A reusable guide and code library for reading public Power BI dashboards, which are interactive reports embedded in websites. It explains how to obtain their public report details and replay their data queries.

Use it to build connectors for public Power BI reports, retrieve dashboard data, change filters such as years or slicers, and decode the returned results.

Many Icelandic public bodies publish data only through dashboards, making ordinary web requests insufficient.

powerbi — Skill for Claude Code and Codex by jokull: A reusable guide and code library for reading public…

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.

agentmods

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

Any agent

npx skills add jokull/icelandic-data --skill powerbi

Clone the repo

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

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/powerbi.svg)](https://agentmods.dev/skills/jokull/icelandic-data/powerbi)

Your own site

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

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,677 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00000	$0.01677
Opus 5	$0.00000	$0.00839
Sonnet 5	$0.00000	$0.00335
Haiku 4.5	$0.00000	$0.00168

Measured 6d ago against content hash 8604c05892c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

powerbi 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 6d 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.

.agents/skills/powerbi/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Power BI dashboard reverse-engineering

Icelandic public bodies publish a lot of data only as embedded Power BI dashboards (https://app.powerbi.com/view?r=<token>, often inside an <iframe> on the agency's site). They all speak one protocol, so scripts/powerbi.py factors out the generalizable parts. A per-source script supplies only the SPA URL, which section to open, and the slicer/column names.

Sources in this repo that are Power BI underneath: samgongustofa (fully migrated — the reference implementation), plus landlaeknir, vernd, farsaeld_barna, ferdamalastofa, tekjusagan, vinnumalastofnun, maelabord_nautgripa, sedlabanki_rates. The last group still only captures whatever fires on page load; migrate them to powerbi.py when they need parameterized queries (change a slicer, pull another year).

The protocol (what's identical everywhere)

Embed token — ?r=<base64({"k":resourceKey,"t":tenant,"c":cluster})>. pb.embed_url(key, tenant) builds it; pb.key_of(url) / pb.token_of(url) decode it. Keys rotate — never hardcode; read them live.
Query endpoint — https://wabi-<region>-<x>-api.analysis.windows.net/ public/reports/querydata?synchronous=true, header x-powerbi-resourcekey: <key>, no bearer for public reports.
Auth reality — the anonymous grant is session-, origin- and rate-bound. A cold httpx client works for a few requests then 401s (PowerBINotAuthorizedException; the API even exposes retry-after), and a POST from any origin other than the app.powerbi.com iframe is rejected. So the robust move is to replay queries with fetch() inside the iframe.
Request body — a SemanticQueryDataShapeCommand. Capture the report's own request as a template and rewrite its Where; the body must keep its top-level modelId/version/cancelQueries or you get 400 "ModelId must be between 1 and 9.2e18".
Response — a DSR (DataShapeResult): a compressed columnar format with ValueDicts (int→string), an R repeat-bitmask (carry the previous row's value) and a Ø null-bitmask. Decompress it or you silently undercount — the naive row["C"][0], row["C"][1] reader drops every compressed row.

Read the full file on GitHub · 113 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.

6d ago First seen · 113 lines · 0 tokens per session scan A 8604c05892c0

Subscribe to this mod's changes

powerbi is a skill published in the GitHub repository jokull/icelandic-data (52 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,677 tokens. 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.

Analytics and metrics

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

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

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens