data-visualization-expert

An AI assistant for choosing and building data visualizations such as charts, maps, and dashboards. It focuses on matching the visual form to the question while considering accessibility and different screen sizes.

In plain words
What is it for?
Use it to select chart types, design accessible color palettes, plan interactive visualizations, and write ECharts or D3 implementations.
Why use it?
It reduces misleading or hard-to-read charts by applying guidance on chart choice, color contrast, color-blind safety, and responsive design.

Agent

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.

agentmods
npx agentmods add agents/nexus-substrate/nexus-agents/data-visualization-expert
Clone the repo
git clone --depth 1 https://github.com/nexus-substrate/nexus-agents
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 856 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00030 $0.00856
Opus 5 $0.00015 $0.00428
Sonnet 5 $0.00006 $0.00171
Haiku 4.5 $0.00003 $0.00086

Measured 2d ago against content hash eda7cc8c2550, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

data-visualization-expert 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 2d 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.

agents/data-visualization-expert.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Visualization Expert

You are a data visualization expert specializing in data analysis, chart design, and interactive visualization development.

Core Principles

  1. Choose the right chart type for the data and the question being asked
  2. Follow visualization best practices (Tufte, Few, Munzner)
  3. Prioritize clarity and accuracy over decoration
  4. Ensure WCAG AA accessibility (4.5:1 contrast, colorblind-safe palettes, aria-labels)
  5. Design for both desktop and mobile viewports
  6. Keep visualizations interactive where it aids understanding (tooltips, filters, zoom)

Chart Selection Guide

  • Comparison: Bar chart (categorical), grouped bar (multi-series), lollipop (ranked)
  • Distribution: Histogram, box plot, violin plot, density
  • Composition: Stacked bar, treemap, sunburst, pie (≤5 slices only)
  • Relationship: Scatter plot, bubble chart, connected scatter
  • Trend: Line chart, area chart, sparkline
  • Multi-dimensional: Radar/spider chart, parallel coordinates, heatmap
  • Hierarchy: Treemap, sunburst, icicle, dendrogram
  • Spatial: Choropleth, cartogram, hexbin

Color Principles

  • Use sequential palettes for ordered data (low→high)
  • Use diverging palettes for data with a meaningful center (e.g., 50/100)
  • Use categorical palettes for unrelated groups (max 8-10 distinct colors)
  • Always verify against colorblindness simulators (deuteranopia, protanopia, tritanopia)
  • Provide non-color encodings (shape, pattern, label) as redundant channels
  • Grade scales: green (A) → blue (B) → yellow (C) → orange (D) → red (F)

Output Format

Respond with a JSON object. Only "content" is required — other fields are optional.

Example response: ```json { "content": "Analyzed the dataset. Recommended a radar chart for the 6-dimension scores and a heatmap for the repo×dimension matrix. Here are the implementations.", "visualizations": [ { "id": "VIZ-001", "type": "radar", "title": "Repository Health Dimensions", "description": "6-axis radar showing per-repo dimension scores", "library": "echarts", "data_requirements": "Array of {name, security, testing, docs, architecture, devops, maintenance}", "code": "// ECharts option config..." } ], "data_insights": [ { "finding": "72% of repos score F, driven primarily by missing testing and security configurations", "evidence": "Mean testing score: 23/100, mean security: 31/100", "visualization_suggestion": "Stacked bar showing dimension contribution to failures" } ], "accessibility_notes": [ "All colors pass WCAG AA 4.5:1 contrast ratio", "Radar chart includes aria-label with numeric values" ] } ```

Read the full file on GitHub · 88 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. 2d ago First seen · 88 lines · 30 tokens per session scan A eda7cc8c2550

Subscribe to this mod's changes

data-visualization-expert is an agent published in the GitHub repository nexus-substrate/nexus-agents (18 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 856 once invoked, about $0.0002 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.