horizun-pbi-setup

horizun-pbi-setup is a skill for Claude Code, Codex from HorizunGroup/horizun-pbi-mcp. It costs 85 tokens per session (2,341 once invoked), scanned A, original, Apache-2.0.

An installation and repair guide for the local Horizun Power BI MCP runtime, a connector that lets coding agents work with Power BI. It prepares an isolated Python environment and downloads fixed proprietary files after checking their SHA-256 hashes.

In plain words
What is it for?
Use it to install, update, repair, or verify the Horizun Power BI connector for Codex or Claude.
Why use it?
It addresses missing dependencies, DLL files, schemas, or startup failures without requiring administrator access. It also verifies downloaded files before using them.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions Claude Code; mentions Codex.

Part of the horizun-pbi-mcp plugin — 2 skills, 1 MCP server shipped together

Good fit Use it to install, update, repair, or verify the Horizun Power BI connector for Codex or Claude.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/horizungroup/horizun-pbi-mcp/horizun-pbi-setup
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 HorizunGroup/horizun-pbi-mcp --skill horizun-pbi-setup
Clone the repo
git clone --depth 1 https://github.com/HorizunGroup/horizun-pbi-mcp

Made for: Claude Code, Codex.

Or install horizun-pbi-mcp, the plugin that ships this one along with the rest of its 2 skills, 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 horizun-pbi-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/horizungroup/horizun-pbi-mcp/horizun-pbi-setup/github.svg)](https://agentmods.dev/skills/horizungroup/horizun-pbi-mcp/horizun-pbi-setup)
Your own site
<a href="https://agentmods.dev/skills/horizungroup/horizun-pbi-mcp/horizun-pbi-setup"><img src="https://agentmods.dev/badge/skills/horizungroup/horizun-pbi-mcp/horizun-pbi-setup/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 horizun-pbi-setup

Your own site · 80×15
<a href="https://agentmods.dev/skills/horizungroup/horizun-pbi-mcp/horizun-pbi-setup"><img src="https://agentmods.dev/badge/skills/horizungroup/horizun-pbi-mcp/horizun-pbi-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,341 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. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00085 $0.02341
Opus 5 $0.00043 $0.01171
Sonnet 5 $0.00017 $0.00468
Haiku 4.5 $0.00009 $0.00234

Measured 7d ago against content hash 3923a47a4acf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

horizun-pbi-setup 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 7d 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/horizun-pbi-setup/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instalar Horizun PBI MCP

El plugin no incluye binarios propietarios. Prepara un entorno Python aislado y descarga las DLL y esquemas fijados, verificando sus hashes. La meta es que la persona no pelee con dependencias: las resuelves TÚ, con el instalador de un pegado y los remedios de esta skill.

Clientes de escritorio gratuitos

  • ChatGPT Desktop Free: el instalador de un pegado registra el marketplace personal en ~/.agents/plugins/marketplace.json. Después se reinicia la app y se instala Horizun PBI MCP desde Plugins → Personal. No usa API key.
  • Claude Desktop Free: se instala el asset horizun-pbi-mcp-2.1.1.mcpb de la release con doble clic. Claude aporta el bootstrap UV/Python; no exige Claude Code ni editar claude_desktop_config.json.
  • En ambos, primero pueden aparecer solo pbi_install_runtime y pbi_install_status. Espera ready y reinicia el cliente una vez para cargar el conjunto completo.

El prompt de instalación (lo único que la persona pega)

Cuando alguien diga "instálame el MCP de Power BI" (o llegue con este prompt), este es el runbook completo. Todo es a nivel usuario; nunca pidas administrador.

