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 cosmix/loom --skill loom-data-visualizationgit clone --depth 1 https://github.com/cosmix/loomWrote 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/cosmix/loom/loom-data-visualization)<a href="https://agentmods.dev/skills/cosmix/loom/loom-data-visualization"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-data-visualization/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/cosmix/loom/loom-data-visualization"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-data-visualization.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 | $0.00029 | $0.02487 |
| Opus 5.5 | $0.00012 | $0.00995 |
| Sonnet 5.5 | $0.00006 | $0.00497 |
| Haiku 4.5 | $0.00003 | $0.00249 |
Grade A, and why
loom-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 27d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Visualization
Overview
Match the chart to the data relationship, encode quantities in perceptually accurate channels, avoid distortion, and make it accessible. This skill is the design layer above the plotting library.
Chart selection by data relationship
| Goal | Prefer | Avoid |
|---|---|---|
| Compare across categories | horizontal bar (sorted), dot plot | pie with >~5 slices |
| Part-to-whole | stacked bar, treemap; pie only ≤5 slices | many pies / donuts for precise comparison |
| Distribution | histogram, box, violin, ECDF | bar of means (hides spread) |
| Two-variable relationship | scatter (+ trend), 2D density/hexbin when dense | scatter with 100k overplotted points |
| Correlation matrix | heatmap (diverging scale) | 3D surface |
| Trend over time | line; area for cumulative | connecting unordered categories with lines |
| Ranking | ordered bar / lollipop | pie |
| Performance vs target | bullet chart | gauge cluster |
| Geographic | choropleth (normalized), point/flow map | raw-count choropleth (just shows population) |
Perceptual accuracy (why bars beat pies)
Cleveland–McGill ranking of how accurately humans decode a quantity:
position on common scale > position on non-aligned scale > length > angle/slope > area > volume > color hue/saturation.
- Encode the most important quantity in position/length (bar, dot, line), not area or color.
- Pie/donut = angle+area (weak); bubble = area (people underestimate large circles — area scales as r², so double the value ≠ double the radius). Reserve area/color for secondary dimensions.
- Sort categorical bars by value (not alphabetically) unless order is semantic — sorting is the insight.
Avoiding distortion (the "lie factor")
- Truncated y-axis exaggerates change. Bar charts must start at 0 (bar length encodes the value). Line/time-series may zoom the axis to show variation — but label it clearly; don't imply a 2% change is a cliff.
- Dual y-axes manufacture spurious correlation and let you slide two series' scales arbitrarily. Replace with indexed series (all = 100 at t0), two small multiples, or a ratio.
- Aim for lie factor ≈ 1 (graphic effect size / data effect size). Don't use 3D, shadows, or area to represent 1D quantities.
- Chartjunk: maximize data-ink ratio (Tufte) — drop gridline clutter, heavy borders, redundant legends, background gradients. Direct-label lines instead of a legend when few series.
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.
- 27d ago Changed · -2 lines · +5 tokens per session eda17652f2e8
- 1mo ago Changed · -16 tokens per session a2f8e7be28e7
- 1mo ago First seen · 179 lines · 40 tokens per session scan A 211d82690947
loom-data-visualization is a skill published in the GitHub repository cosmix/loom (62 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 2,487 once invoked, about $0.0001 per session on Opus 5.5. 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
idiomatic-go
Apply Go community idioms for API and package design, error and concurrency patterns, naming (initialisms, stutter, receivers), generics vs interfaces, and Go code review — including PR or diff review, questions about "the Go way", pointer vs value receivers, channels vs mutexes, and building Go language tooling…
eclipse-license-check
Vet third-party dependencies for an Eclipse Foundation project with the Eclipse Dash License Tool — license checks, "do I need to vet X?" questions, IPLab review filing, and release IP due diligence. Use whenever the user mentions Eclipse license checking, dash-licenses, the Dash License Tool, IPLab, third-party…
go-documentation
Write idiomatic Go doc comments that render correctly on pkg.go.dev — package comments, doc.go, exported-symbol comments, testable Example functions, deprecation notices — and publish or debug modules on pkg.go.dev (pkgsite, the module proxy). Use when writing or reviewing Go documentation, or when a developer used to…
publish-vscode-extension
Publish a VS Code extension to the VS Code Marketplace and/or Open VSX Registry. Use when the user wants to publish, ship, or release a VS Code extension; audit or improve manifest, listing, or release setup; build or upload a .vsix; set up vsce or ovsx; create a marketplace publisher or Open VSX namespace; configure…
domainmodel-dsl
Read, write, and modify Domain Model DSL files (.dmodel) — datatypes, entities with inheritance and multi-valued features, and nested packages with qualified cross-references. Use when the user wants to create, edit, explain, or debug a domain model in this DSL, including resolving references across packages.
statemachine-dsl
Read, write, and modify Statemachine DSL files (.statemachine). Use when the user wants to create, edit, explain, or debug a state machine written in this textual DSL — defining states, events, commands, and transitions, or generating a machine from a description.