powerbi-source-integration

powerbi-source-integration is a skill for Claude Code, Codex from santoshkanthety/powerbi-agent. It costs 96 tokens per session (2,626 once invoked), scanned A, original, MIT.

A guide for connecting business data sources to Microsoft Fabric, a platform for storing and analyzing company data. It covers databases, APIs, CSV files, web scrapes, and other sources, then prepares the data for querying.

In plain words
What is it for?
Use it to plan connections to PostgreSQL and other databases, APIs, files, and web sources; choose full or incremental loading; and develop source-to-data-model pipelines.
Why use it?
It provides patterns for moving data from different systems into a consistent raw data layer. This reduces guesswork around connections, loading methods, source mapping, and normalization.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to plan connections to PostgreSQL and other databases, APIs, files, and web sources; choose full or incremental loading; and develop source-to-data-model pipelines.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/santoshkanthety/powerbi-agent/powerbi-source-integration
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.

Any agent
npx skills add santoshkanthety/powerbi-agent --skill powerbi-source-integration
Clone the repo
git clone --depth 1 https://github.com/santoshkanthety/powerbi-agent

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for powerbi-source-integration

README.md
[![agentmods](https://agentmods.dev/badge/skills/santoshkanthety/powerbi-agent/powerbi-source-integration/github.svg)](https://agentmods.dev/skills/santoshkanthety/powerbi-agent/powerbi-source-integration)
Your own site
<a href="https://agentmods.dev/skills/santoshkanthety/powerbi-agent/powerbi-source-integration"><img src="https://agentmods.dev/badge/skills/santoshkanthety/powerbi-agent/powerbi-source-integration/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.

agentmods 80×15 button for powerbi-source-integration

Your own site · 80×15
<a href="https://agentmods.dev/skills/santoshkanthety/powerbi-agent/powerbi-source-integration"><img src="https://agentmods.dev/badge/skills/santoshkanthety/powerbi-agent/powerbi-source-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,626 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00096 $0.02626
Opus 5 $0.00048 $0.01313
Sonnet 5 $0.00019 $0.00525
Haiku 4.5 $0.00010 $0.00263

Measured 10d ago against content hash d79c6b203e89, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

powerbi-source-integration 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.

skills/powerbi-source-integration/SKILL.md · 306 lines

How it starts

The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Source Integration & Data Model Development

Trigger

Activate when the user mentions: data source, connect source, ingest data, database connection, API connection, CSV upload, web scrape, source connector, raw data model, normalize, Bronze ingestion, source mapping, data model development, source to Bronze, multi-source, PostgreSQL, postgres, JDBC, RDS, Aurora, Azure Database for PostgreSQL, Cloud SQL, read replica, DirectQuery postgres, incremental refresh postgres

What You Know

You have integrated 50+ source systems into enterprise data platforms — from SAP ERP to Salesforce CRM, REST APIs to flat file drops, web scrapes to real-time streams. You know the full journey from "we have data in X" to "it's landed, clean, and queryable in OneLake."

Source Type Patterns

Database Sources

# Supported: SQL Server, PostgreSQL, MySQL, Oracle, Snowflake, SQLite
# Connection: JDBC or pyodbc
# Key settings:
#   - Load strategy: full_load | incremental | cdc
#   - Watermark column: the "modified_date" equivalent
#   - Schema + table list (or empty for all tables)

# Best practices:
# - Prefer incremental over full_load for tables > 100K rows
# - Use Key Vault for credentials, never hardcode
# - Test connection before scheduling pipeline

PostgreSQL

PostgreSQL is fully supported across all Power BI / Fabric integration paths. Choose the right approach based on data volume and latency requirements.

Connection Modes — Decision Guide

Scenario Recommended Mode
Small tables (<1M rows), low latency DirectQuery
Large tables (>1M rows), fast dashboards Import (scheduled refresh)
Fabric Lakehouse as intermediary Copy Activity (Fabric Pipeline) → OneLake → DirectLake
Real-time streaming data Eventstream → Lakehouse → DirectLake

Power BI Desktop — Direct Connection

Get Data → Database → PostgreSQL Database
  Server:   db.example.com          (or db.example.com:5432)
  Database: prod_db
  Data Connectivity mode:
    • Import     — loads data into model (recommended for most cases)
    • DirectQuery — live queries to PostgreSQL (use only for <10M rows and fast server)

Read the full file on GitHub · 306 lines

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. 10d ago First seen · 306 lines · 0 tokens per session scan A d79c6b203e89

Subscribe to this mod's changes

powerbi-source-integration is a skill published in the GitHub repository santoshkanthety/powerbi-agent (2 stars, last pushed 11d ago), licensed MIT. It adds 96 tokens to every session and 2,626 once invoked, about $0.0005 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.