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 | $0.00095 | $0.01813 |
| Opus 5 | $0.00048 | $0.00907 |
| Sonnet 5 | $0.00019 | $0.00363 |
| Haiku 4.5 | $0.00010 | $0.00181 |
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 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pastas - Groundwater Time Series Analysis
Quick Reference
import pastas as ps
import pandas as pd
# Load data
head = pd.read_csv('well.csv', index_col=0, parse_dates=True).squeeze()
precip = pd.read_csv('precip.csv', index_col=0, parse_dates=True).squeeze()
evap = pd.read_csv('evap.csv', index_col=0, parse_dates=True).squeeze()
# Create model
ml = ps.Model(head, name='Well_001')
# Add recharge stress
sm = ps.RechargeModel(precip, evap, rfunc=ps.Gamma(), name='recharge')
ml.add_stressmodel(sm)
# Solve and plot
ml.solve()
ml.plot()
Key Classes
| Class | Purpose |
|---|---|
ps.Model |
Main model container |
ps.StressModel |
Response to external stress (pumping, river) |
ps.RechargeModel |
Recharge from precipitation minus evaporation |
ps.Gamma |
Gamma distribution response function |
ps.Exponential |
Simple exponential response function |
Essential Operations
Create and Solve Model
ml = ps.Model(head, name='well')
ml.add_stressmodel(ps.RechargeModel(precip, evap, rfunc=ps.Gamma(), name='recharge'))
ml.solve()
Add Pumping Well
pumping = pd.read_csv('pumping.csv', index_col=0, parse_dates=True).squeeze()
ml.add_stressmodel(ps.StressModel(pumping, rfunc=ps.Hantush(),
name='pumping', up=False)) # up=False for drawdown
Model Diagnostics
print(f"EVP: {ml.stats.evp():.1f}%") # Explained variance
print(f"RMSE: {ml.stats.rmse():.3f} m") # Root mean square error
print(f"AIC: {ml.stats.aic():.1f}") # Model selection criterion
ml.plots.diagnostics() # Diagnostic plots
ml.plots.acf() # Autocorrelation
Get Contributions
contributions = ml.get_contributions()
for name, contrib in contributions.items():
print(f"{name}: mean={contrib.mean():.2f}")
Step and Impulse Response
step = ml.get_step_response('recharge') # Step response
block = ml.get_block_response('recharge') # Impulse response
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.
- 10d ago First seen · 202 lines · 95 tokens per session scan A 364666b24c48
pastas is a skill published in the GitHub repository SteadfastAsArt/geoscience-skills (58 stars, last pushed 5mo ago), licensed MIT. It adds 95 tokens to every session and 1,813 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
tao-finetune-nv-tesseract-ad-diffusion
NV-Tesseract AD Diffusion — diffusion-based anomaly detection and fine-tuning for multivariate time series. Use when the user asks to "fine-tune NV-Tesseract", "run AD diffusion inference", "detect anomalies with diffusion", "time series anomaly detection", "finetune ad-diffusion", "use…
paper-agent
Full academic manuscript skill for quantitative-science papers, currently calibrated for hydrology and water-resources (Hydrogeology Journal, JHRS) and extensible to other quantitative-science fields via a journal style file. Five modes — Draft (write from scratch), Review (reviewer-style feedback), Revise…
mike-end-to-end
Standard operating procedure for an auditable, headless MIKE+ workflow via the mike-plus MCP server — how to plan, copy, run, QA-gate, compare, plot, audit, and safely stop. Use FIRST whenever an agent is handed a MIKE+ model (.sqlite) or result (.res1d) plus a plain-language goal; it picks the operating mode and…
atai-newton-omega-model
Get time-series embeddings from Archetype AI's Omega encoder (OmegaEncoder::omegaembeddings14) over the prod /query endpoint — send a window of sensor readings, get back a fixed-size vector per channel, no batch job and no session. Use this skill when the user wants to embed multivariate sensor windows (vibration…
mike-compare
Compare two MIKE+ runs via the mike-plus MCP server — baseline vs scenario, before vs after a parameter edit — to say WHERE a change mattered and BY HOW MUCH (delta peak, delta volume, timing shift, RMSE/NSE) and to draw the overlay hydrograph. Use whenever two .res1d files of the same model exist or a re-run just…
mike-plot
Produce publication-style figures from MIKE+ .res1d results via the mike-plus MCP server — a stacked rainfall-runoff hydrograph, a single time series, a network map, a baseline-vs-scenario overlay, or a longitudinal profile (bed / crown / ground / max water level along a pipe string), in the house style (Arial 12…