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 mostafa-drz/claude-skills --skill svg-artgit clone --depth 1 https://github.com/mostafa-drz/claude-skillsWrote 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/mostafa-drz/claude-skills/svg-art)<a href="https://agentmods.dev/skills/mostafa-drz/claude-skills/svg-art"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/svg-art/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/mostafa-drz/claude-skills/svg-art"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/svg-art.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00123 | $0.04308 |
| Opus 5.5 | $0.00049 | $0.01723 |
| Sonnet 5.5 | $0.00025 | $0.00862 |
| Haiku 4.5 | $0.00012 | $0.00431 |
Grade A, and why
svg-art 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 1mo 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 — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preferences
On startup, use Read to load ~/.claude/skills/svg-art/preferences.md. If missing, treat as first-run.
Defaults when no preferences exist:
output-root:~/Desktop/svg-art/(confirmed on first run)default-style:line-icon(minimal, consistent stroke)default-count:9(3×3 grid feels complete, not overwhelming)default-stroke:1.5(px, relative to a 24px canvas)canvas:24x24for icons,400x400for compositionspalette-mode:currentColor(monochrome, themeable) — alternates:duotone,brand-palettetone:friendly-cli(matches user's global tone preference)open-gallery:true
Also load ~/.claude/skills/svg-art/feedback-journal.md if present — contains per-session likes/dislikes and extracted aesthetic signals. Summarize the signal (e.g., "prefers asymmetric compositions, negative space over fills, avoids radial symmetry") and let it shape this session's generation.
Context
On startup, use Bash to detect today's date (date +%Y-%m-%d) and whether the output root exists.
Command routing
Check $ARGUMENTS:
help→ show help, stopconfig→ run config flow, stopreset→ delete preferences + feedback journal, confirm, stopfeedback→ rate the most recent set (teaches the skill), stophistory→ list past sessions with titles and dates, stopstyles→ print a quick reference of available style modes, stop- anything else → generate
Help
svg-art — Artistic SVG generation with a 2026 HTML gallery
Usage:
/svg-art [what to generate] Interactive generation
/svg-art [...] --style <mode> Override default style mode
/svg-art [...] --count <N> How many SVGs (default 9)
/svg-art [...] --palette <colors> e.g., "monochrome", "warm-duotone", "#0a2a6b,#e8eefa"
/svg-art [...] --stroke <px> Stroke width in relative px
/svg-art [...] --canvas <WxH> Canvas size, default 24x24 for icons
/svg-art [...] --notes <text> Extra constraints, references, exclusions
/svg-art config Set preferences
/svg-art reset Clear preferences + feedback journal
/svg-art feedback Rate the last set (teaches the skill)
/svg-art history List past sessions
/svg-art styles Reference of style modes
/svg-art help This help
Style modes:
line-icon Minimal outlined icons, consistent stroke, Feather/Lucide lineage
geometric Bauhaus-inspired: circles, squares, triangles, Swiss-design composition
mark Logomarks — single-concept, tightly composed, memorable at small sizes
generative Math-driven: Voronoi, waves, spirals, noise fields, grid deviations
organic Hand-drawn feel: variable stroke, jittered paths, soft imperfection
duotone Two-color compositions with intentional overlap / transparency
animated SMIL or CSS-animated — subtle breathing motion, not full animation
Examples:
/svg-art "9 icons for a gardening app"
/svg-art "generative poster for a music night" --style generative --canvas 800x1200
/svg-art "brand mark for 'Northwind' — compass / wind motif" --style mark --count 4
/svg-art "icon set: finance dashboard" --style line-icon --stroke 1.75
Output:
{output-root}/{YYYY-MM-DD}-{kebab-title}/
├── gallery.html ← 2026 aesthetic single-file preview
├── data.json ← metadata per SVG (concept, style, size, palette)
├── svgs/
│ ├── 01-{name}.svg
│ ├── 02-{name}.svg
│ └── ...
└── sources.md ← design system for the set + any inspiration refs
Current preferences:
(loaded from preferences.md)
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.
- 1mo ago Changed · +3 lines 1477e9a20609
- 1mo ago First seen · 356 lines · 123 tokens per session scan A cff83fa02e79
svg-art is a skill published in the GitHub repository mostafa-drz/claude-skills (4 stars, last pushed 2d ago), licensed MIT. It adds 123 tokens to every session and 4,308 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
architecture-drawer
Use when asked to draw system architecture diagrams, generate technical architecture SVGs, or export architecture diagrams to editable PowerPoint presentations. Supports multi-layer diagrams with automatic layout validation and scoring (16-dimension evaluator catches collisions, overlaps, dangles, crossings, palette…
style-guide-builder
Build a reusable visual style guide from reference images - how the style renders what the references show and what they never show - as markdown files other skills read. Use when the user has reference images or screenshots and wants new images or video to match their look.
caption-decorations
Author and validate scene caption decorations, choosing between measured procedural decoration presets and arbitrary scene artwork. Use when adding caption highlights, boxes, stickers, animated artwork, custom decoration assets, or debugging why a caption decorator is missing or timed incorrectly.
information-architecture
Map the user journey first, then derive the screen inventory, navigation and hierarchy from it, flagging any screen that serves no journey step. Writes the four-part markdown plus an HTML diagram of the step-to-screen mapping. Use after the brief is settled and before tokens or UI.
persona-acid-test
Stress-test a design through three lenses, confused user, skeptical engineer and impatient PM, before it goes to a stakeholder. Requires an actual design, an HTML file, Figma link or screenshot.
design-review
Critique a design on layout, accessibility, responsiveness, dark mode and edge cases, with Pass, Needs work or Fail verdicts. Use on a built screen.