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 landlabgit 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/landlab)<a href="https://agentmods.dev/skills/steadfastasart/geoscience-skills/landlab"><img src="https://agentmods.dev/badge/skills/steadfastasart/geoscience-skills/landlab/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/landlab"><img src="https://agentmods.dev/badge/skills/steadfastasart/geoscience-skills/landlab.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 | $0.00115 | $0.01842 |
| Opus 5.5 | $0.00046 | $0.00737 |
| Sonnet 5.5 | $0.00023 | $0.00368 |
| Haiku 4.5 | $0.00012 | $0.00184 |
Grade A, and why
landlab 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Landlab - Surface Process Modelling
Quick Reference
from landlab import RasterModelGrid
from landlab.components import FlowAccumulator, StreamPowerEroder
import numpy as np
# Create grid
grid = RasterModelGrid((100, 100), xy_spacing=10.0)
z = grid.add_zeros('topographic__elevation', at='node')
z += np.random.rand(grid.number_of_nodes) * 0.1
# Set boundaries (open bottom edge)
grid.set_closed_boundaries_at_grid_edges(True, True, True, False)
# Create and run components
fa = FlowAccumulator(grid, flow_director='D8')
sp = StreamPowerEroder(grid, K_sp=1e-5)
for _ in range(100):
fa.run_one_step()
sp.run_one_step(dt=1000)
z[grid.core_nodes] += 0.001 * 1000 # Uplift
grid.imshow('topographic__elevation', cmap='terrain')
Grid Types
| Grid | Use Case |
|---|---|
RasterModelGrid |
Regular rectangular grids (most common) |
HexModelGrid |
Hexagonal grids (isotropic flow) |
VoronoiDelaunayGrid |
Irregular point distributions |
NetworkModelGrid |
Channel networks only |
Key Concepts
Fields and Boundaries
# Fields: data stored at grid elements (nodes, links, cells)
z = grid.add_zeros('topographic__elevation', at='node')
grid.at_node['drainage_area'] # Access existing field
# Boundaries: close all edges except outlet
grid.set_closed_boundaries_at_grid_edges(True, True, True, False)
z[grid.core_nodes] += uplift * dt # Core nodes exclude boundaries
Essential Operations
Flow Routing
from landlab.components import FlowAccumulator
fa = FlowAccumulator(grid, flow_director='D8') # or 'Steepest', 'MFD'
fa.run_one_step()
drainage_area = grid.at_node['drainage_area']
Stream Power Erosion
from landlab.components import StreamPowerEroder
sp = StreamPowerEroder(grid, K_sp=1e-5, m_sp=0.5, n_sp=1.0)
sp.run_one_step(dt=1000) # dt in years
Hillslope Diffusion
from landlab.components import LinearDiffuser
ld = LinearDiffuser(grid, linear_diffusivity=0.01) # m^2/yr
ld.run_one_step(dt=100)
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 · +2 lines · +1 tokens per session 106e8ba646f9
- 2mo ago First seen · 194 lines · 114 tokens per session scan A ab25f353b566
landlab is a skill published in the GitHub repository SteadfastAsArt/geoscience-skills (73 stars, last pushed 1mo ago), licensed MIT. It adds 115 tokens to every session and 1,842 once invoked, about $0.0005 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
torchdrug
Builds and troubleshoots TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.
deepspot-m
Generates transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Used for predicted log1p-CPM expression from 224x224 tiles at about 20x, querying the released protein-coding gene panel by symbol, and whole-slide prediction after resolution-aware tiling with histolab.
nemo-mbridge-perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.
ml-training-recipes
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…
pick-a-pii-model
Select an on-device OpenMed PII model from the committed registry by language, runtime format, and size budget, then require recall validation before deployment. Use when an agent must choose a local PII detector for CPU, Apple Silicon, or a mobile export without relying on live model discovery.
evo2
Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing per-nucleotide or per-sequence likelihoods for variant effect scoring, (2) Embedding genomic windows for downstream classification, (3) Generating DNA conditioned on a prefix, (4) Scoring…