Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jokull/icelandic-datanpx agentmods add skills/jokull/icelandic-data/farsaeld-barnaWrote 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/farsaeld-barna)<a href="https://agentmods.dev/skills/jokull/icelandic-data/farsaeld-barna"><img src="https://agentmods.dev/badge/skills/jokull/icelandic-data/farsaeld-barna/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/jokull/icelandic-data/farsaeld-barna"><img src="https://agentmods.dev/badge/skills/jokull/icelandic-data/farsaeld-barna.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00032 | $0.00874 |
| Opus 5 | $0.00016 | $0.00437 |
| Sonnet 5 | $0.00006 | $0.00175 |
| Haiku 4.5 | $0.00003 | $0.00087 |
Grade A, and why
farsaeld-barna 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.
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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Farsæld barna — Child Wellbeing Dashboard
Statistical indicators on child wellbeing in Iceland: health, happiness, education, safety, opportunities, living standards, social relationships, family life, participation, and influence on decisions.
Run by Barna- og fjölskyldustofa (BOFS), operational since 1 January 2022 (merged from Barnaverndarstofa). Explicitly named in the Hagtalnanefnd report (March 2026, footnote 71) as an example of a dashboard where raw data is not made available — only the dashboard and reports.
Landing page
https://farsaeldbarna.is/ — consolidates statistical data underpinning the Farsældarlögin (Child Wellbeing Act, enacted 2022).
Power BI dashboard
| Property | Value |
|---|---|
| Tenant | bc14a44e-e0fb-4e0b-a535-100579d41b65 |
| Report key | 1fcb76a3-b53d-4ba1-a5c9-434d8c346408 |
| Embed URL | https://app.powerbi.com/view?r=<base64> — see scripts/farsaeld_barna.py |
Organized around five "foundations" of wellbeing (implementation framework from Farsældarlögin). Specific indicators not listed on the landing page — enumerate them from scraped Power BI descriptors.
Extraction
Playwright-intercept pattern, but note: this dashboard is a "publish to web" Power BI with static embedded data, not live DAX queries. The data lives in the modelsAndExploration endpoint response (~2 MB JSON), not in executeQueries. The scraper captures: modelsAndExploration, conceptualschema, and resourcePackage blobs. No auth needed.
Script usage
uv run python scripts/farsaeld_barna.py fetch
Data files
| Path | Format | Description |
|---|---|---|
data/raw/farsaeld_barna/powerbi.json |
JSON | Raw Power BI executeQueries responses |
Caveats
- No raw data download. The Hagtalnanefnd report flags this dashboard as one where grunngögn (raw data) are not made available to users — only the dashboard itself. Scraping the Power BI responses is the only route to structured data.
- Stale series warning. Because the data aggregation is across many agency feeds (Hagstofa, HMS, Landlæknir, police, schools), individual indicators may lag the agency's own dashboard. Check the "last updated" text on each tile.
- Overlap with source datasets. Many underlying series are already reachable more directly via hagstofan, landlaeknir, or reykjavik (municipality-level welfare data). Prefer source when available.
- Attribution. Data sourced from multiple public agencies — BOFS coordinates but does not own the underlying series.
- Encoding. Power BI
modelsAndExplorationpayload is UTF-8 throughout (Icelandic chars in dimension labels and indicator titles). Write JSON withensure_ascii=Falseand read withencoding="utf-8".
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 · 58 lines · 32 tokens per session scan A 9173731c51f8
farsaeld-barna is a skill published in the GitHub repository jokull/icelandic-data (52 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 874 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 2026-08-30.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…