A reference for open XML data from Alþingi, Iceland's Parliament. It covers members of parliament, votes, bills, committees, speeches, ministers, and public consultation submissions.

Use it to research Icelandic parliamentary activity, including how members voted, which committees handled matters, what was said in speeches, and which submissions were made.

It provides structured parliamentary records without requiring authentication. The data is updated about once a day and may be cached for up to roughly ten minutes.

althingi — Skill for Claude Code and Codex by jokull/icelandic-data

Install

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.

Clone the repo

git clone --depth 1 https://github.com/jokull/icelandic-data

agentmods

npx agentmods add skills/jokull/icelandic-data/althingi

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jokull/icelandic-data/althingi/github.svg)](https://agentmods.dev/skills/jokull/icelandic-data/althingi)

Your own site

<a href="https://agentmods.dev/skills/jokull/icelandic-data/althingi"><img src="https://agentmods.dev/badge/skills/jokull/icelandic-data/althingi/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jokull/icelandic-data/althingi"><img src="https://agentmods.dev/badge/skills/jokull/icelandic-data/althingi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 7,394 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00034	$0.07394
Opus 5.5	$0.00014	$0.02958
Sonnet 5.5	$0.00007	$0.01479
Haiku 4.5	$0.00003	$0.00739

Measured 1mo ago against content hash 464569e84b26, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

althingi 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 1mo 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.

UA, is the failure mode. `curl` works out of the box, so this bites only when

.agents/skills/althingi/SKILL.md · 465 lines

How it starts

The opening of the file, as written. The whole thing — 465 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Alþingi — Parliament XML

Requires: Tier 0 (core).

Open XML feeds from the Alþingi database: every MP since 1875, per-MP roll-call votes, the parliamentary matter catalogue, committee membership, speeches, ministerial appointments and consultation submissions.

API

Base URL: https://www.althingi.is/altext/xml/

No authentication, no rate limit published. Plain GET, no query language — each endpoint is a fixed path with query-string filters. Responses are text/xml; charset=utf-8.

Send a User-Agent. The site returns 403 Forbidden to httpx's default UA. Any identifying string is accepted — sending none, or a default library UA, is the failure mode. curl works out of the box, so this bites only when moving from a shell probe to code.

Responses are served through Cloudflare and come back cf-cache-status: HIT with an age of up to ~10 minutes. Combined with the daily refresh, treat anything you read as up to a day old.

Data refreshes once per day ("Gögnin uppfærast að öllu jöfnu einu sinni á sólarhring"), so there is nothing to gain from polling faster.

There is no schema

Alþingi states outright: "Ekki er til xml-skema fyrir gögnin, nema Alþingistíðindi" and "Framsetningin á gögnunum geta tekið breytingum án fyrirvara" — no XSD except for Alþingistíðindi, and the shape may change without notice.

In practice there is no schema at all. The two XSDs the index page links for the record proper — http://skema.althingi.is/skema/althingi_{gerdabok,raedur}.xsd — are dead: skema.althingi.is returns no DNS answer (checked 2026-08-15, while www.althingi.is resolves normally). Do not plan on validating against them.

So everything here is shape-by-observation. That is what the health probe guards, and it is why it asserts Icelandic element names rather than values.

Element names are Icelandic

Tags are <þingmaður>, <atkvæðagreiðsla>, <þingflokkur>, <kjördæmi> — non-ASCII, which is legal XML but unusual. Both lxml and stdlib xml.etree.ElementTree handle it; this repo uses the stdlib parser, so no new dependency. Parse from bytes (resp.content), never resp.text — the documents carry their own encoding declaration and a str input trips ValueError: Unicode strings with encoding declaration are not supported.

Read the full file on GitHub · 465 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.

1mo ago Changed · +2 lines 464569e84b26
2mo ago First seen · 463 lines · 34 tokens per session scan A 75c5f1431250

Subscribe to this mod's changes

althingi is a skill published in the GitHub repository jokull/icelandic-data (57 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 7,394 once invoked, about $0.0001 per session on Opus 5.5. 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.

Research

althingi next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
althingijokull/icelandic-data	Skill	57	yesterday	MIT	A	34	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

althingi