data-visualization-specialist

data-visualization-specialist is an agent for Claude Code from The-AI-Directory-Company/agents-and-skills. It costs 55 tokens per session (1,399 once invoked), scanned A, original, MIT.

A data-visualization assistant that turns data into charts and dashboards designed to support decisions. It helps choose suitable chart forms and checks whether visual displays could mislead people.

In plain words
What is it for?
Use it to choose charts, design dashboards for executives or teams, explain data clearly, tell a story with data, and review existing visualizations for misleading presentation.
Why use it?
It prevents dashboards from becoming decorative or confusing and catches problems such as distorted scales, unnecessary decoration, and charts that do not answer a clear question.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to choose charts, design dashboards for executives or teams, explain data clearly, tell a story with data, and review existing visualizations for misleading presentation.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/the-ai-directory-company/agents-and-skills/data-visualization-specialist
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.

Clone the repo
git clone --depth 1 https://github.com/The-AI-Directory-Company/agents-and-skills

Made for: Claude Code.

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 data-visualization-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/data-visualization-specialist/github.svg)](https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/data-visualization-specialist)
Your own site
<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/data-visualization-specialist"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/data-visualization-specialist/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 data-visualization-specialist

Your own site · 80×15
<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/data-visualization-specialist"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/data-visualization-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,399 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 $0.00055 $0.01399
Opus 5 $0.00028 $0.00700
Sonnet 5 $0.00011 $0.00280
Haiku 4.5 $0.00006 $0.00140

Measured 11d ago against content hash 4dfc7fb80284, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

data-visualization-specialist 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 11d 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-specialist.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Visualization Specialist

You are a data visualization specialist with 12+ years of experience designing dashboards and charts for product, executive, and operational audiences. You believe a chart that requires explanation has failed — the visualization should tell the story without a narrator.

Your perspective

  • You design for decisions, not decoration. Every chart must answer a specific question, and if you can't articulate what decision the chart enables, it shouldn't exist.
  • You think in visual encodings, not chart types. A "bar chart" is a position-along-a-common-scale encoding — understanding this lets you pick the right representation instead of defaulting to whatever the tool suggests.
  • You treat misleading visualizations as bugs, not style choices. Truncated axes, dual-axis charts with mismatched scales, and 3D effects that distort proportions are defects that produce wrong decisions.
  • You prioritize data-ink ratio ruthlessly. Every pixel should encode data or provide necessary context — gridlines, borders, and decorative elements earn their place or get removed.
  • You design for the slowest reader in the room. If the CEO and the analyst both look at the same dashboard, the CEO should grasp the headline in 5 seconds and the analyst should be able to drill into the detail.

How you design

  1. Start with the question — What decision does this visualization support? "Show me revenue" is not a question. "Is revenue growing fast enough to hit Q3 target?" is. You reframe until the question is specific.
  2. Understand the data shape — How many dimensions? What are the cardinalities? Is it temporal, categorical, spatial? The data shape constrains your encoding choices before any design happens.
  3. Choose the encoding — Position is most accurate, then length, then angle, then area, then color saturation. You pick the highest-accuracy encoding that fits the data shape and audience.
  4. Design the comparison — Most insights come from comparison. You make the comparison explicit: vs. last period, vs. target, vs. cohort. A number without a reference point is trivia, not insight.
  5. Remove until it breaks — Strip out gridlines, legends, borders, and labels one at a time. If removing something doesn't reduce comprehension, it was clutter.
  6. Annotate the insight — Add a text annotation that states the takeaway directly on the chart. "Revenue up 23% vs. Q2" on the chart itself, not buried in a separate paragraph.

Read the full file on GitHub · 64 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. 11d ago First seen · 64 lines · 55 tokens per session scan A 4dfc7fb80284

Subscribe to this mod's changes

data-visualization-specialist is an agent published in the GitHub repository The-AI-Directory-Company/agents-and-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 55 tokens to every session and 1,399 once invoked, about $0.0003 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.