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.
git clone --depth 1 https://github.com/CSalcedoDataBI/powerbi-pbip-toolsWrote 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/commands/csalcedodatabi/powerbi-pbip-tools/dashboard)<a href="https://agentmods.dev/commands/csalcedodatabi/powerbi-pbip-tools/dashboard"><img src="https://agentmods.dev/badge/commands/csalcedodatabi/powerbi-pbip-tools/dashboard/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/commands/csalcedodatabi/powerbi-pbip-tools/dashboard"><img src="https://agentmods.dev/badge/commands/csalcedodatabi/powerbi-pbip-tools/dashboard.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 | $0.00000 | $0.00472 |
| Opus 5.5 | $0.00000 | $0.00189 |
| Sonnet 5.5 | $0.00000 | $0.00094 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
dashboard 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 1mo 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.
What it actually says
/dashboard — Interactive KPI Dashboard Generator
Creates a fully interactive HTML dashboard from any Power BI model connected via MCP.
Output: a standalone .html file with 12 KPI cards, sparklines, and sentiment charts.
Usage
/dashboard
/dashboard sales 2025
/dashboard <describe what you want>
What this command does
- Reads
.claude/skills/dashboard-builder.mdfor full instructions and configuration - Connects to the Power BI Desktop model via MCP
- Queries all required monthly metrics in parallel (DAX)
- Generates a standalone HTML file with:
- 12 KPI metric cards (3-column grid) with embedded sparklines
- 4 sparkline interaction modes (vs. Average · vs. PY Bar · vs. PY Line · vs. PY Only Bar)
- Dashboard page: CY vs PY sentiment line chart (green/red fill)
- Category donut, country bars, annual evolution — all dynamic by metric
- Drill-through: click any KPI card → Dashboard page filtered to that metric
- Year filter: select any year, all charts and KPIs update live
- Saves to
OUTPUT_BASE\dashboards\{topic}_{year}.html
Execution
Read the skill file first, then follow its phases exactly:
Phase 1: Connect to MCP and identify the model
Phase 2: Run all DAX queries in parallel
Phase 3: Fill the HTML template with real data
Phase 4: Run the quality checklist before saving
Critical rules
- Never fabricate numbers — every value must come from a DAX query response
- Always query in parallel — fire all DAX queries in a single message
- Never save inside the git repo — output goes to OUTPUT_BASE only
- Use the template — read
tools/dashboard/template.htmlbefore generating any HTML
Output examples
DASHBOARDS\dashboards\sales_2025.htmlDASHBOARDS\dashboards\contoso_overview_2024.htmlDASHBOARDS\dashboards\kpi_analysis_q1_2025.html
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.
- 1mo ago First seen · 51 lines · 0 tokens per session scan A a2979c822a7d
dashboard is a command published in the GitHub repository CSalcedoDataBI/powerbi-pbip-tools (6 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 472 tokens. 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 commands, from other repositories
migrating-fabric-trial-capacities
Migrate workspaces from trial capacity to production capacity.
sql-developer
Comprehensive SQL Server development assistance for T-SQL queries, stored procedures, performance tuning, and code review with Microsoft documentation verification.
powershell-developer
Comprehensive PowerShell development assistance for scripts, modules, GUIs, and Windows automation with Microsoft best practices verification.
swift-developer
Comprehensive Swift development assistance for iOS/macOS apps, Swift packages, SwiftUI, Swift 6 concurrency, and code review with Apple documentation verification.
rust-developer
Comprehensive Rust development assistance for systems programming, async applications, web services, and CLI tools with Rust documentation verification.
close-studio-pro
Gracefully close Mendix Studio Pro + its children (runtime, MxBuild, Java helpers) and clean up orphan toolchain from a previous crash. Sends WMCLOSE first; reports counts of what was closed. Default project: TestOSApp3 testbed; default port: 8082.