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 skills add equinor/neqsim --skill neqsim-regression-baselinesgit clone --depth 1 https://github.com/equinor/neqsimWrote 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.
[](https://agentmods.dev/skills/equinor/neqsim/neqsim-regression-baselines)<a href="https://agentmods.dev/skills/equinor/neqsim/neqsim-regression-baselines"><img src="https://agentmods.dev/badge/skills/equinor/neqsim/neqsim-regression-baselines.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00051 | $0.01792 |
| Opus 5 | $0.00026 | $0.00896 |
| Sonnet 5 | $0.00010 | $0.00358 |
| Haiku 4.5 | $0.00005 | $0.00179 |
Grade A, and why
neqsim-regression-baselines 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NeqSim Regression Baseline Management
Preventing silent accuracy drift in a physics engine requires committed baseline values that CI validates on every build.
Why Baselines Matter
A property correlation change that improves methane density by 0.1% might degrade ethane viscosity by 5%. Without baselines, these regressions are invisible until a downstream user reports wrong results months later.
Baseline Workflow
When to Create Baselines
Create baselines before modifying:
- Flash calculation algorithms (
flashops/) - Phase property calculations (
phase/,physicalproperties/) - Component parameter databases (
COMP.csv,mbwr32param.csv) - Mixing rule implementations
- Process equipment calculations that depend on thermodynamic properties
- Cost estimation or mechanical design correlations
Step 1: Capture Current Values
Run the existing code and record results in a JSON fixture file:
@Test
void captureBaseline_SRK_methane_density() {
SystemInterface fluid = new SystemSrkEos(273.15 + 25.0, 60.0);
fluid.addComponent("methane", 1.0);
fluid.setMixingRule("classic");
ThermodynamicOperations ops = new ThermodynamicOperations(fluid);
ops.TPflash();
fluid.initProperties();
// Record these values as the baseline
double density = fluid.getDensity("kg/m3"); // e.g., 45.23
double Cp = fluid.getCp("J/molK"); // e.g., 38.5
double Z = fluid.getZ(); // e.g., 0.892
assertEquals(45.23, density, 0.5, "Methane density at 25C/60bar");
assertEquals(38.5, Cp, 0.5, "Methane Cp at 25C/60bar");
assertEquals(0.892, Z, 0.005, "Methane Z-factor at 25C/60bar");
}
Step 2: Choose Appropriate Tolerances
| Property Type | Typical Tolerance | Rationale |
|---|---|---|
| Density | 0.5-1.0% relative | Well-predicted by cubic EOS |
| Z-factor | 0.5% absolute (0.005) | Directly from EOS |
| Viscosity | 2-5% relative | Correlation-dependent, more variable |
| Thermal conductivity | 5-10% relative | Least accurate transport property |
| Phase fractions | 1% absolute (0.01) | Phase split sensitivity varies |
| Enthalpy/Cp | 1-2% relative | Derived from EOS |
| Bubble/dew point | 0.5-1.0 K or 0.5-1.0 bar | Phase boundary sensitivity |
| Compressor power | 1-2% relative | Depends on enthalpy accuracy |
| Separator compositions | 2% relative per component | Depends on K-value accuracy |
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.
- 4d ago First seen · 195 lines · 51 tokens per session scan A a8ae624389af
neqsim-regression-baselines is a skill published in the GitHub repository equinor/neqsim (150 stars, last pushed today), licensed Apache-2.0. It adds 51 tokens to every session and 1,792 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 2026-09-03.
Other skills, from other repositories
testing
Skill validation framework PLUS daily test-suite health and regression intelligence. Validates skill conformance (frontmatter, manifest coverage, resolver coverage). Runs the project test suite in tiered phases (unit / evals / integration / system health), classifies failures, and produces a regression-aware report.
mockito-stale-mock-silent-trycatch-failure
Fix misleading Flutter/Dart test failures where expected data is empty ([]) or default values instead of the mocked response, caused by stale Mockito generated mocks or missing stubs being silently swallowed by try/catch in provider/repository code. Use when: (1) Test expects non-empty data but gets [], (2) Mock stubs…
fix-bug
Diagnoses and fixes bugs using a test-first workflow (reproduce, diagnose, fix). Use this skill whenever the user reports a bug, describes unexpected behavior, or asks to investigate or fix a defect. Even if the user says "something's broken", "this isn't working", "fix this bug", or "why does X happen", load this…
test-auto-fix
Diagnoses failing tests across any project, classifies each failure as a test-bug, prod-bug, or unsure, confidence-gates the fix (auto-apply at >=90%, 80-89 ask, <80 escalate), applies it, and re-runs until green. Surface-driven: reads per-project configuration from a surface file keyed by normalised git remote URL.…
debugging
Use when debugging bugs, test failures, or unexpected behavior. Triggers: 'why isn't this working', 'this doesn't work', 'X is broken', 'something's wrong', 'getting an error', 'exception in', 'stopped working', 'regression', 'crash', 'hang', 'flaky test', 'intermittent failure', or when user pastes a stack…
fortify
Fortify existing code by splitting large functions, adding edge-case coverage, and backfilling unit tests. Use when user asks to "fortify", "harden", "bulletproof", "make robust", "make solid", "strengthen", "add missing tests", "split functions", or wants to improve reliability of existing code. Don't use for new…