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 pastasgit 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/pastas)<a href="https://agentmods.dev/skills/steadfastasart/geoscience-skills/pastas"><img src="https://agentmods.dev/badge/skills/steadfastasart/geoscience-skills/pastas/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/pastas"><img src="https://agentmods.dev/badge/skills/steadfastasart/geoscience-skills/pastas.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 | $0.00096 | $0.01472 |
| Opus 5.5 | $0.00038 | $0.00589 |
| Sonnet 5.5 | $0.00019 | $0.00294 |
| Haiku 4.5 | $0.00010 | $0.00147 |
Grade A, and why
pastas 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Groundwater response models with Pastas
Use Pastas for a well's response to time-varying stresses. Fitted response parameters are effective model parameters; they do not by themselves establish transmissivity, aquifer geometry or hydraulic connectivity. Use FloPy/MODFLOW for a supported spatial-flow question.
This entrypoint targets Pastas 2.0. Its component constructors accept the
owning model and register themselves; older add_stressmodel patterns are
being retired. Use the tested dependency baseline for reproducible work. The
2.0 package also needs tqdm for its imported solver timer in the checked environment.
Prepare data and reserve evaluation dates
Record the head unit and vertical reference, well/screen, timestamp convention, stress units and whether evaporation is measured or estimated reference potential evaporation. A negative relative head or depth-to-water series is not automatically elevation above sea level. Preserve the original datum.
For daily recharge models use consistently converted head (m), precipitation and reference evaporation (mm/day). Preserve daily accumulation labels; do not invent a timezone or shift dates without knowing the observation support. Missing rainfall is not zero. Keep head gaps unfilled, check stress coverage through the model warmup, and record any stress infilling with its calibration source. Pastas defaults can fill and extend stresses, so make these choices explicit before constructing the model.
Fix calibration and holdout dates before fitting. Construct the model using calibration heads and stresses only, including data-derived initial values. Future observed stresses may support a hindcast; future observed heads must not adjust fitted parameters or simulated state. A forecast additionally needs specified future stress scenarios and uncertainty.
Calibrate a checked recharge model
This function expects unique, ordered daily-date Series, complete nonnegative stresses covering the requested observed warmup, and at least three finite calibration heads. Those input checks are enforced by the bundled helper.
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.
- 1mo ago Changed · -74 lines 889838834781
- 1mo ago Changed · +2 lines · +1 tokens per session d01f2f4d869d
- 2mo ago First seen · 202 lines · 95 tokens per session scan A 364666b24c48
pastas is a skill published in the GitHub repository SteadfastAsArt/geoscience-skills (73 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 1,472 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
earthquake-guide
Gates and workflows for the earthquake tools (USGS ComCat and EMSC). Use to judge how bad a quake was, read USGS aftershock odds, check whether a depth or location holds up, match one event across USGS and EMSC, or count and list events over years or in a region — before concluding from a missing product, a default…
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.
xarray-netcdf
Labeled multi-dimensional array analysis with xarray: NetCDF/HDF5 I/O, lazy Dask loading, rechunking, Zarr stores, and CF conventions.
obspy-seismology
Seismological data analysis with ObsPy — FDSN waveform download, response removal, phase picking, moment tensor inversion, and seismicity mapping.
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…