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 agentmods add skills/jokull/icelandic-data/new-data-sourcenpx skills add jokull/icelandic-data --skill new-data-sourcegit clone --depth 1 https://github.com/jokull/icelandic-dataWrote 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/jokull/icelandic-data/new-data-source)<a href="https://agentmods.dev/skills/jokull/icelandic-data/new-data-source"><img src="https://agentmods.dev/badge/skills/jokull/icelandic-data/new-data-source.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.03648 |
| Opus 5 | $0.00015 | $0.01824 |
| Sonnet 5 | $0.00006 | $0.00730 |
| Haiku 4.5 | $0.00003 | $0.00365 |
Grade A, and why
new-data-source scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://{domain}/geoserver/wfs?service=WFS&request=GetCapabilities" | head -50 How it starts
The opening of the file, as written. The whole thing — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New Data Source — How to Learn and Integrate
Step-by-step methodology for adding a new Icelandic data source to this toolkit. Based on proven patterns from 20+ existing skills.
Phase 1: Discovery
Goal: Understand what the source offers before writing any code.
1.1 Find the API
Most Icelandic public data is served via one of these patterns:
| Pattern | Examples | How to detect |
|---|---|---|
| REST/JSON API | Hagstofan, UST (loftgæði) | /api/ in URL, returns JSON |
| WFS (GeoServer) | Vegagerðin, LMI | geoserver in URL, ?service=WFS |
| PX-Web | Hagstofan, Reykjavík | .px files, POST with JSON query |
| Power BI embed | Samgöngustofa, Ferdamálastofa | app.powerbi.com/view?r= in page source |
| CKAN | Reykjavík open data | /api/3/action/ in URL |
| Static files (Excel/CSV) | Seðlabanki | Direct download links |
| Web scraping needed | Skatturinn, Nasdaq | No API — HTML pages, login flows |
First moves:
# Check for WFS/WMS capabilities
curl -s "https://{domain}/geoserver/wfs?service=WFS&request=GetCapabilities" | head -50
# Check for REST API
curl -s "https://{domain}/api/" | jq .
# Check for CKAN
curl -s "https://{domain}/api/3/action/package_list" | jq '.result[:10]'
1.2 Probe the API
Once you know the type, enumerate what's available:
For WFS (GeoServer):
# List all layers
curl -s "{base}?service=WFS&version=2.0.0&request=GetCapabilities"
# Fetch 3 features to inspect schema
curl -s "{base}?service=WFS&version=2.0.0&request=GetFeature&typeName={layer}&outputFormat=application/json&count=3&srsName=EPSG:4326"
For REST APIs:
# Hit the root/docs endpoint
curl -s "{base}/" | jq .
# Try common endpoint patterns
curl -s "{base}/stations" | jq '.[0]'
curl -s "{base}/data?limit=5" | jq .
For Power BI: read the powerbi skill and reuse scripts/powerbi.py.
It already handles the embed token, the in-iframe query replay (a cold httpx
client 401s — the grant is origin/session/rate-bound), and DSR decompression
(skip it and you silently undercount). samgongustofa.py is the reference
implementation to copy. Don't re-solve any of this by hand.
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.
- 3d ago First seen · 353 lines · 31 tokens per session scan A c73ac1c860f3
new-data-source is a skill published in the GitHub repository jokull/icelandic-data (52 stars, last pushed 4d ago), licensed MIT. It adds 31 tokens to every session and 3,648 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.