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 agentmods add instructions/equinor/neqsim/thermodynamic-initializationgit clone --depth 1 https://github.com/equinor/neqsimWhat 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 | $0.00400 | $0.00400 |
| Opus 5 | $0.00200 | $0.00200 |
| Sonnet 5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
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.
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 substituteinit(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.
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.
- 2d ago First seen · 22 lines · 400 tokens per session scan A 9a9e23dff5ee
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.
Other instructions, from other repositories
Thermodynamics.jl AGENTS.md
Instructions for CliMA/Thermodynamics.jl, covering thermodynamics.jl agent guide, ecosystem guidelines, before you act: agent autonomy, repo-specific guidelines and architecture.
VCVio AGENTS.md
Instructions for Verified-zkEVM/VCVio, covering vcvio — ai agent guide, fast start, attribution, headers, and docstrings, module scopes and what this project is.
oci-agent CLAUDE.md
Instructions for Netflix-Skunkworks/oci-agent, covering observational causal inference (oci) agent and rules.
bio-gene-to-reference-tree copilot-instructions.md
Instructions for Hongda-Zhao/bio-gene-to-reference-tree, a project described as: Auditable agent skill for resolving protein queries, selecting references, and planning reproducible phylogenetic trees.
braina GEMINI.md
Instructions for brainets/braina, covering project: braina (brain interaction analysis), 1. project context & purpose, 2. commands, verify environment (all core dependencies) and run the verification test suite for frites + hoi.
research-automation CLAUDE.md
Instructions for lucafusarbassini/research-automation, covering ricet - research automation framework, project overview, claude-flow mcp, workflow habits and file organization.