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-community-skills --skill cfd-couplinggit clone --depth 1 https://github.com/equinor/neqsim-community-skillsWrote 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-community-skills/cfd-coupling)<a href="https://agentmods.dev/skills/equinor/neqsim-community-skills/cfd-coupling"><img src="https://agentmods.dev/badge/skills/equinor/neqsim-community-skills/cfd-coupling/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/skills/equinor/neqsim-community-skills/cfd-coupling"><img src="https://agentmods.dev/badge/skills/equinor/neqsim-community-skills/cfd-coupling.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 | $0.00277 | $0.07924 |
| Opus 5 | $0.00138 | $0.03962 |
| Sonnet 5 | $0.00055 | $0.01585 |
| Haiku 4.5 | $0.00028 | $0.00792 |
Grade A, and why
neqsim-cfd-coupling 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 10d 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 — 524 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CFD Coupling
A one-dimensional model works in bulk quantities. Damage does not: it concentrates wherever the local flow field departs from the bulk — bends, welds, restrictions, headers, tube bundles. Screening models bridge that gap with generic textbook multipliers.
This skill closes the gap properly. It takes whatever is known about a component (P&ID, STID tag register, datasheets, plant data), takes the fluid from a NeqSim flash, builds and runs an OpenFOAM case on the real geometry, and converts the solved field back into the factor the one-dimensional model was guessing at. When a CFD study already exists it qualifies that study instead of running a new one.
Every layer works on its own. NeqSim and OpenFOAM are both optional: without NeqSim the fluid state is stated directly, and without OpenFOAM the case is still written and can be transferred and run elsewhere.
When to Use
- A screening model needs a local enhancement factor and a generic multiplier is currently being assumed.
- Pressure drop, velocity or wall shear is needed on real geometry rather than on an equivalent-length correlation.
- Flow maldistribution across a bundle, manifold or header matters to the answer.
- Two phases share the line and the interface matters - stratified, slug or annular flow, a free surface, or liquid accumulating in a low point.
- A CFD report, vendor flow analysis or CFD/FEM deliverable is attached to an equipment tag and must be qualified before its numbers are used.
- A new CFD run must be specified and needs fluid properties, turbulence inlet values and near-wall mesh sizing.
- A tonal noise or vibration observation needs a fail-closed readiness decision before transient compressible CFD, acoustics, or structural coupling is scoped.
When Not to Use
- As a substitute for a qualified CFD engineer on a design decision. This is a screening and coupling toolkit, not a verification-and-validation review.
- To extract a number from a CFD study that fails the quality gate.
- For droplet break-up statistics, separation efficiency or a dense dispersed
phase. The multiphase screening will say
lagrangianoreuler_euler; those cases are recommended with a reason but not generated here. - For a temperature field. The generated cases solve momentum only, with the
fluid properties frozen at the inlet flash. A stagnant or dead-leg region, a
buoyancy-driven or thermally stratified region, or any wall-temperature
question needs a buoyant conjugate solver (
buoyantSimpleFoam,buoyantPimpleFoam,chtMultiRegionFoam) that this skill does not write. Usefem-couplingfor the wall and near-wall temperature, and hand-build the buoyant case if the fluid-side field itself is the deliverable. - To diagnose a tonal aeroacoustic source with the generated steady RANS or
incompressible VOF cases. Call
assess_aeroacoustic_readinessfirst. A ready case still requires a separately configured transient compressible LES/DES, spectral pressure probes, acoustic propagation, and structural modal analysis when vibration is in scope.
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- docker/Dockerfile 1.1 KB
- examples/multiphase_vof_case.py 5.4 KB runs code
- examples/pid_to_openfoam_case.py 5.8 KB runs code
- pyproject.toml 707 B
- README.md 3.0 KB
- src/cfd_coupling/__init__.py 2.5 KB runs code
- src/cfd_coupling/boundary.py 11 KB runs code
- src/cfd_coupling/design_basis.py 9.9 KB runs code
- src/cfd_coupling/model.py 18 KB runs code
- src/cfd_coupling/multiphase.py 16 KB runs code
- src/cfd_coupling/openfoam.py 61 KB runs code
- tests/test_boundary.py 4.7 KB runs code
- tests/test_cfd_coupling_model.py 9.0 KB runs code
- tests/test_design_basis.py 3.4 KB runs code
- tests/test_multiphase.py 10 KB runs code
- tests/test_openfoam.py 13 KB runs code
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.
- 10d ago First seen · 524 lines · 277 tokens per session scan A 157faea38876
neqsim-cfd-coupling is a skill published in the GitHub repository equinor/neqsim-community-skills (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 277 tokens to every session and 7,924 once invoked, about $0.0014 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 2026-08-31.
Other skills, from other repositories
neuroskill-bci
Use live BCI cognitive and mood state from NeuroSkill.
ruview-advanced-sensing
Advanced RuView capabilities — RuvSense multistatic sensing (attention-weighted fusion, geometric diversity, persistent field model), cross-viewpoint fusion across multiple nodes, RF tomography (ISTA L1 solver, voxel grids), longitudinal biomechanics drift, pre-movement intention signals, adversarial signal detection…
ruview-applications
Run RuView sensing applications — presence/occupancy, breathing & heart rate, activity & fall detection, 17-keypoint pose estimation (WiFlow), sleep monitoring & apnea screening, environment mapping, Mass Casualty Assessment (MAT), and the 3D point-cloud fusion demo. Use when someone wants to actually do something…
lab-hardware-cad
Design custom laboratory hardware as parametric build123d models and export fabrication-ready STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a research…
opentrons-integration
Author, review, migrate, simulate, and troubleshoot official Opentrons Python Protocol API v2 protocols for Flex and OT-2 robots. Use for robot-specific liquid handling, deck and labware setup, pipettes, modules, runtime parameters, liquid classes, and Opentrons App analysis. Use pylabrobot instead when one workflow…
pylabrobot
Develop and review PyLabRobot lab-automation resources, liquid-handling plans, offline simulations, and supported-device integrations. Use for PyLabRobot protocols or API questions; keep physical execution behind an explicit operator safety gate.