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 muxia0396/svg-icon-skills --skill png-to-svggit clone --depth 1 https://github.com/muxia0396/svg-icon-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/muxia0396/svg-icon-skills/png-to-svg)<a href="https://agentmods.dev/skills/muxia0396/svg-icon-skills/png-to-svg"><img src="https://agentmods.dev/badge/skills/muxia0396/svg-icon-skills/png-to-svg/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/muxia0396/svg-icon-skills/png-to-svg"><img src="https://agentmods.dev/badge/skills/muxia0396/svg-icon-skills/png-to-svg.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 | $0.00092 | $0.01047 |
| Opus 5 | $0.00046 | $0.00524 |
| Sonnet 5 | $0.00018 | $0.00209 |
| Haiku 4.5 | $0.00009 | $0.00105 |
Grade A, and why
png-to-svg 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 12d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PNG to SVG
Reconstruct the visible foreground as deliberate vector geometry. Treat the raster as evidence, not as content to wrap inside an SVG.
Resolve <skill-dir> to the directory containing this file. Resolve all bundled paths from it.
Hard requirements
- Produce real SVG primitives and paths. Never use
<image>, raster data URLs,foreignObject, CSS background images, or external asset references. - Leave the SVG canvas transparent and exclude every source-background pixel.
- Preserve the requested lockup, spacing, alignment, palette, negative space, and optical weight.
- Prefer the fewest clean primitives and Bézier points that explain the raster. Do not ship a noisy automatic trace.
- Do not search for an original SVG or substitute an icon-library asset. Reconstruct only from the supplied raster and user facts.
- State genuine ambiguity instead of inventing hidden geometry.
Workflow
1. Inspect the source
View the original at native size and zoomed in. Record:
- canvas dimensions, alpha channel, and likely background;
- foreground bounds and intended whitespace;
- dominant colors and antialiasing fringe;
- symmetry axes, repeated widths, radii, angles, and negative spaces;
- whether the form is best explained by strokes, fills, or both;
- whether several visible parts form one lockup or separate assets.
For an opaque source, explicitly identify and remove the background. For a textured or ambiguous background, separate the intended foreground semantically and inspect every edge.
2. Form a geometry model
Read references/geometry-and-qa.md. Start with the lowest adequate complexity:
- circles, ellipses, lines, polylines, rectangles, rounded rectangles, and arcs;
- small primitive composites and negative-space cutouts;
- a few deliberate cubic curves with tangent continuity;
- a simplified custom outline only for a genuinely irregular silhouette.
For line icons, test a centerline-stroke model before drawing both edges as an outline. Infer a shared stroke width, caps, joins, and corner language. For filled icons, reconstruct the silhouette and open interior holes rather than painting them with the source background color.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 99 lines · 92 tokens per session scan A 76aeca362977
png-to-svg is a skill published in the GitHub repository muxia0396/svg-icon-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 1,047 once invoked, about $0.0005 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.
Other skills, from other repositories
thesvg
Fetch brand SVG logos and cloud architecture icons (AWS, Azure, GCP) from theSVG. Use when the user asks for a brand logo, company icon, framework mark, service icon, or any "icon/logo for X" where X is a real brand or cloud service. Returns ready-to-use CDN URLs or raw SVG markup.
wireframe
Produce low-fidelity black-and-white UI wireframes as SVGs or viewer pages. Use when asked to wireframe, sketch a screen, draft a layout, make a low-fi mockup, or publish wireframes.
fireworks-tech-graph
Create technical diagrams such as software architecture, data flow, flowcharts, sequence diagrams, C4 reviews, cloud deployments, event streams, observability investigations, agent/memory systems, UML, ER, network topology, timelines, and technical concept maps, then export SVG, PNG, focused semantic SVG-to-GIF…
data-viz-renderer
Generate self-contained HTML/SVG infographics from JSON data, including stat cards, bar charts, flow diagrams, and mixed dashboards. Offers 8 color palettes and built-in icons with no external dependencies. Triggered when users request data visualization, infographics, charts, or dashboards.
ip-as-logo
Generate extremely simple, cute, personified square character images with rounded heavy forms, two purposeful character colors, one solid background color, and a dominant lower-corner composition. Use when creating an animal, creature, robot, ghost, plant, object, or other character image, including when the agent…
add-icon-mapping
Add or modify icon keyword mappings for providers, models, or agents in lobe-icons. Use this whenever a task involves mapping a provider/model id to an icon, adding a new entry to ModelProvider enum or providerMappings/modelMappings/agentMappings, or fixing a provider/model that renders the fallback (default) icon in…