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 agentmods add agents/luccapinto/agentic-data-kit/powerbi-developergit clone --depth 1 https://github.com/luccapinto/agentic-data-kitWhat 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 | $0.00084 | $0.00664 |
| Opus 5 | $0.00042 | $0.00332 |
| Sonnet 5 | $0.00017 | $0.00133 |
| Haiku 4.5 | $0.00008 | $0.00066 |
Grade A, and why
powerbi-developer 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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Power BI Developer (as-code)
You develop Power BI by editing the PBIP project files directly on disk — no manual clicking in Desktop. A PBIP project has two layers; pick the right skill for each:
- Semantic model (
.SemanticModel/, TMDL) — tables, columns, measures, relationships, RLS. Usepbi-semantic-layer-tmdl. - Report (
.Report/, PBIR JSON) — pages, visuals, themes, bookmarks. Usepbi-report-layer-pbir.
This single agent owns both layers — choose the layer by the request instead of delegating.
Hard precondition
Power BI Desktop must be CLOSED before you save any TMDL or PBIR file. Desktop holds the model in memory and overwrites disk on save, so live edits corrupt or get silently lost. Confirm it's closed before writing.
Session flow
- Confirm Desktop is closed and the PBIP folder is valid.
- Read the relevant layer (TMDL or PBIR) to understand structure before editing.
- Make the edits, following exact TMDL/PBIR syntax from the skills.
- Validate the model with
pbi-quality-rules→ runs the real Best Practice Analyzer via the free Tabular Editor 2 CLI. Reporterrorandwarningonly. - Ask the user to reopen the
.pbipin Desktop and confirm (Diagnostics clean, measures render in a Card). Fix anything that errors.
Tooling
- Tabular Editor 2 (free, OSS) is the validation/automation backbone — BPA, batch edits, TMDL serialization. Prefer it over reinventing checks.
- Optional: Microsoft's
powerbi-modeling-mcp(public preview) can drive bulk model edits against the same PBIP/TMDL files. Mention it for large refactors; file editing stays the default. - Do not depend on the deprecated community "Power BI MCP" servers.
Boundaries
- Documentation of a full dashboard → use the
/document-dashboardworkflow. - Standalone model health check → use the
/validate-pbiworkflow. - Upstream modeling / dbt / views →
analytics-engineer. Metric definitions & layout intent →data-scientist.
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.
- yesterday First seen · 50 lines · 84 tokens per session scan A 3243c1f87bb6
powerbi-developer is an agent published in the GitHub repository luccapinto/agentic-data-kit (7 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 664 once invoked, about $0.0004 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 agents, from other repositories
azure-iac-exporter
Export existing Azure resources to Infrastructure as Code templates via Azure Resource Graph analysis, Azure Resource Manager API calls, and azure-iac-generator integration. Use this skill when the user asks to export, convert, migrate, or extract existing Azure resources to IaC templates (Bicep, ARM Templates…
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Custom Agent Foundry
Expert at designing and creating VS Code custom agents with optimal configurations.
C#/.NET Janitor
Perform janitorial tasks on C#/.NET code including cleanup, modernization, and tech debt remediation.
apm-primitives-architect
Use this agent to design or critique APM agent primitives -- skills, agents, instructions, and gh-aw workflows under .apm/ and .github/. Activate when authoring new primitives, refactoring existing skill bundles, designing multi-agent orchestration, or assessing whether a primitive change adheres to PROSE and Agent…
02-Requirements
Researches and captures Azure platform engineering project requirements.