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/simpegnpx skills add SteadfastAsArt/geoscience-skills --skill simpeggit clone --depth 1 https://github.com/SteadfastAsArt/geoscience-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/steadfastasart/geoscience-skills/simpeg)<a href="https://agentmods.dev/skills/steadfastasart/geoscience-skills/simpeg"><img src="https://agentmods.dev/badge/skills/steadfastasart/geoscience-skills/simpeg.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 5.1 | $0.00112 | $0.01749 |
| Opus 5 | $0.00056 | $0.00874 |
| Sonnet 5 | $0.00022 | $0.00350 |
| Haiku 4.5 | $0.00011 | $0.00175 |
Grade A, and why
simpeg 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 6d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SimPEG - Geophysical Simulation & Inversion
Quick Reference
from discretize import TensorMesh
from simpeg.electromagnetics.static import resistivity as dc
from simpeg import maps, data_misfit, regularization, optimization
from simpeg import inverse_problem, inversion, directives
import numpy as np
# Create mesh
hx, hz = np.ones(100) * 10, np.ones(50) * 5
mesh = TensorMesh([hx, hz], origin='CN')
# Forward model
simulation = dc.Simulation2DNodal(mesh, survey=survey, sigmaMap=maps.ExpMap(mesh))
dpred = simulation.dpred(model)
# Inversion
dmis = data_misfit.L2DataMisfit(data=data, simulation=simulation)
reg = regularization.WeightedLeastSquares(mesh)
opt = optimization.InexactGaussNewton(maxIter=20)
inv_prob = inverse_problem.BaseInvProblem(dmis, reg, opt)
inv = inversion.BaseInversion(inv_prob, directiveList=[...])
mrec = inv.run(m0)
Key Classes
| Class | Purpose |
|---|---|
TensorMesh, TreeMesh |
Discretization (regular grid, adaptive octree) |
Survey |
Data acquisition geometry |
Simulation |
Forward modeling engine |
Data |
Observed/predicted data container |
InvProblem |
Combines misfit, regularization, optimization |
Essential Operations
Create Mesh
from discretize import TensorMesh
# 2D mesh (x, z) - centered in x, top at z=0
hx, hz = np.ones(100) * 20, np.ones(50) * 10
mesh = TensorMesh([hx, hz], origin='CN')
# 3D mesh
mesh = TensorMesh([np.ones(50)*25, np.ones(50)*25, np.ones(30)*10], origin='CCN')
DC Resistivity Survey
from simpeg.electromagnetics.static import resistivity as dc
elec_locs = np.c_[np.linspace(-95, 95, 20), np.zeros(20)]
source_list = []
for i in range(17): # dipole-dipole
rx = dc.receivers.Dipole(elec_locs[[i+2]], elec_locs[[i+3]])
src = dc.sources.Dipole([rx], elec_locs[i], elec_locs[i+1])
source_list.append(src)
survey = dc.Survey(source_list)
Forward Model
model = np.ones(mesh.nC) * 100 # 100 ohm-m
simulation = dc.Simulation2DNodal(mesh, survey=survey, sigmaMap=maps.ExpMap(mesh))
dpred = simulation.dpred(np.log(1/model)) # input: log(conductivity)
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.
- 6d ago First seen · 174 lines · 112 tokens per session scan A 1fbf0eb5f7cd
simpeg is a skill published in the GitHub repository SteadfastAsArt/geoscience-skills (57 stars, last pushed 5mo ago), licensed MIT. It adds 112 tokens to every session and 1,749 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 skills, from other repositories
mxl-driver-dftbplus
This skill should be used when users want to couple MaxwellLink to the MaxwellLink-aware DFTB+ fork via the MaxwellLinkSocket block, including real-time Ehrenfest dynamics, VelocityVerlet Born-Oppenheimer MD, dipole-derivative choices, build/install, and TCP/UNIX socket connection patterns.
mxl-multimode
This skill should be used when users need the MaxwellLink multimode Fabry-Pérot cavity solver to study a spatial grid of molecules coupled to many photonic modes (mesoscale VSC), in either socket or embedded mode.
paper_tutorial_plasmon_heating
Dual-purpose tutorial to reproduce manuscript Figure 5b, 5d, and 5e plasmonic flux and HCN heating maps (EM-only, TLS, and ASE/BOMD), and to transfer the workflow to related plasmon-molecule systems by adjusting geometry, molecular model, and run procedures.
paper_tutorial_vsc_water
Dual-purpose tutorial to reproduce manuscript liquid-water vibrational strong-coupling spectra and CPU scaling (single-mode cavity plus Meep Bragg resonator), and to adapt the same procedure to related VSC systems by retuning cavity/resonator parameters, size ladders, and execution settings.
mxl-meep
This skill should be used when users need MaxwellLink + Meep FDTD workflows, including embedded vs socket coupling, MPI considerations, and recommended templates.
mxl-core
This skill should be used when users need the canonical MaxwellLink workflow, including socket vs embedded coupling, units/time handling, and MPI/HPC invariants.