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/cosmix/loom/loom-data-visualizationnpx skills add cosmix/loom --skill loom-data-visualizationgit clone --depth 1 https://github.com/cosmix/loomWhat 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 | $0.00040 | $0.02505 |
| Opus 5 | $0.00020 | $0.01252 |
| Sonnet 5 | $0.00008 | $0.00501 |
| Haiku 4.5 | $0.00004 | $0.00250 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 179 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.
- 2d 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 (54 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 2,505 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.
Other skills, from other repositories
realistic-prompt-generation
Generate natural, controlled prompt variants from a target-blind design brief and prompt architecture while preserving approved jobs, acts, journeys, constraints, roles, locales, proximity bands, and evidence language. Use after architecture design and before contamination or semantic QA.
drawio-logical-diagrams
Creates professional logical flow diagrams and logical system architecture diagrams using draw.io XML format (.drawio files). Use when creating: (1) logical flow diagrams showing data/process flow between system components, (2) logical architecture diagrams representing system structure without cloud provider…
aws-drawio-architecture-diagrams
Creates professional AWS architecture diagrams in draw.io XML format (.drawio files) using official AWS Architecture Icons (aws4 library). Use when the user asks for AWS diagrams, VPC layouts, multi-tier architectures, serverless designs, network topology, or draw.io exports involving Lambda, EC2, RDS, or other AWS…
aksel-builder
Expert builder for Aksel, the Nav / @navikt design system — React components, design tokens, layout primitives, theming (light/dark), icons, CSS, the Tailwind preset, version migrations, Figma-to-code. Triggers — Aksel, "using/with aksel", Nav/Navikt, "designsystemet", "design system", @navikt/ds- (e.g.…
aksel-spacing
Lag responsive layouts med Aksel Design System (v8+) - spacing tokens, layout primitives (Box, HStack, VStack, HGrid, Page, Bleed) og ResponsiveProp.
web-design-reviewer
Visuell inspeksjon av nettsider for å identifisere og fikse designproblemer. Trigges av forespørsler som "sjekk designet", "gå gjennom UI-en", "fiks layouten", "finn designfeil". Finner problemer med responsivt design, tilgjengelighet, visuell konsistens og layout, og fikser dem i kildekoden.