neqsim thermodynamic-initialization.instructions.md

Instructions for choosing the minimum thermodynamic initialization needed in NeqSim, a software library for calculating fluid and chemical properties. The required level depends on whether the work needs composition bookkeeping, phase equilibrium, caloric properties, derivatives, or transport properties.

In plain words
What is it for?
Use it when setting up NeqSim calculations involving phase equilibrium, fugacity, chemical potentials, enthalpy, entropy, derivatives, or physical and transport properties.
Why use it?
It prevents unnecessary initialization and keeps calculations aligned with the quantities being evaluated. Higher levels are used only when their specific data is required.

Instructions file for GitHub Copilot

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 instructions/equinor/neqsim/thermodynamic-initialization
Clone the repo
git clone --depth 1 https://github.com/equinor/neqsim

Made for: GitHub Copilot.

Per session 400 This file is loaded in full into every session.
When invoked 400 The same file — it is already loaded in full.
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 $0.00400 $0.00400
Opus 5 $0.00200 $0.00200
Sonnet 5 $0.00080 $0.00080
Haiku 4.5 $0.00040 $0.00040

Measured 2d ago against content hash 9a9e23dff5ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

neqsim thermodynamic-initialization.instructions.md 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/instructions/thermodynamic-initialization.instructions.md · 22 lines

What it actually says

Minimal thermodynamic initialization level

Use the lowest NeqSim thermodynamic initialization level that is sufficient for the quantities being evaluated. Do not raise an initialization level defensively or because a higher level is available.

Required rule

  • Use init(0) only for composition and phase-amount bookkeeping that does not require EOS state.
  • Use init(1) for fixed-temperature/fixed-pressure phase-equilibrium work: cubic-root selection, molar volume and compressibility factor, fugacity coefficients, chemical potentials, tangent-plane or Gibbs-equilibrium comparisons, phase stability, and TP-flash iteration state.
  • Use init(2) only when first temperature derivatives or caloric properties are actually required, such as enthalpy, entropy, heat capacity, Joule-Thomson coefficients, or temperature derivatives of residual Helmholtz/Gibbs terms.
  • Use init(3) only when second composition derivatives, full derivative matrices, or another explicitly documented level-3 quantity is required.
  • Use initProperties() only when physical/transport properties are required. Do not substitute init(3) for physical-property initialization.

Before adding or increasing an initialization level, identify the exact downstream getter or derivative that requires it and verify that requirement in the relevant phase/component implementation. If the code only evaluates cubic roots, fugacity equality, fixed-T/P Gibbs equilibrium, phase fractions, or compositions, init(1) is normally sufficient.

Higher initialization levels add avoidable calculations in flash and process-simulation hot paths. A change from init(1) to init(2) or init(3) therefore requires a correctness-based justification and focused validation; it must not be accepted solely from an automated review suggestion.

When reducing an existing initialization level, add focused tests showing unchanged requested results and benchmark stable metrics where the path is performance-sensitive.

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 · 22 lines · 400 tokens per session scan A 9a9e23dff5ee

Subscribe to this mod's changes

neqsim thermodynamic-initialization.instructions.md is an instructions file published in the GitHub repository equinor/neqsim (147 stars, last pushed 2d ago), licensed Apache-2.0. It adds 400 tokens to every session, about $0.0020 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.

Related

Other instructions, from other repositories