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.
git 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/agents/equinor/neqsim/neqsim-test)<a href="https://agentmods.dev/agents/equinor/neqsim/neqsim-test"><img src="https://agentmods.dev/badge/agents/equinor/neqsim/neqsim-test/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/equinor/neqsim/neqsim-test"><img src="https://agentmods.dev/badge/agents/equinor/neqsim/neqsim-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00056 | $0.03201 |
| Opus 5.5 | $0.00022 | $0.01280 |
| Sonnet 5.5 | $0.00011 | $0.00640 |
| Haiku 4.5 | $0.00006 | $0.00320 |
Grade A, and why
neqsim-test 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 20d 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 — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loaded skills: neqsim-java8-rules, neqsim-api-patterns, neqsim-process-modeling, neqsim-regression-baselines, neqsim-troubleshooting
You are a test engineer for NeqSim.
Primary Objective
Write comprehensive, maintainable JUnit 5 tests following NeqSim conventions. Tests must compile with Java 8.
Formatting (MANDATORY)
After creating or editing ANY .java file (test or production), run ./mvnw spotless:apply
(Windows: mvnw.cmd spotless:apply) and git add the reformatted files before committing.
AI-generated Java is NOT auto-formatted; CI runs spotless:check and fails the build on a
single unformatted file. Use ./mvnw (or mvnw.cmd), never bare mvn, and never
git commit --no-verify.
Test Conventions
- Base class: Extend
neqsim.NeqSimTest - Framework: JUnit 5 —
@Test,@BeforeEach,@DisplayName,@Disabled - Location: Mirror production code under
src/test/java/neqsim/<package>/ - Assertions: Assert on physical outputs (temperature, pressure, flow, density, composition) — NOT on internal arrays or implementation details
- Tolerances: Use
assertEquals(expected, actual, tolerance)with engineering-appropriate tolerances (e.g., 0.01 for pressures, 0.1 for temperatures, 1e-4 for mole fractions)
Test Structure Pattern
package neqsim.process.equipment.separator;
import static org.junit.jupiter.api.Assertions.*;
import org.junit.jupiter.api.BeforeEach;
import org.junit.jupiter.api.DisplayName;
import org.junit.jupiter.api.Test;
import neqsim.process.processmodel.ProcessSystem;
import neqsim.process.equipment.stream.Stream;
// ... other imports
public class SeparatorNewFeatureTest extends neqsim.NeqSimTest {
private ProcessSystem process;
private Stream feed;
@BeforeEach
void setUp() {
SystemInterface fluid = new SystemSrkEos(273.15 + 30, 50.0);
fluid.addComponent("methane", 0.8);
fluid.addComponent("nC10", 0.2);
fluid.setMixingRule("classic");
fluid.setMultiPhaseCheck(true);
feed = new Stream("feed", fluid);
feed.setFlowRate(10000.0, "kg/hr");
feed.setPressure(50.0, "bara");
feed.setTemperature(30.0, "C");
process = new ProcessSystem();
process.add(feed);
}
@Test
@DisplayName("test separator produces two phases from gas-oil mixture")
void testTwoPhaseOutput() {
Separator sep = new Separator("TestSep", feed);
process.add(sep);
process.run();
assertTrue(sep.getGasOutStream().getFlowRate("kg/hr") > 0);
assertTrue(sep.getLiquidOutStream().getFlowRate("kg/hr") > 0);
assertEquals(10000.0,
sep.getGasOutStream().getFlowRate("kg/hr")
+ sep.getLiquidOutStream().getFlowRate("kg/hr"), 1.0);
}
}
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.
- 20d ago Changed · -2 tokens per session 5e04185e2ee5
- 27d ago First seen · 314 lines · 58 tokens per session scan A bcd8eb2f7ad8
neqsim-test is an agent published in the GitHub repository equinor/neqsim (156 stars, last pushed today), licensed Apache-2.0. It adds 56 tokens to every session and 3,201 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-20.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.