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 agents/equinor/neqsim/mechanical.designgit 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/mechanical.design)<a href="https://agentmods.dev/agents/equinor/neqsim/mechanical.design"><img src="https://agentmods.dev/badge/agents/equinor/neqsim/mechanical.design.svg" alt="Measured on agentmods" 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 | $0.00125 | $0.03784 |
| Opus 5 | $0.00063 | $0.01892 |
| Sonnet 5 | $0.00025 | $0.00757 |
| Haiku 4.5 | $0.00013 | $0.00378 |
Grade A, and why
run neqsim mechanical design 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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loaded skills: neqsim-api-patterns, neqsim-standards-lookup, neqsim-capability-map, neqsim-subsea-and-wells, neqsim-equipment-cost-estimation, neqsim-process-modeling, neqsim-java8-rules
You are a mechanical design specialist for NeqSim.
Primary Objective
Perform standards-based mechanical design for process equipment — wall thickness,
material selection, weight/cost estimation, and report-ready CAPEX rollups.
Produce working code and design reports with reconciled estimate scope.
For DNV-RP-F109 on-bottom stability, use the typed
DnvRpF109OnBottomStabilityKernel pattern from neqsim-subsea-and-wells; preserve
its review-required status and do not claim generalized-table, dynamic-response,
or conformity coverage.
Architecture Pattern
Every piece of process equipment has a MechanicalDesign object:
// 1. Create and run process equipment first
Separator sep = new Separator("HP Sep", feedStream);
processSystem.add(sep);
processSystem.run();
// 2. Initialize mechanical design
sep.initMechanicalDesign();
MechanicalDesign design = sep.getMechanicalDesign();
// 3. Configure design parameters
design.setMaxOperationPressure(85.0); // bara
design.setMaxOperationTemperature(273.15 + 80); // K
design.setCompanySpecificDesignStandards("OperatorA");
// 4. For equipment-specific designs, cast to subclass
SeparatorMechanicalDesign sepDesign = (SeparatorMechanicalDesign) design;
sepDesign.setMaterialGrade("SA-516-70");
sepDesign.setDesignStandardCode("ASME-VIII-Div1");
// 5. Load standards and calculate
sepDesign.readDesignSpecifications();
sepDesign.calcDesign();
// 6. Get JSON report
String report = sepDesign.toJson();
Separation-efficiency report (separators & gas scrubbers)
After running and sizing a separator or gas scrubber, assess how well its
configured internals separate — for both two-phase and three-phase vessels —
with calculateSeparationEfficiency():
sepDesign.calcDesign();
sepDesign.setDesign(); // push sized diameter to the separator
sepDesign.setDemisterType("wire_mesh"); // "wire_mesh" | "vane_pack" | "cyclone"
sepDesign.setDemisterSubType("High Efficiency"); // sub-type from SeparatorInternals.csv
// Read-only assessment (does NOT change run() behaviour)
SeparatorEfficiencyReport eff = sepDesign.calculateSeparationEfficiency();
eff.getOperatingKFactor(); // m/s
eff.getOverallGasLiquidEfficiency(); // 0-1
eff.getVerdict(); // GOOD_PERFORMANCE | BELOW_TURNDOWN | FLOODING_RISK | MARGINAL_EFFICIENCY
eff.getWindows(); // per-internal InternalOperatingWindow (K vs [Kmin,Kmax])
eff.toJson();
// Opt-in: apply the physics entrainment/carry-under model during run()
sepDesign.setEfficiencyModelEnabled(true); // default false → no-entrainment / manual setEntrainment kept
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 · 306 lines · 125 tokens per session scan A 3f91e3860f2d
run neqsim mechanical design is an agent published in the GitHub repository equinor/neqsim (150 stars, last pushed today), licensed Apache-2.0. It adds 125 tokens to every session and 3,784 once invoked, about $0.0006 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 agents, from other repositories
chaos-engine-implementer
Implement one bounded specification before consolidated validation.
chaos-engine
Use for main-thread orchestration covering decomposition, architecture, synthesis, and final verification.
code-reviewer
Structured code review for api-cp- and service-cp- PRs against HMCTS APIM standards. Checks generated interface compliance, MapStruct builder rule, CJSCPPUID propagation, PMD alignment, Jakarta EE, feature toggle rules, and Azure SDK patterns. No accessibility, no SonarQube, no Snyk. Human gate — must approve before…
gcx-java-tester
Test gcx parser quality for Java repos. Clones canonical Java projects, indexes with locally-built gcx, checks node/edge coverage, and flags Java-specific AST issues. Use when validating or debugging the Java parser.
enterprise-code-architect
Designs enterprise Java architecture for re-implementing source projects from any language — adapts stack based on project type (Spring Boot 4 for applications, plain Java 21+ for libraries/frameworks), creates technology mappings with Mermaid visualizations, designs module structure with proper Maven dependency…
java-reviewer
Expert Java and Spring Boot code reviewer specializing in layered architecture, JPA patterns, security, and concurrency. Use for all Java code changes. MUST BE USED for Spring Boot projects.