A Python tool that turns scattered geographic or Cartesian point measurements into regular grids using interpolation. Interpolation estimates values between known points, while a grid arranges the results in rows and columns.

Use it to grid elevation or other point data with spline, linear, or cubic methods, reduce dense data, remove trends, process vectors, and save results as NetCDF.

It makes unevenly spaced measurements easier to analyse, map, reduce, and save as structured datasets.

verde — Skill for Claude Code and Codex by SteadfastAsArt

Install

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.

Any agent

npx skills add SteadfastAsArt/geoscience-skills --skill verde

Clone the repo

git clone --depth 1 https://github.com/SteadfastAsArt/geoscience-skills

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin verde — /plugin install verde after adding the marketplace above.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/steadfastasart/geoscience-skills/verde/github.svg)](https://agentmods.dev/skills/steadfastasart/geoscience-skills/verde)

Your own site

<a href="https://agentmods.dev/skills/steadfastasart/geoscience-skills/verde"><img src="https://agentmods.dev/badge/skills/steadfastasart/geoscience-skills/verde/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/steadfastasart/geoscience-skills/verde"><img src="https://agentmods.dev/badge/skills/steadfastasart/geoscience-skills/verde.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,655 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00123	$0.01655
Opus 5	$0.00062	$0.00827
Sonnet 5	$0.00025	$0.00331
Haiku 4.5	$0.00012	$0.00166

Measured 9d ago against content hash 31b0179f1357, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

verde 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/grid_data.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

verde/SKILL.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verde - Spatial Data Gridding

Quick Reference

import verde as vd

# Basic gridding
spline = vd.Spline()
spline.fit(coordinates, values)  # coordinates = (lon, lat) tuple
grid = spline.grid(spacing=0.1)  # Returns xarray Dataset

# Access result
elevation = grid.elevation.values

# Save output
grid.to_netcdf('output.nc')

Key Classes

Class	Purpose
`Spline`	Bi-harmonic spline interpolation (smooth, good extrapolation)
`Linear`	Delaunay triangulation (fast, no extrapolation)
`Cubic`	Cubic interpolation (medium smoothness)
`Chain`	Pipeline of processing steps
`BlockReduce`	Decimate data to block means/medians
`Trend`	Polynomial trend fitting and removal
`Vector`	Grid 2-component vector data

Essential Operations

Grid Scattered Data

coordinates = (longitude, latitude)  # Tuple of 1D arrays
values = elevation  # 1D array

spline = vd.Spline()
spline.fit(coordinates, values)
grid = spline.grid(spacing=0.1, data_names=['elevation'])

Project to Cartesian

import pyproj

projection = pyproj.Proj(proj='merc', lat_ts=data_lat.mean())
proj_coords = projection(longitude, latitude)

spline = vd.Spline()
spline.fit(proj_coords, values)
grid = spline.grid(spacing=1000)  # 1000m spacing

Block Reduce Large Datasets

import numpy as np

reducer = vd.BlockReduce(reduction=np.median, spacing=0.1)
coords_reduced, values_reduced = reducer.filter(coordinates, values)

Remove Trend Before Gridding

trend = vd.Trend(degree=2)  # Quadratic
trend.fit(coordinates, values)
residuals = values - trend.predict(coordinates)

# Grid residuals, then add trend back

Processing Pipeline

chain = vd.Chain([
    ('trend', vd.Trend(degree=1)),
    ('reduce', vd.BlockReduce(np.median, spacing=0.05)),
    ('spline', vd.Spline())
])
chain.fit(coordinates, values)
grid = chain.grid(spacing=0.01)

Cross-Validation

spline = vd.Spline()
scores = vd.cross_val_score(spline, coordinates, values, cv=5)
print(f"Mean R2: {scores.mean():.3f}")

Read the full file on GitHub · 191 lines

Files

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.

Changes

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.

9d ago First seen · 191 lines · 123 tokens per session scan A 31b0179f1357

Subscribe to this mod's changes

verde is a skill published in the GitHub repository SteadfastAsArt/geoscience-skills (57 stars, last pushed 5mo ago), licensed MIT. It adds 123 tokens to every session and 1,655 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.

Block Reduction Claude Code Cross-Validation Fatiando Gridding Interpolation Scientific Spline Verde ai-agents geophysics geoscience spatial-analysis

gis-skills

Use when processing geospatial data, publishing map services, querying spatial databases, performing geometry operations, or building web map applications. Index of 23 skills: GDAL, GeoServer, QGIS, PostGIS, JTS, GeoPandas, Shapely, CesiumJS, OpenLayers, NetTopologySuite and more.

znlgis/opengis-skills · 71 tokens

verde