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 agentmods add skills/kyegomez/swarms/data-visualizationnpx skills add kyegomez/swarms --skill data-visualizationgit clone --depth 1 https://github.com/kyegomez/swarmsWhat 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 | $0.00023 | $0.00716 |
| Opus 5 | $0.00012 | $0.00358 |
| Sonnet 5 | $0.00005 | $0.00143 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
data-visualization 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 yesterday.
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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Visualization Skill
When creating data visualizations, follow these principles to ensure clear and effective communication:
Core Principles
1. Choose the Right Chart Type
- Line Charts: Trends over time, continuous data
- Bar Charts: Comparing categories, discrete data
- Scatter Plots: Relationships between variables, correlations
- Pie Charts: Parts of a whole (use sparingly, max 5-6 segments)
- Heatmaps: Patterns in large datasets, correlations
- Box Plots: Distribution statistics, outlier detection
2. Design Guidelines
Clarity
- Use clear, descriptive titles and labels
- Include units of measurement
- Add a legend when multiple series are present
- Ensure adequate contrast and readability
Accuracy
- Start y-axis at zero for bar charts (unless good reason)
- Use consistent scales across related charts
- Avoid distorting data through inappropriate scaling
- Label data points when precision matters
Simplicity
- Remove chart junk and unnecessary decorations
- Use color purposefully, not decoratively
- Limit the number of colors (5-7 max)
- Ensure accessibility (colorblind-friendly palettes)
3. Color Best Practices
- Sequential: Use for ordered data (light to dark)
- Diverging: Use for data with a meaningful midpoint
- Categorical: Use for unordered categories
- Highlight: Use accent colors to draw attention
- Test accessibility with colorblind simulators
4. Storytelling with Data
- Lead with the insight, not the data
- Use annotations to highlight key findings
- Arrange charts in logical flow
- Provide context and comparisons
- Include data sources and timestamp
Visualization Workflow
-
Understand the Data
- Explore data structure and distributions
- Identify key variables and relationships
- Determine the message to communicate
-
Select Visualization Type
- Match chart type to data characteristics
- Consider audience and use case
- Plan for interactivity if needed
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.
- yesterday First seen · 99 lines · 23 tokens per session scan A fb84bbe43685
data-visualization is a skill published in the GitHub repository kyegomez/swarms (7,106 stars, last pushed 3d ago), licensed Apache-2.0. It adds 23 tokens to every session and 716 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
file-reference-skill
Example skill demonstrating secure file reference resolution with supporting files.
pdf-extractor
Extract and convert PDF documents using Python scripts.
csv-parser
Parse and analyze CSV files with data validation.
json-parser
Parse and validate JSON data with schema support.
git-helper
Generate git commit messages and help with git workflows.
code-reviewer
Review code for best practices, potential bugs, security vulnerabilities, and performance issues.