design_flash_benchmark

design_flash_benchmark is a skill for Claude Code, Codex from equinor/neqsim. It costs 15 tokens per session (1,712 once invoked), scanned A, original, Apache-2.0.

A test-matrix generator for comparing flash algorithms. A flash calculation finds how a fluid mixture separates into gas and liquid under specified conditions.

In plain words
What is it for?
Use it to plan benchmark studies, extend tests to new fluid families, and stress-test calculations near critical points or in multiphase regions.
Why use it?
It organizes comparisons across fluid mixtures, temperatures, pressures, and difficulty levels, so important edge cases are not missed.

Skill for Claude CodeCodex

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 skills/equinor/neqsim/design_flash_benchmark
Any agent
npx skills add equinor/neqsim --skill design_flash_benchmark
Clone the repo
git clone --depth 1 https://github.com/equinor/neqsim

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for design_flash_benchmark

README.md
[![agentmods](https://agentmods.dev/badge/skills/equinor/neqsim/design_flash_benchmark.svg)](https://agentmods.dev/skills/equinor/neqsim/design_flash_benchmark)
Your own site
<a href="https://agentmods.dev/skills/equinor/neqsim/design_flash_benchmark"><img src="https://agentmods.dev/badge/skills/equinor/neqsim/design_flash_benchmark.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,712 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 $0.00015 $0.01712
Opus 5 $0.00008 $0.00856
Sonnet 5 $0.00003 $0.00342
Haiku 4.5 $0.00002 $0.00171

Measured 5d ago against content hash 4a3d25039436, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design_flash_benchmark 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 5d 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/skills/design_flash_benchmark/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Design Flash Benchmark

Purpose

Create a structured test matrix for comparing flash algorithm performance across fluid types, thermodynamic conditions, and difficulty levels.

When to Use

  • Starting a new flash algorithm comparison study
  • Extending an existing benchmark to new fluid families
  • Designing stress tests for near-critical or multi-phase regions

Benchmark Design Procedure

Step 1: Select Fluid Families

Choose from these standard families:

Family Components Mole Fractions Characteristics
Lean gas CH4(0.90), C2(0.05), C3(0.03), N2(0.01), CO2(0.01) Fixed or ±10% Easy, mostly single-phase
Rich gas CH4(0.70), C2(0.10), C3(0.08), nC4(0.05), nC5(0.03), N2(0.02), CO2(0.02) Fixed or ±15% Moderate, clear two-phase
Gas condensate CH4(0.65), C2(0.08), C3(0.06), nC4(0.04), nC5(0.03), nC6(0.02), nC7(0.02), nC10(0.05), N2(0.02), CO2(0.03) ±20% Near-critical behavior
CO2-rich CO2(0.80), CH4(0.10), N2(0.05), H2S(0.03), C2(0.02) ±15% Strong non-ideality
Wide-boiling CH4(0.50), nC4(0.15), nC10(0.15), nC16(0.10), nC20(0.10) ±20% Large volatility range
Sour gas CH4(0.60), CO2(0.15), H2S(0.10), C2(0.08), C3(0.05), N2(0.02) ±15% Acid gas behavior

Step 2: Define PT Space

For each family, define the pressure-temperature sampling grid:

import numpy as np

def generate_pt_grid(T_min_K, T_max_K, P_min_bara, P_max_bara, n_T=20, n_P=20):
    """Generate a regular PT grid."""
    T_values = np.linspace(T_min_K, T_max_K, n_T)
    P_values = np.logspace(np.log10(P_min_bara), np.log10(P_max_bara), n_P)
    cases = []
    for T in T_values:
        for P in P_values:
            cases.append({"T_K": float(T), "P_bara": float(P)})
    return cases

Standard ranges by family:

Family T range (K) P range (bara) Focus region
Lean gas 200–400 1–200 Dew point region
Rich gas 220–450 5–300 Two-phase dome
Gas condensate 250–500 10–500 Near cricondenbar
CO2-rich 250–400 10–200 CO2 critical region
Wide-boiling 300–600 1–100 Large T range

Read the full file on GitHub · 164 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. 5d ago First seen · 164 lines · 15 tokens per session scan A 4a3d25039436

Subscribe to this mod's changes

design_flash_benchmark is a skill published in the GitHub repository equinor/neqsim (150 stars, last pushed today), licensed Apache-2.0. It adds 15 tokens to every session and 1,712 once invoked, about $0.0001 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 skills, from other repositories

Image Processing Testing

Testing image processing pipelines including format conversion, resize quality, metadata handling, watermark verification, and thumbnail generation.

PramodDutta/qaskills · 25 tokens

pyqgis

Use when extending QGIS with Python plugins, automating map composition, or scripting QGIS processing algorithms. PyQGIS: QGIS Python API for custom tools, processing scripts, and plugin development.

znlgis/opengis-skills · 44 tokens

qgis-process

Use when running QGIS geoprocessing tools headless from command line or CI/CD — buffer, clip, reproject, raster analysis without GUI. QGIS Processing: batch spatial analysis via qgisprocess CLI.

znlgis/opengis-skills · 48 tokens

data-batch-processing

Use this skill when designing batch processing with Hive, Spark SQL, Pig, or HQL. This skill enforces: Hive metastore management, Spark SQL Catalyst optimization, file format selection (Parquet, ORC, Avro), partitioning and bucketing strategies, query tuning with statistics and dynamic partition pruning. Do NOT use…

j4flmao/agent-skills · 98 tokens

aws-dataprocessing-mcp

Data processing and transformation services.

Friz-zy/ai-capability-registry · 15 tokens

pythermodb-reference-maker

Extract thermodynamic tables and correlations from references (CSV, PDF, images, or text) and convert them into the project's structured pyThermoDB YAML schema. Supports data tables, constants tables, matrix-parameter tables, and equation-based correlations (e.g., Cp, vapor pressure, density, enthalpy of…

sinagilassi/PyThermoCalcDB-NASA-MCP · 132 tokens