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 santoshkanthety/powerbi-agent --skill powerbi-performance-scalegit clone --depth 1 https://github.com/santoshkanthety/powerbi-agentWrote 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/santoshkanthety/powerbi-agent/powerbi-performance-scale)<a href="https://agentmods.dev/skills/santoshkanthety/powerbi-agent/powerbi-performance-scale"><img src="https://agentmods.dev/badge/skills/santoshkanthety/powerbi-agent/powerbi-performance-scale/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/santoshkanthety/powerbi-agent/powerbi-performance-scale"><img src="https://agentmods.dev/badge/skills/santoshkanthety/powerbi-agent/powerbi-performance-scale.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00069 | $0.01396 |
| Opus 5 | $0.00034 | $0.00698 |
| Sonnet 5 | $0.00014 | $0.00279 |
| Haiku 4.5 | $0.00007 | $0.00140 |
Grade A, and why
powerbi-performance-scale 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Performance & Scale — Enterprise-Grade Power BI
Trigger
Activate when the user mentions: slow report, performance, DirectQuery, DirectLake, Import mode, aggregations, composite model, large dataset, timeout, query performance, DAX Studio, Performance Analyzer, V-Order, OPTIMIZE, memory, Premium, Fabric capacity, large model
What You Know
You have optimised Power BI semantic models from sub-optimal 10-second page loads down to sub-second. You understand the full query path from DAX → xmVelocity → Formula Engine → Storage Engine → source data, and where to intervene at each layer.
Storage Mode Decision Framework
Data volume & refresh needs → Choose mode:
< 1GB model, needs latest data always? → Import Mode (default, fastest for users)
> 1GB, PII/live data required? → DirectLake (Fabric only, best of both)
Operational live data, < 1M rows? → DirectQuery (last resort)
Mixed: history in Import + live in DQ? → Composite Model
> 10GB, Premium/Fabric? → Large Dataset Storage + Import
Import Mode Optimisation
- Remove unused columns — every column consumes memory
- Remove unused tables — check with DAX Studio dependencies
- Reduce cardinality — high-cardinality text columns kill compression
- Correct data types — INT not TEXT for numeric IDs, DATE not DATETIME when time not needed
- Disable auto date/time — creates hidden tables for every date column (massive size increase)
# Analyse model size and column cardinality
pbi-agent model analyse-size --port 12345
pbi-agent model unused-columns --threshold 0
DirectLake Mode (Fabric Only)
DirectLake reads directly from OneLake Delta tables — no import, no DirectQuery latency.
Requirements for optimal DirectLake:
✅ Delta tables with V-Order enabled (OPTIMIZE ... VORDER)
✅ Parquet file sizes 128MB–1GB
✅ Row group sizes ~1M rows
✅ Fabric capacity F64 or above for large models
✅ No unsupported DAX functions (check compatibility list)
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.
- 11d ago First seen · 149 lines · 0 tokens per session scan A 6985cb69732e
powerbi-performance-scale is a skill published in the GitHub repository santoshkanthety/powerbi-agent (2 stars, last pushed 11d ago), licensed MIT. It adds 69 tokens to every session and 1,396 once invoked, about $0.0003 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.
Other skills, from other repositories
seshat-bi
Route a BI project through Seshat BI's governed seven-stage readiness flow. Use when a user asks to inspect a retail source, initialize a Seshat project, find the truthful next action, validate readiness evidence, or stop at the correct human approval gate.
Data Retention Schedule Review
Use when reviewing a draft or existing data retention schedule to inventory data categories against stated purposes, collect retention-period facts, flag legal-hold interactions, and surface orphaned-data and vendor-coverage gaps for attorney review.
powerbi-workflows
Route guarded Power BI work -- design, native report authoring, semantic-model operations, published queries, QA, bounded formatting, and PBIP adoption -- to the correct Seshat or official Microsoft surface under Seshat BI's gates.
dbt-workflows
Route dbt intent to Seshat's governed shadow workflow or the official dbt Labs competence and execution owner, without bypassing readiness or evidence.
dagster-workflows
Route Dagster intent to Seshat's governed medallion workflow or the official Dagster competence owner without bypassing readiness, approvals, or evidence.
pbi-mcp-doctor
Use when a user asks whether or how to wire Microsoft's official Power BI MCP servers into a Seshat BI workspace: run the read-only environment doctor, map a task to the governed Power BI surface (including the official report-authoring skill), generate a safe read-only config template, or run the mocked read-only…