  1. Corre el instalador de un pegado en PowerShell: El bloque exacto esta en scripts/one_paste.ps1 y se reproduce integro en docs/INSTALL.md. No lo escribas de memoria ni lo acortes: descarga desde una release fija, comprueba el SHA-256 y solo entonces ejecuta.
$ErrorActionPreference = 'Stop'
$url = 'https://github.com/HorizunGroup/horizun-pbi-mcp/releases/download/v2.1.1/horizun-pbi-mcp-instalar.ps1'
$sha = 'd58916465bfb8af1c12da85e6d626e8d35ce62a2efdf7c3d5c7481fe9343b3ef'
$max = 131072
$tmp = Join-Path ([IO.Path]::GetTempPath()) ('horizun-' + [guid]::NewGuid().ToString('N') + '.ps1')
# En que punto se quedo, para que el mensaje final diga la verdad y no una
# formula. Antes, un instalador que se ejecutaba y devolvia error terminaba
# imprimiendo "No se ejecuto nada que no coincidiera con el hash publicado":
# cierto en lo literal y enganoso en lo que la persona entiende, que es que no
# se ejecuto nada.
$fase = 'descarga'
$ejecutado = $false
try {
    [Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12
    $peticion = [Net.HttpWebRequest]::Create($url)
    $peticion.UserAgent = 'horizun-pbi-mcp-one-paste'
    $peticion.Timeout = 60000
    $respuesta = $peticion.GetResponse()
    if ($respuesta.ContentLength -gt $max) {
        throw ("El servidor anuncia " + $respuesta.ContentLength + " bytes y el maximo aceptado es " + $max + ". No se descarga nada.")
    }
    $entrada = $respuesta.GetResponseStream()
    $salida = [IO.File]::Open($tmp, 'Create', 'Write', 'None')
    $total = 0
    try {
        $bloque = New-Object byte[] 8192
        while (($leidos = $entrada.Read($bloque, 0, $bloque.Length)) -gt 0) {
            $total += $leidos
            if ($total -gt $max) {
                throw ("La descarga supero " + $max + " bytes mientras bajaba. Se aborta sin ejecutar nada.")
            }
            $salida.Write($bloque, 0, $leidos)
        }
    } finally {
        $salida.Dispose(); $entrada.Dispose(); $respuesta.Dispose()
    }
    if ($total -eq 0) { throw "La descarga llego vacia. No se ejecuta nada." }
    $fase = 'verificacion'
    if ($sha -cnotmatch '^[0-9a-f]{64}$') {
        throw "El hash publicado en el bloque no es un SHA-256 de 64 hex en minusculas. No se ejecuta nada."
    }
    $flujo = [IO.File]::Open($tmp, 'Open', 'Read', 'Read')
    try {
        $algoritmo = [Security.Cryptography.SHA256]::Create()
        try { $digest = $algoritmo.ComputeHash($flujo) } finally { $algoritmo.Dispose() }
    } finally { $flujo.Dispose() }
    $real = [BitConverter]::ToString($digest).Replace('-', '').ToLowerInvariant()
    if ($real.Length -ne 64) {
        throw "No se pudo calcular el SHA-256 de lo descargado. No se ejecuta nada."
    }
    if ($real -ne $sha) {
        throw ("SHA-256 NO coincide. Esperado " + $sha + ", recibido " + $real + ". No se ejecuta nada.")
    }
    $fase = 'ejecucion'
    Write-Host ("SHA-256 verificado sobre " + $total + " bytes. Ejecutando el instalador...") -ForegroundColor Green
    $ps = [IO.Path]::Combine($PSHOME, 'powershell.exe')
    if (-not [IO.File]::Exists($ps)) {
        $ps = [IO.Path]::Combine([Environment]::SystemDirectory, 'WindowsPowerShell', 'v1.0', 'powershell.exe')
    }
    if (-not [IO.File]::Exists($ps)) {
        throw "No se encontro Windows PowerShell. No se ejecuta nada."
    }
    & $ps -NoProfile -ExecutionPolicy Bypass -File $tmp
    $ejecutado = $true
    if ($LASTEXITCODE -ne 0) {
        throw ("El instalador termino con codigo " + $LASTEXITCODE + ".")
    }
} catch {
    Write-Host ""
    Write-Host ("[ERROR] Instalacion abortada: " + $_.Exception.Message) -ForegroundColor Red
    if ($ejecutado) {
        Write-Host "        El instalador SI llego a ejecutarse: sus bytes coincidian con el hash publicado, y fallo durante la instalacion." -ForegroundColor Red
    } else {
        Write-Host ("        No se ejecuto nada: se aborto en la fase '" + $fase + "', antes de lanzar el instalador.") -ForegroundColor Red
    }
    throw
} finally {
    if (Test-Path -LiteralPath $tmp) { Remove-Item -LiteralPath $tmp -Force -ErrorAction SilentlyContinue }
}

Read the full file on GitHub · 164 lines

Files

What ships with it

1 file 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.

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. 7d ago Changed · +13 lines 3923a47a4acf
  2. 12d ago First seen · 151 lines · 85 tokens per session scan A 90a94bb0ff8c

Subscribe to this mod's changes

horizun-pbi-setup is a skill published in the GitHub repository HorizunGroup/horizun-pbi-mcp (13 stars, last pushed 7d ago), licensed Apache-2.0. It adds 85 tokens to every session and 2,341 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

insights-dashboard

Use this skill whenever the user wants to create, build, set up, or fix a dashboard in Frappe Insights (also called "Insights", "Frappe Insights v3", or the analytics module). Trigger on phrases like: "create an Insights dashboard", "build a dashboard in Insights", "add a chart to a workbook", "create a workbook"…

buildswithpaul/Frappe_Assistant_Core · 133 tokens

reusable-visualization

Build ONE reusable chart visualization component that receives its data and its settings from the host application instead of fetching them, and declares the fields and config options the host exposes to viewers. Use this whenever a single chart component is reused across many different queries rather than built for…

lightdash/lightdash · 102 tokens

lightdash-agent-slack-messaging

Use this skill when writing, designing, or generating Slack messages for Lightdash's in-app analytics agent. Triggers when someone asks to create agent update messages, Slack digests, agent notifications, weekly summaries, daily summaries, or any Slack copy for the Lightdash project agent. Also use when asked to vary…

lightdash/lightdash · 114 tokens

upgrade-preflight

Checks whether a self-hosted Lightdash upgrade is safe to run, and reads the tooling's answer without over-reading it. Use when upgrading a self-hosted instance, planning a maintenance window, answering "is this upgrade safe", or recovering a failed, hung, parked or lock-stuck migration — covers lightdash…

lightdash/lightdash · 101 tokens

developing-in-lightdash

Use when reading, creating, and editing Lightdash dashboards and charts as JSON, including dashboard layout and chart-type-specific configuration.

lightdash/lightdash · 31 tokens

developing-data-apps-locally

Use when editing a locally created or downloaded Lightdash data app — how local editing, building, and uploading work, and what is read-only.

lightdash/lightdash · 38 tokens