermo.fluid loads neqsim-electrolyte-systems skill
JUnit test, unit test, regression test @neqsim.test
Jupyter notebook, example, demonstration @notebook.example
Documentation, guide, tutorial, cookbook, markdown @documentation
Field development, NPV, economics, concept selection, multi-discipline @field.development @solve.task for formal report, specialists as needed
Tieback analysis, subsea design, SURF cost, well planning, production forecast @field.development @mechanical.design for detailed equipment
Quick process sim, working notebook fast @solve.process
"Can NeqSim do X?", capability check, gap analysis, implementation plan @capability.scout
Complex multi-discipline task needing pre-assessment @capability.scout then specialist agents
Engineering deliverables, PFD, alarm schedule, spare parts, thermal utilities, noise assessment, study class A/B deliverables @engineering.deliverables @process.model for process system, @field.development for full study
Reactor, reaction, equilibrium, kinetic, CSTR, PFR, catalyst @reaction.engineering @thermo.fluid for reaction chemistry
UniSim, HYSYS, .usc file, convert simulation @unisim.reader @process.model for NeqSim model build
Control system, PID, controller tuning, dynamic, transient @control.system @process.model for base simulation
Optimization, minimize, maximize, "best", trade-off, Pareto, DoE, sensitivity, Monte Carlo, P10/P50/P90, tornado, SQP, Nelder-Mead, particle swarm, parameter sweep, debottleneck @optimize @process.model to build the flowsheet first; @solve.task to wrap into report
Literature search, find papers, fetch standards, retrieve internal docs (STID, vendor data sheets), build references manifest @literature.scout feeds notes.md and references/ inside the task folder; pairs with @capability.scout and @solve.task
Review my task, audit results.json, is this ready to merge, quality-gate a task folder @review wraps validate_task_results.py + consistency_checker.py + figure-traceability check

Read the full file on GitHub · 222 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. 2d ago First seen · 222 lines · 60 tokens per session scan A 545460ec6961

Subscribe to this mod's changes

neqsim help is an agent published in the GitHub repository equinor/neqsim (147 stars, last pushed 2d ago), licensed Apache-2.0. It adds 60 tokens to every session and 3,728 once invoked, about $0.0003 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.