agentmods.dev

finn-datakilde

finn-datakilde is a skill for Claude Code from tenki-labs/datanorge-mcp. It costs 198 tokens per session (1,437 once invoked), scanned A, original, MIT.

A skill for finding public datasets and APIs in Norway's data.norge.no catalogue. It searches for both downloadable files and live data services when both are available.

In plain words
What is it for?
Use it to find Norwegian public data about a topic, inspect its metadata, and retrieve data when a source is available.
Why use it?
It reduces the work of finding trustworthy public data and choosing between downloading a dataset or querying an API.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the datanorge plugin — 1 skill, 2 commands, 1 MCP server shipped together

not rated 3repo 2mo ago A scan 198 tokens original MIT

Good fit Use it to find Norwegian public data about a topic, inspect its metadata, and retrieve data when a source is available.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tenki-labs/datanorge-mcp/finn-datakilde
View source ↗ tenki-labs/datanorge-mcp
Install

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.

Any agent
npx skills add tenki-labs/datanorge-mcp --skill finn-datakilde
Clone the repo
git clone --depth 1 https://github.com/tenki-labs/datanorge-mcp

Made for: Claude Code.

Or install datanorge, the plugin that ships this one along with the rest of its 1 skill, 2 commands, 1 MCP server.

Wrote 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.

agentmods badge for finn-datakilde

README.md
[![agentmods](https://agentmods.dev/badge/skills/tenki-labs/datanorge-mcp/finn-datakilde/github.svg)](https://agentmods.dev/skills/tenki-labs/datanorge-mcp/finn-datakilde)
Your own site
<a href="https://agentmods.dev/skills/tenki-labs/datanorge-mcp/finn-datakilde"><img src="https://agentmods.dev/badge/skills/tenki-labs/datanorge-mcp/finn-datakilde/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.

agentmods 80×15 button for finn-datakilde

Your own site · 80×15
<a href="https://agentmods.dev/skills/tenki-labs/datanorge-mcp/finn-datakilde"><img src="https://agentmods.dev/badge/skills/tenki-labs/datanorge-mcp/finn-datakilde.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 198 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,437 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00198 $0.01437
Opus 5 $0.00099 $0.00718
Sonnet 5 $0.00040 $0.00287
Haiku 4.5 $0.00020 $0.00144

Measured 11d ago against content hash 260d49e2a493, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

finn-datakilde 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.

skills/finn-datakilde/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Finn datakilde

Svar på «Hvor finner jeg data om dette?» ved å lete i data.norge.no — og lever, når mulig, både et datasett (fil/nedlasting) og et API (live/oppslag) så brukeren kan velge. Krediter alltid kilden.

Verktøy (datanorge MCP)

  • search_datasets / search_apis — søk etter datasett og API-er
  • get_dataset / get_api — full metadata, lenker og lisens
  • fetch_data — hent de faktiske dataene fra en URL

Mangler verktøyene, er MCP-serveren ikke koblet til. Be brukeren installere datanorge- pluginen (eller claude mcp add datanorge -- npx -y github:tenki-labs/datanorge-mcp).

Arbeidsflyt

  1. Forstå spørsmålet. Trekk ut temaet. Ikke putt dimensjonsord i søkestrengen (kommune, per, hver, fylke, år, måned) — søk på selve temaet; dimensjonen bruker du når du leser/henter dataene. Lag 2–4 norske søkevarianter (presist begrep, synonym, bredere term).

  2. Søk i BEGGE katalogene. Kjør search_datasets og search_apis for temaet (gjerne parallelt). Målet er å gi brukeren både et datasett og et API der begge finnes.

  3. Vurder treffene. Relevans, troverdig utgiver (SSB, Kartverket, Miljødirektoratet, Meteorologisk institutt, kommuner …), åpne data, og ferskhet.

  4. Forfin — påkrevd ved 0/svake treff. Gir et søk 0 eller svake treff, må du kjøre minst én ny runde (synonym, bredere begrep, engelsk) før du konkluderer — ikke stol på at ett tilfeldig søk traff. Loop opptil ~5 runder; stopp når du har gode kandidater i begge kategorier.

  5. Hent detaljer, og par datasett med API. Kjør get_dataset og get_api for toppkandidatene. Har et datasett 0 distribusjoner (dataene ligger bak et API), kjør search_apis på samme tittel for å finne companion-API-et — datasett og API kommer ofte i par («X» + «X – API»).

  6. Lever data ved oppdeling. Ber brukeren om en oppdeling (per/hver kommune, over tid, per fylke …), ikke stopp ved katalogoppføringen: hent et lite utdrag med fetch_data som faktisk viser oppdelingen, eller si tydelig hvorfor det ikke lar seg gjøre.

Read the full file on GitHub · 82 lines

Changes

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.

  1. 11d ago First seen · 82 lines · 198 tokens per session scan A 260d49e2a493

Subscribe to this mod's changes

finn-datakilde is a skill published in the GitHub repository tenki-labs/datanorge-mcp (3 stars, last pushed 2mo ago), licensed MIT. It adds 198 tokens to every session and 1,437 once invoked, about $0.0010 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.

Research
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens