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 jokull/icelandic-data --skill maskinagit 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/maskina)<a href="https://agentmods.dev/skills/jokull/icelandic-data/maskina"><img src="https://agentmods.dev/badge/skills/jokull/icelandic-data/maskina.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.05883 |
| Opus 5 | $0.00016 | $0.02942 |
| Sonnet 5 | $0.00007 | $0.01177 |
| Haiku 4.5 | $0.00003 | $0.00588 |
Grade A, and why
maskina 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 8d 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 'https://maskina.is/wp-json/wp/v2/posts?per_page=5&orderby=date&order=desc&_fields=id,title,date,link,excerpt' How it starts
The opening of the file, as written. The whole thing — 453 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maskína — Public Opinion Polls
Public opinion polls and surveys from Iceland's leading polling company. Two data sources: WordPress articles (prose) and Tableau Public dashboard (structured).
This is the first stop for opinion-poll questions. The data here comes
structured, straight from the pollster — no browser, no news-article
scraping. Only when the question needs other pollsters (Gallup, Prósent,
Félagsvísindastofnun), cross-pollster comparison, or polls Maskína never
published itself should you fall back to the heavier skodanakannanir skill
(number extraction from RÚV/Vísir/Heimildin news articles).
Data Sources
1. WordPress REST API (articles)
Base URL: https://maskina.is/wp-json/wp/v2/posts
Open API, no authentication. Standard WP REST endpoints.
# Latest posts
curl 'https://maskina.is/wp-json/wp/v2/posts?per_page=5&orderby=date&order=desc&_fields=id,title,date,link,excerpt'
# Search for party support polls
curl 'https://maskina.is/wp-json/wp/v2/posts?search=fylgi&per_page=5&_fields=id,title,date,link,excerpt'
# Full article by ID
curl 'https://maskina.is/wp-json/wp/v2/posts/6412?_fields=id,title,date,link,content'
Content format: HTML in content.rendered. Requires HTML stripping. Poll data is embedded as prose text — "Samfylkingin stendur nú í um 25% fylgi".
Search is a full-text index, not a fixed set of topics. /wp/v2/categories
returns only Fréttir (339 posts) and Uncategorized @is (32) — there is no
real taxonomy to browse. /wp/v2/tags is empty. The ?search= parameter is
the only practical way to find topical content, and it matches title + body
text freely — any word Maskína has ever polled about works, not just the
terms below.
Known recurring, branded series (repeated release after release — worth
building a systematic fetcher around, the way fylgi already is):
| Series | Search term(s) | Example title |
|---|---|---|
| Fylgi flokka (national party support) | fylgi |
"Ný fylgismæling fyrir flokka á Alþingi" |
| Borgarviti (Reykjavík city politics) | borgarviti |
"Borgarviti Maskínu: vaxandi óánægja með störf borgarstjóra" |
| Stofnanaviti (institutional trust) | stofnanaviti |
"Stofnanaviti Maskínu er kominn út!" |
| ESB/aðild (EU membership) | ESB, aðild, Evrópusambandið |
"53% hlynnt áframhaldandi aðildarviðræðum við ESB" (2026-01-12) |
| Traust til ráðherra/ríkisstjórnar (government/minister trust & approval) | ríkisstjórnin, ráðherra |
"Ný traust mæling allra ráðherra" |
| Meðmæling Maskínu (annual "recommended companies") | Meðmæling |
"12 fyrirtæki hljóta Meðmælingu Maskínu 2023" |
| Kryddsíld (year-end TV special poll) | Kryddsíld |
"Kannanir úr Kryddsíld 2023" |
| Áramótaskaupið (satisfaction with the New Year's Eve comedy show) | Áramótaskaupið |
"Gríðarleg ánægja með Áramótaskaupið" |
| Eurovision | Eurovision |
"13% horfðu á Eurovision í ár" |
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.
- 8d ago First seen · 453 lines · 33 tokens per session scan A c0b2ccfe21a4
maskina is a skill published in the GitHub repository jokull/icelandic-data (52 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 5,883 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…