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.
npx skills add MinaSaad1/pbi-cli --skill power-bi-daxgit clone --depth 1 https://github.com/MinaSaad1/pbi-cliWrote 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/minasaad1/pbi-cli/power-bi-dax)<a href="https://agentmods.dev/skills/minasaad1/pbi-cli/power-bi-dax"><img src="https://agentmods.dev/badge/skills/minasaad1/pbi-cli/power-bi-dax/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/minasaad1/pbi-cli/power-bi-dax"><img src="https://agentmods.dev/badge/skills/minasaad1/pbi-cli/power-bi-dax.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 | $0.00126 | $0.01535 |
| Opus 5 | $0.00063 | $0.00767 |
| Sonnet 5 | $0.00025 | $0.00307 |
| Haiku 4.5 | $0.00013 | $0.00153 |
Grade A, and why
Power BI DAX 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 10d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- power-bi-dax — 88% identical, 14 lines differ
How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Power BI DAX Skill
Execute and validate DAX queries against connected Power BI models.
Prerequisites
pipx install pbi-cli-tool
pbi-cli skills install
pbi connect
Executing Queries
# Inline query
pbi dax execute "EVALUATE TOPN(10, Sales)"
# From file
pbi dax execute --file query.dax
# From stdin (piping)
cat query.dax | pbi dax execute -
echo "EVALUATE Sales" | pbi dax execute -
# With options
pbi dax execute "EVALUATE Sales" --max-rows 100
pbi dax execute "EVALUATE Sales" --timeout 300 # Custom timeout (seconds)
# JSON output for scripting
pbi --json dax execute "EVALUATE Sales"
DAX Expression Limitations in CLI
When passing DAX as a -e argument, the shell collapses newlines into a single line. Simple expressions like SUM(Sales[Amount]) work fine, but multi-line DAX using VAR/RETURN breaks because the DAX parser needs line breaks between those keywords.
Why this matters: A measure like VAR x = [Total Sales] VAR y = [Sales PY] RETURN DIVIDE(x - y, y) will fail with a syntax error because the engine sees it as one continuous line without statement separators.
Workarounds (pick one):
# Option 1: Pipe from stdin (recommended for measures)
echo 'VAR TotalSales = SUM(Sales[Amount])
VAR TotalCost = SUM(Sales[Cost])
RETURN TotalSales - TotalCost' | pbi measure create "Profit" -e - -t Sales
# Option 2: Write to a .dax file and use --file (for queries)
echo 'EVALUATE
ROW("Result",
VAR x = SUM(Sales[Amount])
RETURN x
)' > query.dax
pbi dax execute --file query.dax
Single-line alternatives (preferred when possible):
For simple ratio/growth measures, use inline patterns instead of VAR/RETURN:
# Instead of: VAR x = SUM(...) / VAR y = SUM(...) / RETURN DIVIDE(x, y)
# Use inline DIVIDE -- it handles division-by-zero gracefully (returns BLANK):
pbi measure create "Margin %" \
-e "DIVIDE(SUM(Sales[Amount]) - SUM(Sales[Cost]), SUM(Sales[Amount]))" \
-t Sales --format-string "0.0%"
# Instead of: VAR current = [Total Sales] / VAR prev = [Sales PY] / RETURN DIVIDE(...)
# Reference measures directly in DIVIDE:
pbi measure create "YoY %" \
-e "DIVIDE([Total Sales] - [PY Sales], [PY Sales])" \
-t Sales --format-string "0.0%"
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.
- 10d ago First seen · 211 lines · 126 tokens per session scan A 496aab8ba12b
Power BI DAX is a skill published in the GitHub repository MinaSaad1/pbi-cli (452 stars, last pushed today), licensed MIT. It adds 126 tokens to every session and 1,535 once invoked, about $0.0006 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
powerbi-expert
Expert-level Power BI, DAX, M language, data modeling, Power Query, report design, and paginated reports. Use when the user mentions DAX, Power Query, BI, Microsoft platforms, analytics, or data modeling, or when the task involves DAX Fundamentals, Advanced DAX, Row-Level Security, or Report Design.
powerbi-modeling
Power BI semantic models - DAX measures, star schemas, relationships, RLS, and performance tuning via MCP. Use when creating data models, writing DAX, or configuring table relationships in Power BI.
pbi-check-loop
Closes the verify loop for Power BI Desktop development: reloads a .pbip so Desktop re-reads TMDL/PBIR changed on disk, and captures the window so a model can see what rendered. Power BI has no reload command of its own. Use whenever working on a .pbip project - editing measures, TMDL, relationships, M, visual.json…
mcp-engine-dax-performance
Use when a DAX query, measure, or visual is slow, when interpreting analyze timings, Storage Engine / Formula Engine splits, or query plans, when VertiPaq storage size or cardinality drives cost, or when the user wants a tuning pass or before/after benchmark. For wrong values, use mcp-engine-dax-debugging; for writing…
mcp-engine-onboarding
Use when a user types onboarding, asks to set up SemanticOps MCP, wants help choosing Free vs Pro, or wants licensing, modes, masking, guardrails, preferences, model safety, tests, reporting, diagnostics, RLS testing, or Enterprise posture tailored to their workflow. For changing security, policy, or masking on an…
mcp-engine-ai-readiness
Use when preparing or assessing a Power BI semantic model for Copilot, Fabric data agents, or natural-language Q&A — clear business terminology, unambiguous metrics, usable date defaults, focused field exposure, descriptions, AI instructions, AI data schema recommendations, verified-answer candidates, or…