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 joevstaas/awesome-claude-skills --skill vannmiljogit clone --depth 1 https://github.com/joevstaas/awesome-claude-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/joevstaas/awesome-claude-skills/vannmiljo)<a href="https://agentmods.dev/skills/joevstaas/awesome-claude-skills/vannmiljo"><img src="https://agentmods.dev/badge/skills/joevstaas/awesome-claude-skills/vannmiljo/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/joevstaas/awesome-claude-skills/vannmiljo"><img src="https://agentmods.dev/badge/skills/joevstaas/awesome-claude-skills/vannmiljo.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 | $0.00033 | $0.02526 |
| Opus 5 | $0.00016 | $0.01263 |
| Sonnet 5 | $0.00007 | $0.00505 |
| Haiku 4.5 | $0.00003 | $0.00253 |
Grade A, and why
vannmiljo 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 11d 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vannmiljo Data Pipeline Skill
Use this skill when working with Vannmiljo (Norwegian water monitoring) data — scraping, GeoJSON building, or ingesting into ODP.
Project Overview
The Vannmiljo project extracts water quality monitoring data from Miljodirektoratet's Vannmiljo database and ingests it into the Ocean Data Platform (ODP).
Pipeline: Vannmiljo web scraper → GeoJSON files → ODP datasets
Source: vannmiljo.miljodirektoratet.no Field documentation: vannmiljokoder.miljodirektoratet.no/files/Om_VMS_Registreringsfelt.htm
Project Structure
Vannmiljo/
├── geojson_builder.py # Builds GeoJSON from scraped Vannmiljo data
├── ingest_holmestrandsfjorden.py # Ingest script for Holmestrandsfjorden
├── test_column_metadata.py # Test script for ODP column metadata
├── input_polygons/ # GeoJSON polygons defining areas of interest
│ ├── holmestrandsfjorden.geojson
│ ├── fordefjorden.geojson
│ └── langoya.geojson
└── output/ # Generated GeoJSON files with measurements
└── holmestrandsfjorden_alle_stasjoner.geojson
PyArrow Schema for Vannmiljo Data
All Vannmiljo datasets share the same schema. All columns are pa.string() except water_location_id (int64). The id column is a generated UUID primary key.
import pyarrow as pa
VANNMILJO_SCHEMA = pa.schema([
pa.field("id", pa.string(), nullable=False),
pa.field("water_location_id", pa.int64(), nullable=True,
metadata={"description": "Unik ID for vannlokaliteten i Vannmiljo"}),
pa.field("water_location_code", pa.string(), nullable=True,
metadata={"description": "Kode som knytter registreringen til en bestemt vannlokalitet"}),
pa.field("station_name", pa.string(), nullable=True,
metadata={"description": "Navn på målestasjonen"}),
pa.field("station_description", pa.string(), nullable=True,
metadata={"description": "Beskrivelse av vannlokaliteten"}),
pa.field("act_info", pa.string(), nullable=True,
metadata={"description": "Aktivitetsinformasjon for stasjonen"}),
pa.field("faktaark_url", pa.string(), nullable=True,
metadata={"description": "URL til stasjonens faktaark i Vannmiljo"}),
pa.field("betegnelse", pa.string(), nullable=True,
metadata={"description": "Betegnelse for provetakingsaktiviteten"}),
pa.field("aktivitet", pa.string(), nullable=True,
metadata={"description": "Overvåkings- eller kartleggingsaktivitet registreringen tilhorer"}),
pa.field("oppdragsgiver", pa.string(), nullable=True,
metadata={"description": "Ansvarlig for anskaffelsen av overvåkingsoppdraget"}),
pa.field("oppdragstaker", pa.string(), nullable=True,
metadata={"description": "Utforer av overvåkingen"}),
pa.field("parameter_id", pa.string(), nullable=True,
metadata={"description": "ID for parameteren som er målt eller observert"}),
pa.field("parameter", pa.string(), nullable=True,
metadata={"description": "Navn på parameteren som er målt eller observert"}),
pa.field("cas_nr", pa.string(), nullable=True,
metadata={"description": "CAS-nummer for kjemisk komponent"}),
pa.field("medium", pa.string(), nullable=True,
metadata={"description": "Medium parameteren er målt i (vann, sediment, biota, partikler)"}),
pa.field("vitenskapelig_navn", pa.string(), nullable=True,
metadata={"description": "Vitenskapelig (latinsk) navn på art/takson"}),
pa.field("provetakingsmetode", pa.string(), nullable=True,
metadata={"description": "Standard provetakingsmetode benyttet"}),
pa.field("analysemetode", pa.string(), nullable=True,
metadata={"description": "Standard analysemetode benyttet"}),
pa.field("provenr", pa.string(), nullable=True,
metadata={"description": "Provenummer for replikate prover"}),
pa.field("filtrert_prove", pa.string(), nullable=True,
metadata={"description": "Om vannproven er filtrert gjennom 0,45 um filter"}),
pa.field("opprinnelse", pa.string(), nullable=True,
metadata={"description": "Opprinnelse for registreringen"}),
pa.field("provedato", pa.string(), nullable=True,
metadata={"description": "Tidspunkt for provetaking"}),
pa.field("operator", pa.string(), nullable=True,
metadata={"description": "Verdioperator: = (påvist), < (under grense), > (over område), ND (ikke påvist)"}),
pa.field("verdi", pa.string(), nullable=True,
metadata={"description": "Målt eller observert verdi"}),
pa.field("enhet", pa.string(), nullable=True,
metadata={"description": "Enhet for registrert verdi"}),
pa.field("listenavn", pa.string(), nullable=True,
metadata={"description": "Navn på verdilisten parameteren tilhorer"}),
pa.field("ovre_dyp", pa.string(), nullable=True,
metadata={"description": "Ovre dybdegrense i meter (vann) eller centimeter (sediment)"}),
pa.field("nedre_dyp", pa.string(), nullable=True,
metadata={"description": "Nedre dybdegrense i meter (vann) eller centimeter (sediment)"}),
pa.field("deteksjonsgrense", pa.string(), nullable=True,
metadata={"description": "Deteksjonsgrensen til den aktuelle måleverdi"}),
pa.field("kvantifiseringsgrense", pa.string(), nullable=True,
metadata={"description": "Kvantifiseringsgrensen for den aktuelle måleverdi"}),
pa.field("kommentarer", pa.string(), nullable=True,
metadata={"description": "Kommentarer knyttet til registreringen (maks 2000 tegn)"}),
pa.field("sist_endret", pa.string(), nullable=True,
metadata={"description": "Dato for siste endring av registreringen"}),
pa.field("geometry", pa.string(), nullable=True,
metadata={
"isGeometry": "1",
"index": "1",
"description": "Punkt-geometri for målestasjonen (WKT)",
}),
])
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.
- 11d ago First seen · 200 lines · 33 tokens per session scan A 3e0d4730625e
vannmiljo is a skill published in the GitHub repository joevstaas/awesome-claude-skills (6 stars, last pushed 14d ago), licensed MIT. It adds 33 tokens to every session and 2,526 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
torchdrug
Build and troubleshoot 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.
arboreto
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…
pyhealth
Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer…
deepspot-m
Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you need spatial gene expression in log1p-CPM for 224x224 tiles at about 20x, want to query protein-coding genes by symbol instead of a fixed panel, or want to run prediction across a whole slide after tiling with…
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.
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.