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 MarcSkovMadsen/holoviz-mcp --skill holoviewsgit clone --depth 1 https://github.com/MarcSkovMadsen/holoviz-mcpWrote 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/marcskovmadsen/holoviz-mcp/holoviews)<a href="https://agentmods.dev/skills/marcskovmadsen/holoviz-mcp/holoviews"><img src="https://agentmods.dev/badge/skills/marcskovmadsen/holoviz-mcp/holoviews/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/marcskovmadsen/holoviz-mcp/holoviews"><img src="https://agentmods.dev/badge/skills/marcskovmadsen/holoviz-mcp/holoviews.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00026 | $0.04755 |
| Opus 5 | $0.00013 | $0.02377 |
| Sonnet 5 | $0.00005 | $0.00951 |
| Haiku 4.5 | $0.00003 | $0.00475 |
Grade A, and why
holoviews 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 12d 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 — 558 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HoloViews Development Skills
This document provides best practices for developing plots and charts with HoloViz HoloViews in notebooks and .py files.
Please develop as an Expert Python Developer developing advanced data-driven, analytics and testable data visualisations, dashboards and applications would do. Keep the code short, concise, documented, testable and professional.
Dependencies
Core dependencies provided with the holoviews Python package:
- holoviews: Declarative data visualization library with composable elements. Best for: complex multi-layered plots, advanced interactivity (linked brushing, selection), when you need fine control over plot composition, scientific visualizations. More powerful but steeper learning curve than hvPlot. hvPlot is built upon holoviews.
- colorcet: Perceptually uniform colormaps
- panel: Provides widgets and layouts enabling tool, dashboard and data app development.
- param: A declarative approach to creating classes with typed, validated, and documented parameters. Fundamental to the reactive programming model of hvPlot and the rest of the HoloViz ecosystem.
- pandas: Industry-standard DataFrame library for tabular data. Best for: data cleaning, transformation, time series analysis, datasets that fit in memory. The default choice for most data work.
Optional dependencies from the HoloViz Ecosystem:
- hvplot: Easy to use plotting library with Pandas
.plotlike API. Built on top of HoloViews. - datashader: Renders large datasets (millions+ points) into images for visualization. Best for: big data visualization, geospatial datasets, scatter plots with millions of points, heatmaps of dense data. Requires hvPlot or HoloViews as frontend.
- geoviews: Geographic data visualization with map projections and tile sources. Best for: geographic/geospatial plots, map-based dashboards, when you need coordinate systems and projections. Built on HoloViews, works seamlessly with hvPlot.
- holoviz-mcp: Model Context Protocol server for HoloViz ecosystem. Provides access to detailed documentation, component search and agent skills.
- hvsampledata: Shared datasets for the HoloViz projects.
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.
- 12d ago First seen · 558 lines · 26 tokens per session scan A 8286076d5b4c
holoviews is a skill published in the GitHub repository MarcSkovMadsen/holoviz-mcp (34 stars, last pushed 10d ago), licensed BSD-3-Clause. It adds 26 tokens to every session and 4,755 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
dataviz-mcp
Show Python visualizations live in the browser with the dataviz-mcp MCP tools (show, screenshot). Use when those tools are available and the user asks to display, plot, chart, or visualize anything. Do not use for apps the user serves themselves with panel serve.
arrowspace
Spectral vector search using graph Laplacian eigenstructure. Use when cosine/L2 similarity misses latent structure in your embeddings.
data-report
Turns CSV, Excel, or JSON data into a polished visual report page.
docetl
Build and run LLM-powered data processing pipelines with DocETL. Use when users say "docetl", want to analyze unstructured data, process documents, extract information, or run ETL tasks on text. Helps with data collection, pipeline creation, execution, and optimization.
build-with-tinybase
Scaffold, extend, and verify reactive local-first JavaScript or TypeScript applications with TinyBase. Use when choosing TinyBase for in-memory tabular or key-value state, generating an app with create-tinybase, adding schemas or UI bindings, configuring browser or database persistence, configuring MergeableStore…
portaljs-add-chart
Add a chart (line, bar, area, pie, or scatter) to a dataset's showcase in a PortalJS portal. Installs recharts, writes a reusable Chart component, and renders it in the showcase Views section. Use when visualizing a dataset already registered in datasets.json.