validate-pbi

A command that checks a Power BI project containing a semantic model, the data structure behind reports, charts, and calculations.

In plain words
What is it for?
Use it to validate a PBIP project, run Best Practice Analyzer checks, review TMDL files, and produce a Markdown report listing errors, warnings, and documentation coverage.
Why use it?
It helps find model, calculation, relationship, naming, and documentation problems before the project is published. It also reports isolated tables and potentially confusing relationship designs.

Command for Claude Code

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 commands/luccapinto/agentic-data-kit/validate-pbi
Clone the repo
git clone --depth 1 https://github.com/luccapinto/agentic-data-kit

Made for: Claude Code.

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 427 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 $0.00427
Opus 5 $0.00014 $0.00214
Sonnet 5 $0.00005 $0.00085
Haiku 4.5 $0.00003 $0.00043

Measured 2d ago against content hash f284ca2ca3b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validate-pbi 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 2d 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.

.claude/commands/validate-pbi.md · 47 lines

What it actually says

Workflow: /validate-pbi

Usage: /validate-pbi [path/to/project.pbip]

Answers "is my model healthy?" by running the quality checks on a PBIP semantic model. If no path is given, use the project in the current folder; if there are several, ask which one.

Steps

  1. Locate the project. Use pbi-semantic-layer-tmdl to confirm a valid PBIP project. If none is found, report it and stop.
  2. Run the BPA. Use pbi-quality-rules to run the Best Practice Analyzer (Tabular Editor 2 CLI, or the TMDL-parsing fallback). Recommend the user close Desktop first so disk is current. Record every error and warning.
  3. Structural review.
    • Doc coverage: tables/measures with a description vs. total.
    • Relationships: flag island tables (no relationships), bidirectional filters, and many-to-many joins.
  4. Report — a short Markdown summary:
# Validation Report — <Project>
**Date:** <today> | **Source:** TMDL files

## Summary
| Category | Errors | Warnings |
|----------|--------|----------|
| Naming   | 0 | 3 |
| DAX      | 1 | 2 |
| Model    | 0 | 1 |
| Docs     | 0 | 8 |

## Errors (fix before publishing)
- [DAX_EMPTY_EXPRESSION] Measure "Turnover %" — empty expression

## Doc coverage
- Tables: 5/7 described (71%) · Measures: 12/20 described (60%)
  1. Offer fixes. Auto-offer to fix all errors; ask whether to address warnings and missing descriptions.
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. 2d ago First seen · 47 lines · 27 tokens per session scan A f284ca2ca3b1

Subscribe to this mod's changes

validate-pbi is a command published in the GitHub repository luccapinto/agentic-data-kit (7 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 427 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 2026-08-31.