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 SteadfastAsArt/geoscience-skills --skill discretizegit 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/discretize)<a href="https://agentmods.dev/skills/steadfastasart/geoscience-skills/discretize"><img src="https://agentmods.dev/badge/skills/steadfastasart/geoscience-skills/discretize/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/steadfastasart/geoscience-skills/discretize"><img src="https://agentmods.dev/badge/skills/steadfastasart/geoscience-skills/discretize.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 | $0.00049 | $0.00702 |
| Opus 5.5 | $0.00020 | $0.00281 |
| Sonnet 5.5 | $0.00010 | $0.00140 |
| Haiku 4.5 | $0.00005 | $0.00070 |
Grade A, and why
discretize 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 1mo 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
discretize
Construct the mesh and location-aware operators before attaching physical data. The library does not determine the CRS or the physical units of its coordinates.
Choose geometry and data locations
Use TensorMesh for separable rectangular grids; choose TreeMesh when local
refinement substantially reduces cost. Finalize a tree before using its operators.
Pad model boundaries and refine sources, receivers and property contrasts as
required by the forward problem, then test domain and resolution sensitivity.
Record axis meanings, origin, units, cell widths and active-cell mask. In a 2D
vertical section the second coordinate can mean elevation, but this is a project
convention. A vector of length n_cells is not a face or edge vector.
Divergence with an independent answer
The synthetic velocity field is u = (2x, -3y) per second. Its divergence is -1 s⁻¹, including on this nonuniform mesh. Boundary fluxes are represented at their actual face locations; no zero boundary condition is imposed implicitly.
# example: nonuniform-divergence
import numpy as np
from discretize import TensorMesh
mesh = TensorMesh([[1.0, 2.0, 3.0], [2.0, 4.0]], origin=[0.0, 0.0])
face_velocity_m_s = np.r_[2 * mesh.faces_x[:, 0], -3 * mesh.faces_y[:, 1]]
divergence_s_inv = mesh.face_divergence @ face_velocity_m_s
integrated_divergence_m2_s = np.dot(mesh.cell_volumes, divergence_s_inv)
The rectangular area is 36 m², so the area-integrated divergence and outward
boundary flux are both -36 m²/s. In 2D, cell_volumes are cell areas.
Handoffs and checks
- Inspect
cell_centers,faces_x,faces_yand the operator shape. Keep cell, face, node and edge quantities distinct when interpolating or plotting. - Cell ordering has the first coordinate varying fastest; reshape cell vectors with Fortran order when required. Test a spatially varying field, not a uniform array that could hide an ordering error.
- Verify constants/linear fields, conservation and convergence against an independent analytic case before using a mesh in an inverse problem.
- Preserve inactive/air masks and do not turn NaNs into zero conductivity.
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.
- 1mo ago First seen · 64 lines · 49 tokens per session scan A 770b225b3814
discretize is a skill published in the GitHub repository SteadfastAsArt/geoscience-skills (70 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 702 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 2026-09-16.
Other skills, from other repositories
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.
obspy-seismology
Seismological data analysis with ObsPy — FDSN waveform download, response removal, phase picking, moment tensor inversion, and seismicity mapping.
xarray-netcdf
Labeled multi-dimensional array analysis with xarray: NetCDF/HDF5 I/O, lazy Dask loading, rechunking, Zarr stores, and CF conventions.
soil-data
Soil data analysis via SoilGrids 2.0 REST API and SSURGO: SOC stocks, texture classification, kriging interpolation, and soil profile visualization.
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…