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/rikisreikningurWrote 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/rikisreikningur)<a href="https://agentmods.dev/skills/jokull/icelandic-data/rikisreikningur"><img src="https://agentmods.dev/badge/skills/jokull/icelandic-data/rikisreikningur/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/rikisreikningur"><img src="https://agentmods.dev/badge/skills/jokull/icelandic-data/rikisreikningur.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 | $0.00055 | $0.03398 |
| Opus 5 | $0.00028 | $0.01699 |
| Sonnet 5 | $0.00011 | $0.00680 |
| Haiku 4.5 | $0.00006 | $0.00340 |
Grade A, and why
rikisreikningur 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 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.
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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ríkisreikningur — state accounts (Fjársýsla ríkisins)
Requires: Tier 0 (core).
Government-wide revenue, expenditure, and surplus/deficit from the state
treasury. rikisreikningur.is is the public disclosure portal operated by
Fjársýsla ríkisins (State Treasury / Financial Management Authority).
Published data:
- Annual state accounts (ríkisreikningur) back to 2004
- In-year monthly summaries (mánaðaryfirlit) for the current fiscal year
- "Heimamundur" — a detailed per-institution ledger published as XLSX
- A front-page dashboard of revenue/expense category and málefnasvið (policy-area) breakdown
Architecture
React SPA at rikisreikningur.is. Data comes from a small Azure Functions
backend at rikisreikningurapi.azurewebsites.net with four JSON endpoints
plus a file-download endpoint. An X-Api-Key header is required — the key
is hard-coded in the public JS bundle and is effectively an anonymous
throttling key, not a secret.
API
| Endpoint | Returns |
|---|---|
GET /api/FJS/NuverandiTimabil |
{"ar": "2025", "timabil": "06"} — latest closed period. timabil 01–12 = monthly, 13 = full-year accounts |
GET /api/FJS/TekjurOgGjold |
{"afkoma":[…], "tekjur_gjold":[…]} — yearly surplus/deficit + revenue/expense split into 7 categories (see below) |
GET /api/FJS/Data/malefni_tg |
Revenue & expense by málefnasvið (policy area 01–36) × year × type — ~620 rows |
GET /api/FJS/Data/skrar |
Manifest of downloadable Excel/CSV files (ríkisreikningur, heimamundur, forsidugogn) |
GET /api/Files/Rikisreikningur/{name} |
Raw file download (XLSX/CSV/PDF) |
Auth header: X-Api-Key: 6d4d7394-2992-473d-9ea7-45946b39ad9d
This is not a secret — do not move it to an env var or a repo secret. It is a
static public key shipped in the SPA's own JS bundle (verified: it appears in
https://www.rikisreikningur.is/static/js/main.*.chunk.js), so every visitor to
the site already has it. Hardcoding it is correct; hiding it would only break
scripts/rikisreikningur.py for anyone cloning the repo.
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 76c4d80815b5
- 12d ago First seen · 227 lines · 55 tokens per session scan A 038ab3be566f
rikisreikningur is a skill published in the GitHub repository jokull/icelandic-data (53 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 3,398 once invoked, about $0.0003 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
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.