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 skills/steadfastasart/geoscience-skills/loopstructuralnpx skills add SteadfastAsArt/geoscience-skills --skill loopstructuralgit clone --depth 1 https://github.com/SteadfastAsArt/geoscience-skillsWhat 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 | $0.00108 | $0.01889 |
| Opus 5 | $0.00054 | $0.00945 |
| Sonnet 5 | $0.00022 | $0.00378 |
| Haiku 4.5 | $0.00011 | $0.00189 |
Grade A, and why
loopstructural 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 3d 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LoopStructural - 3D Geological Modelling
Quick Reference
from LoopStructural import GeologicalModel
from LoopStructural.visualisation import LavaVuModelViewer
import pandas as pd
import numpy as np
# Create model
model = GeologicalModel(origin=[0, 0, -1000], maximum=[10000, 10000, 0])
# Add data
model.data = pd.DataFrame({
'X': [5000], 'Y': [5000], 'Z': [-500],
'feature_name': ['strat'], 'val': [0]
})
# Build and visualize
model.create_and_add_foliation('strat', interpolatortype='PLI')
model.update()
viewer = LavaVuModelViewer(model)
viewer.add_isosurface(model['strat'], isovalue=0)
viewer.interactive()
Key Classes
| Class | Purpose |
|---|---|
GeologicalModel |
Main model container - holds features and data |
ProcessInputData |
Data preparation and validation |
StructuralFrame |
Coordinate system for fold modelling |
FaultSegment |
Individual fault surface with displacement |
Essential Operations
Build Stratigraphic Model
model = GeologicalModel([0, 0, -1000], [10000, 10000, 0])
model.data = pd.DataFrame({
'X': [5000, 5000, 5000],
'Y': [5000, 5000, 5000],
'Z': [-200, -500, -800],
'feature_name': ['strat', 'strat', 'strat'],
'val': [0, 1, 2] # Different unit values
})
model.create_and_add_foliation('strat', interpolatortype='PLI', nelements=1000)
model.update()
Add Orientation Data
# Structural measurements (strike/dip)
orientations = pd.DataFrame({
'X': [2000, 5000, 8000],
'Y': [5000, 5000, 5000],
'Z': [-100, -100, -100],
'feature_name': ['strat', 'strat', 'strat'],
'strike': [90, 90, 90],
'dip': [30, 30, 30],
'val': [np.nan, np.nan, np.nan]
})
model.data = pd.concat([interfaces, orientations])
Model with Fault
# Define fault data
fault_data = pd.DataFrame({
'X': [5000, 5000], 'Y': [2000, 8000], 'Z': [-500, -500],
'feature_name': ['fault1', 'fault1'],
'val': [0, 0], 'coord': [0, 0]
})
fault_orient = pd.DataFrame({
'X': [5000], 'Y': [5000], 'Z': [-500],
'feature_name': ['fault1'],
'gx': [1], 'gy': [0], 'gz': [0] # Fault normal
})
model.data = pd.concat([fault_data, fault_orient, strat_data])
model.create_and_add_fault('fault1', displacement=200) # Add fault first
model.create_and_add_foliation('strat') # Stratigraphy affected by fault
model.update()
What ships with it
3 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.
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.
- 3d ago First seen · 213 lines · 108 tokens per session scan A efc79e5c4aca
loopstructural is a skill published in the GitHub repository SteadfastAsArt/geoscience-skills (54 stars, last pushed 5mo ago), licensed MIT. It adds 108 tokens to every session and 1,889 once invoked, about $0.0005 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 skills, from other repositories
Spatial Omics Skills Index
Skills for spatial transcriptomics analysis including single-cell to spatial mapping (MOSCOT), 3D visualization (PyVista), and related spatial workflows.
tao-train-bevfusion
BEVFusion for multi-sensor 3D object detection. Fuses LiDAR point clouds and camera images in bird's-eye-view (BEV) space, used in autonomous driving for robust 3D perception. Use when training, evaluating, or running inference for a TAO BEVFusion model. Trigger phrases include "train BEVFusion", "LiDAR + camera…
occt
Use when developing custom CAD/CAM/CAE applications requiring a production-grade 3D geometric kernel — B-Rep modeling, Boolean operations, fillets, STEP/IGES I/O, meshing. OCCT (Open CASCADE Technology): the industrial C++ geometry kernel that powers FreeCAD, KiCad, and many commercial CAD systems.
mathgraphs
Math graphing, 3D scene building with lights and particles, and presentations.
glm-lake-mendota
Simulate vertical water temperature profiles for lakes using the General Lake Model (GLM), calibrate key parameters to minimize RMSE against field observations, and produce validated NetCDF output.
map-to-evo-schemas
Use when implementing the reader and geoscience-object builder for an Evo data converter — turning a parsed file into evo-schemas objects. Covers implementing read file, building Pointset/TriangleMesh/grid/etc. objects, uploading arrays via dataclient.savetable or the parquet-hash pattern, and setting CRS, bounding…