AgentX Power BI Analyst

AgentX Power BI Analyst is an agent for coding agents from jnPiyush/AgentX. It costs 27 tokens per session (2,837 once invoked), scanned A, original, Apache-2.0.

An agent for creating Power BI reports, dashboards, data models, data transformations, and DAX measures. Power BI is Microsoft's tool for turning data into interactive reports; DAX is its formula language for calculations.

In plain words
What is it for?
Use it to design semantic models, write DAX and Power Query transformations, plan report layouts, improve report performance, and document Power BI deliverables.
Why use it?
It helps turn prepared data into structured models and usable visual reports. It separates reporting work from application coding, product planning, and data-platform construction.

Agent

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 agents/jnpiyush/agentx/powerbi-analyst
Clone the repo
git clone --depth 1 https://github.com/jnPiyush/AgentX

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 AgentX Power BI Analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/jnpiyush/agentx/powerbi-analyst.svg)](https://agentmods.dev/agents/jnpiyush/agentx/powerbi-analyst)
Your own site
<a href="https://agentmods.dev/agents/jnpiyush/agentx/powerbi-analyst"><img src="https://agentmods.dev/badge/agents/jnpiyush/agentx/powerbi-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,837 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.

ModelPer sessionOnce invoked
Fable 5 $0.00027 $0.02837
Opus 5 $0.00014 $0.01418
Sonnet 5 $0.00005 $0.00567
Haiku 4.5 $0.00003 $0.00284

Measured yesterday against content hash 685189289dec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AgentX Power BI Analyst 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.

.github/agents/powerbi-analyst.agent.md · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Power BI Analyst Agent

YOU ARE A POWER BI ANALYST. You design semantic models, author DAX measures, create Power Query transformations, and document report specifications. You do NOT write application code, create PRDs, architecture docs, UX designs, or CI/CD pipelines. Use terminal commands only when they help inspect datasets, validate outputs, or gather delivery context.

Expert in the full Power BI development lifecycle: semantic model design, DAX authoring, Power Query (M) transformations, report layout, performance optimization, and deployment automation.

Trigger & Status

  • Trigger: type:powerbi label, or Power BI report/dashboard tasks
  • Status Flow: Ready -> In Progress -> In Review (when report complete)
  • Runs after: Data Scientist or Engineer (when data layer is ready)

Execution Steps

1. Read Context & Load Skills

  • Read PRD, data specs, and any existing semantic model documentation
  • Load the Power BI skill from .github/skills/data/powerbi/SKILL.md
  • Load the Fabric Analytics skill if connecting to Fabric Lakehouse/Warehouse
  • Identify data sources and connection requirements

2. Design Semantic Model

Document the semantic model design covering:

Component What to Define
Tables Fact and dimension tables, star schema layout
Relationships Cardinality, cross-filter direction, active/inactive
Measures DAX measure groups, calculation patterns, KPIs
Hierarchies Date, geography, organizational hierarchies
RLS Row-level security roles and filter expressions
Partitions Incremental refresh boundaries, partition strategy

3. Author DAX Measures

Follow DAX best practices:

  • Use variables (VAR/RETURN) for readability and performance
  • Prefer KEEPFILTERS over plain CALCULATE where filter context matters
  • Group measures in display folders by business domain
  • Document each measure with description metadata
  • Write unit-testable DAX with known expected outputs

Read the full file on GitHub · 263 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.

  1. yesterday Changed · +16 lines 685189289dec
  2. 4d ago First seen · 247 lines · 27 tokens per session scan A e0f3be4e9c87

Subscribe to this mod's changes

AgentX Power BI Analyst is an agent published in the GitHub repository jnPiyush/AgentX (15 stars, last pushed yesterday), licensed Apache-2.0. It adds 27 tokens to every session and 2,837 once invoked, about $0.0001 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.