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-pbi-cligit 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-pbi-cli)<a href="https://agentmods.dev/skills/santoshkanthety/powerbi-agent/powerbi-pbi-cli"><img src="https://agentmods.dev/badge/skills/santoshkanthety/powerbi-agent/powerbi-pbi-cli/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-pbi-cli"><img src="https://agentmods.dev/badge/skills/santoshkanthety/powerbi-agent/powerbi-pbi-cli.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 | $0.00149 | $0.02476 |
| Opus 5.5 | $0.00060 | $0.00990 |
| Sonnet 5.5 | $0.00030 | $0.00495 |
| Haiku 4.5 | $0.00015 | $0.00248 |
Grade A, and why
powerbi-pbi-cli 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 16d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The pbi CLI
pbi-cli (Mina Saad, MIT) drives Power BI Desktop and PBIR report folders from the terminal:
semantic model edits over the local Analysis Services instance, and report-layer edits written
straight into PBIR JSON. It overlaps pbi-agent deliberately — use whichever is installed, and
know the differences below, because the failure modes are not the same.
Target version: ≥ 3.12.0. Earlier versions wrap every bound field as a Measure, which
silently produces broken slicers and tables. Check with pbi --version — and note that
--version itself only became trustworthy in 3.12.0, where it reads from package metadata
instead of a hardcoded constant that had drifted.
Two entry points, and it matters
| Entry point | Owns |
|---|---|
pbi |
all model and report work — connect, model, measure, report, visual, filters, bookmarks, format, database |
pbi-cli |
only skill management: pbi-cli skills install / list / uninstall |
pbi skills install does not exist. Claude Code integration is opt-in by design: pbi connect
does not write to ~/.claude/.
pipx install pbi-cli
pbi-cli skills install # opt in to the skill pack
pbi connect # attach to the open Desktop instance
pbi visual bind — the part that costs people a day
Binding a field writes a field reference into visual.json. Whether it is written as a
Column or a Measure, and whether it is wrapped in an aggregation, decides whether the
visual renders at all.
How the kind is resolved (3.12.0+)
In order:
- The TMDL or
model.bimthat the report'sdefinition.pbirpoints at — on disk, no connection needed. - The live model via
pbi connect, opened only for fields missing on disk. - A per-visual role default; slicers default to
Column.
Names are canonicalised to the model's casing, and a measure referenced under the wrong table
is rewritten against its home table. A field found in neither place produces a warnings
entry rather than a silent guess — read the warnings. A warning here means the visual will
render empty, and reading it now is cheaper than opening Desktop to find out.
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.
- 16d ago First seen · 197 lines · 0 tokens per session scan A 00cea9ecaa8e
powerbi-pbi-cli is a skill published in the GitHub repository santoshkanthety/powerbi-agent (3 stars, last pushed 17d ago), licensed MIT. It adds 149 tokens to every session and 2,476 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-07.
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.
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…
bi-analyst-knowledge
Use Seshat's public analyst-judgment knowledge to derive decision-questions, choose an analytical framing, and order a story from approved metric contracts and a committed source-profile.