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 owenmorgan/claude-skills --skill png2svggit clone --depth 1 https://github.com/owenmorgan/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/owenmorgan/claude-skills/png2svg)<a href="https://agentmods.dev/skills/owenmorgan/claude-skills/png2svg"><img src="https://agentmods.dev/badge/skills/owenmorgan/claude-skills/png2svg/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/owenmorgan/claude-skills/png2svg"><img src="https://agentmods.dev/badge/skills/owenmorgan/claude-skills/png2svg.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 | $0.00053 | $0.00891 |
| Opus 5 | $0.00026 | $0.00445 |
| Sonnet 5 | $0.00011 | $0.00178 |
| Haiku 4.5 | $0.00005 | $0.00089 |
Grade A, and why
png2svg 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
png2svg — Raster to SVG Conversion
Convert raster images (PNG, JPEG, BMP, TIFF, WebP) to high-fidelity SVG.
Auto-detects the best tracing engine:
- potrace for monochrome images (logos, icons, line art) — smooth bezier curves, tiny files
- vtracer for full-colour images (illustrations, photos) — preserves colour layers
Setup check
Before first use, verify dependencies are installed:
python3 -c "from PIL import Image; import numpy; print('ok')" && python3 -c "import vtracer; print('vtracer ok')" && potrace --version
If anything is missing:
pip install Pillow numpy vtracer && brew install potrace
Script location
The conversion script is at ${CLAUDE_SKILL_DIR}/scripts/png2svg.py.
Workflow
-
Identify the image(s) — confirm the file path(s) with the user. If they mention a directory, use Glob to find image files (
**/*.png,**/*.jpg). -
Determine output location — default is alongside the input file with
.svgextension. Ask if unclear. -
Run the conversion:
python3 "${CLAUDE_SKILL_DIR}/scripts/png2svg.py" <input> [options]
- Report the result — show the engine used, file sizes, and output path.
Options
| Flag | Description | Default |
|---|---|---|
-o, --output |
Output file or directory | Same dir as input |
-e, --engine |
auto, potrace, or vtracer |
auto |
-p, --preset |
vtracer quality: max, high, fast |
max |
-c, --colour |
Fill colour for potrace (hex) | Auto-detected |
--alphamax |
Corner smoothness: 0=sharp, 1.334=smooth | 1.0 |
--opttolerance |
Curve precision: lower=more precise | 0.1 |
--turdsize |
Speckle suppression threshold (px) | 2 |
Examples
# Auto-detect engine
python3 "${CLAUDE_SKILL_DIR}/scripts/png2svg.py" logo.png
# Force potrace with custom colour
python3 "${CLAUDE_SKILL_DIR}/scripts/png2svg.py" logo.png -e potrace -c '#1a1a1a'
# Batch convert
python3 "${CLAUDE_SKILL_DIR}/scripts/png2svg.py" /path/to/*.png -o /path/to/svgs/
# Sharper corners on a logo
python3 "${CLAUDE_SKILL_DIR}/scripts/png2svg.py" icon.png --alphamax 0.5
# Force vtracer for a colour illustration
python3 "${CLAUDE_SKILL_DIR}/scripts/png2svg.py" artwork.png -e vtracer -p max
What ships with it
2 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 · 90 lines · 53 tokens per session scan A 7c3ee77705d8
png2svg is a skill published in the GitHub repository owenmorgan/claude-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 53 tokens to every session and 891 once invoked, about $0.0003 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.