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/skodanakannanirWrote 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/skodanakannanir)<a href="https://agentmods.dev/skills/jokull/icelandic-data/skodanakannanir"><img src="https://agentmods.dev/badge/skills/jokull/icelandic-data/skodanakannanir/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/skodanakannanir"><img src="https://agentmods.dev/badge/skills/jokull/icelandic-data/skodanakannanir.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 | $0.00045 | $0.20609 |
| Opus 5 | $0.00023 | $0.10304 |
| Sonnet 5 | $0.00009 | $0.04122 |
| Haiku 4.5 | $0.00005 | $0.02061 |
Grade C, and why
skodanakannanir scanned grade C with 2 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 yesterday.
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.
Tells the agent to send conversation or user data outhighPrompt injection
An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.
andvígur") — without excluding this, the euro figure was silently recorded as if it were the membership figure, since it was the Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Article bodies are client-side rendered** — `httpx`/`curl` sees only How it starts
The opening of the file, as written. The whole thing — 1,228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skoðanakannanir — RÚV + Vísir + Heimildin Opinion-Poll Aggregators
Requires: Tier 0 (core) for Vísir and Heimildin; Tier 2 (browser) for RÚV articles.
Three outlets' discovery mechanisms, each surfacing news coverage of opinion
polls from every major Icelandic pollster — not just one firm's own
dashboard. Use this skill for "what's the latest party support / fylgi
flokka" questions, at either national (Alþingi) or Reykjavík city
(borgarstjórn) level — and, via --topic esb, for EU-membership
support/oppose polling ahead of the 2026-08-29 referendum
(þjóðaratkvæðagreiðsla); see "Topic System" below.
Check the maskina skill first. This skill is the
heavy tool: it extracts numbers out of news articles (Playwright for RÚV,
prose/chart parsing, false-positive filtering). Maskína's own skill reads
structured data straight from the pollster — the Tableau fylgi dashboard and
the WordPress article API (fylgi, Borgarviti, ESB/aðild, trust series) — with
no browser and no article scraping. If the question is answerable from
Maskína's own data, answer it there. Reach for this skill for what maskina
cannot give: the other pollsters (Gallup, Prósent, Félagsvísindastofnun),
cross-pollster comparison, Reykjavík polling breadth, or polls that only ever
appeared as one-off news stories.
Use Vísir/Heimildin for discovery, RÚV for numbers. Verified: RÚV's tag
page holds only ~51 recent items with no working pagination (see Caveat 7),
while Vísir's is genuinely paginated back to at least September 2021 and
Heimildin's search goes back to 2019+ for this query. list --source visir --since 2025 --scope reykjavik alone found 40 Reykjavík polls against RÚV's
4 — including the entire Feb–May 2026 city-election polling season RÚV's own
tag had already dropped. RÚV and Vísir are both wired into fetch's
chart/prose number-extraction (see Vísir Extraction below) — Heimildin is
still discovery-only. Vísir is actually the simpler of the two to fetch:
its article bodies are server-rendered, so fetch_visir_article() is plain
httpx, no Playwright, no browser at all (RÚV needs one — see the RÚV
fetch section).
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- eval/baseline-2026-07-20.json 14 KB
- eval/baseline-round2-2026-07-20.json 13 KB
- eval/baseline-round3-2026-07-20.json 13 KB
- eval/baseline-round4-2026-07-20.json 16 KB
- eval/baseline-round5-2026-07-20.json 20 KB
- eval/questions-round2.json 4.7 KB
- eval/questions-round3.json 4.9 KB
- eval/questions-round4.json 5.2 KB
- eval/questions-round5.json 6.3 KB
- eval/questions.json 3.5 KB
- reference/party-inflections-bin.json 12 KB
- reference/party-ontology-2026.json 4.8 KB
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.
- yesterday Changed · +2 lines e19bcfd1db19
- 12d ago First seen · 1,226 lines · 45 tokens per session scan C f09cfd0870dc
skodanakannanir is a skill published in the GitHub repository jokull/icelandic-data (53 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 20,609 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (tells the agent to send conversation or user data out, 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…