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 tomzx/agents --skill create-svg-imagegit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/create-svg-image)<a href="https://agentmods.dev/skills/tomzx/agents/create-svg-image"><img src="https://agentmods.dev/badge/skills/tomzx/agents/create-svg-image/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/tomzx/agents/create-svg-image"><img src="https://agentmods.dev/badge/skills/tomzx/agents/create-svg-image.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 | $0.01862 |
| Opus 5.5 | $0.00037 | $0.00745 |
| Sonnet 5.5 | $0.00018 | $0.00372 |
| Haiku 4.5 | $0.00009 | $0.00186 |
Grade A, and why
create-svg-image 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 22d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create SVG Image
Produces hand-authored SVG diagrams and visualizations that look intentional at any size and render correctly across browsers and non-browser renderers (resvg, librsvg, chat previews).
The aesthetic rules are in references/svg-style-guide.md; this skill supplies the workflow, the geometry math, and the validation loop.
Prerequisites
- A subject to visualize: a user description, or source material (code, schema, process notes, data).
- The target medium (README, docs page, slide, issue comment, standalone file), since it fixes width, aspect ratio, and renderer limits.
references/svg-style-guide.md, read in step 2.- Optional tools, each with a graceful fallback:
xmllintornpx svglintfor parse checks,rsvg-convertor a browser for render checks.
Steps
1. Gather context
Ask for or infer:
- What the visualization should show, and the one message a viewer should take away.
- The audience, target medium, and approximate display width.
- Any brand palette or sibling diagrams the output must match.
- Whether a dark mode variant is needed (style guide, Dark mode section).
2. Load the style guide and choose the tool
- Read
references/svg-style-guide.mdand adopt its tokens: color table, type scale, stroke ladder, corner radii, spacing grid. - Start from the starter template in the guide and replace its content.
- When the user did not ask for SVG specifically, check whether a Mermaid type covers the need: if yes, prefer
create-mermaid-visualization; hand-author SVG when precise layout, branding, or a non-diagram figure is required.
3. Plan the layout before writing XML
Compute the geometry first; fixing layout after the fact is the main source of ugly SVG.
- Pick display width from content: list 400px, flowchart 600-700px, architecture 700-800px.
- Set
viewBoxto content bounds plus 24px margins, snapped to the 4px grid. - Estimate every label's width as 0.6 × font-size × characters, then size boxes: width = longest label + 32px, height = 3 × font-size for one line plus 1.5 × font-size per extra line.
- Compute baselines: label baseline = box center y + 0.35 × font-size; title baseline = top padding + 0.75 × font-size, centered on the content, not the canvas.
- Route connectors: at least 16px clear of nodes and 8px from each other, orthogonal or curved per the guide, never mixed.
- If any two elements would overlap, move them now, not after rendering.
What ships with it
1 file 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.
- 22d ago Changed · -2 lines aecffdc86c02
- 25d ago Changed 73f3a928e859
- 1mo ago First seen · 131 lines · 92 tokens per session scan A f1dbc342a13e
create-svg-image is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 1,862 once invoked, about $0.0004 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 2026-09-15.
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.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
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.