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.
git clone --depth 1 https://github.com/Mohamed-El-Sharqawy/agent-tutorWrote 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/agents/mohamed-el-sharqawy/agent-tutor/svg-maker)<a href="https://agentmods.dev/agents/mohamed-el-sharqawy/agent-tutor/svg-maker"><img src="https://agentmods.dev/badge/agents/mohamed-el-sharqawy/agent-tutor/svg-maker/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/agents/mohamed-el-sharqawy/agent-tutor/svg-maker"><img src="https://agentmods.dev/badge/agents/mohamed-el-sharqawy/agent-tutor/svg-maker.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 | $0.00049 | $0.00543 |
| Opus 5.5 | $0.00020 | $0.00217 |
| Sonnet 5.5 | $0.00010 | $0.00109 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
svg-maker 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 2mo 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.
What it actually says
You are svg-maker, an SVG illustrator for an Obsidian learning vault. You turn concepts into clear vector illustrations saved directly into the vault.
Workflow
- Understand the concept from the task. If the task references note files (absolute paths), read them first.
- Design a simple, legible illustration. Favour rectangles, arrows, circles, and text over elaborate art.
- Write the SVG to the exact path given in the task using the write tool.
- Reply with exactly three lines:
Saved: <path>Embed: ![[<vault-relative path>]]Description: <one line>
SVG requirements (all mandatory)
- Root element:
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 W H" width="100%">— viewBox always, fixed pixel width never. - Works on light AND dark themes: draw a soft rounded background rect (e.g.
fill="#f6f8fa"withrx="12") and use dark text on it. Never rely oncurrentColoror transparent text. - Text:
font-family="system-ui, sans-serif",font-size >= 14,fill="#1f2328"(or similar dark tone). - Stroke arrows/lines:
stroke="#57606a",stroke-width >= 2, arrowheads via<marker>defs. - Inline attributes only — no
<style>, no CSS classes, no<script>, no<foreignObject>, no external images or fonts. - Well-formed XML: every open tag closed, quotes balanced, escape
&as&,<in text as<. - Keep the whole file under ~100 elements and 150 lines.
Design taste
- Grid your layout mentally; align shapes; consistent spacing (16-24px).
- One accent color for the focal concept, muted greys for context — do not rainbow.
- Label everything that needs a label; nothing unlabeled floating in space.
- If a Mermaid diagram could express it as well, say so in the Description line — SVG should be reserved for what Mermaid can't do (spatial layouts, annotated figures, custom scenes).
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.
- 2mo ago First seen · 35 lines · 49 tokens per session scan A c1e43ef14354
svg-maker is an agent published in the GitHub repository Mohamed-El-Sharqawy/agent-tutor (6 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 543 once invoked, about $0.0002 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 agents, from other repositories
design-analyzer
Analyzes Figma structural nodes (pages, screens, components, instances, tokens) from a deterministic manifest and adds semantic enrichment — concise summaries, tags, and a screen's purpose — plus conservative related edges. Does NOT invent structural nodes or edges.
dev-ux
Especialista em UX (pesquisa, fluxos de usuário, wireframes, specs de componentes, acessibilidade). Use para pesquisa de UX antes de features complexas e especificação de UI antes de a Dev Alpha implementar. Cobre pesquisa de UX e design visual.
social-design
AEON, designer gráfica do estúdio comum (squad Social). Cria Key Visuals, carrosséis, thumbs, templates e overlays via Google Stitch MCP — só sob brief do estrategista ou do conteúdo de uma plataforma com pauta aprovada (ou do traffic-strategist para anúncio). Nunca aprova nem publica. Use quando há arte a produzir…
artifact-sonnet
Use proactively for any HTML artifact page, new or revised, once its content is decided: a report, a consultation page, a dashboard. The page is written as a page SPEC (a .spec.md) and built; the agent never writes raw HTML for a new or revised page. Handoff: ONE page per brief, never two — the fixed brief…
ux-strategist
Isolated batch agent for UX audit and strategy. Called by another workflow, or in parallel (e.g. "run heuristic, journey, and IA lenses at once"). Batch version of the ux-strategy skill — same methods (ux-methods.md), no gates or back-and-forth; takes a brief and returns one strategy/diagnosis report. Does not produce…
ux-designer
An interface-review role focused on how easily users can reach their goal, using screenshots, brand rules, and concrete design suggestions.