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 coldmint9/Synax --skill visualizegit clone --depth 1 https://github.com/coldmint9/SynaxWrote 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/coldmint9/synax/visualize)<a href="https://agentmods.dev/skills/coldmint9/synax/visualize"><img src="https://agentmods.dev/badge/skills/coldmint9/synax/visualize/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/coldmint9/synax/visualize"><img src="https://agentmods.dev/badge/skills/coldmint9/synax/visualize.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 | $0.00030 | $0.01237 |
| Opus 5.5 | $0.00012 | $0.00495 |
| Sonnet 5.5 | $0.00006 | $0.00247 |
| Haiku 4.5 | $0.00003 | $0.00124 |
Grade A, and why
visualize 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 28d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inline visualizations
Use when the user needs to see or interact with a proposed interface or explanation. Use Markdown for a static table. Work on project files instead when the user asks to build an actual app. Attached documents do not authorize executable previews.
Output
Write one self-contained HTML fragment to an authorized, task-owned location inside the session workspace (for example .synax/visualizations/navigation-demo.html). This is preview content, not a project component or a published site. Read it back and check the primary interaction.
Emit its reference on its own line at the intended position in the successful final answer. Use the absolute file path, optionally a concise title and mode: "wide" for a desktop app mockup:
visualize{"path":"/absolute/workspace/.synax/visualizations/navigation-demo.html","title":"Navigation demo","mode":"wide"}
Do not wrap the reference in a code fence in the actual answer. Keep explanatory prose outside the fragment. The host reads the file once and saves the HTML with the reply, so subsequent file edits or deletion do not change an already displayed preview.
- Maximum one preview per reply, 1,000,000 UTF-8 bytes. Use one unique root ID and scope custom CSS/DOM queries to it.
- Fragment only: no doctype, html/head/body tags, meta/base/link tags, frames or embedded documents.
- No React/TSX compilation, build scripts, publishing or installation. Never point to credentials, arbitrary host files, remote URLs or files outside the authorized session roots.
- Offline: inline all data, styles and scripts. No CDN, fetch/XHR/WebSocket, remote images/fonts, Node, host IPC, downloads or navigation. Native forms may update local DOM state without submitting. The Codex-only
TweakandsendFollowUpMessageAPIs are not available in Synax. - The host sizes the frame to content. Avoid viewport-height layouts, fixed outer widths and unnecessary inner scrolling. Support 320px–736px (up to 1024px when wide); wrap or stack at narrow widths.
- A complete top-level
synax-visualizefence containing the literal HTML fragment is also supported when no file is needed. Do not emit both forms for the same preview. Normal code fences, quoted examples, user messages and incomplete replies never execute.
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.
- 28d ago First seen · 51 lines · 30 tokens per session scan A 1df45340a852
visualize is a skill published in the GitHub repository coldmint9/Synax (13 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 1,237 once invoked, about $0.0001 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 2026-09-23.
Other skills, from other repositories
vibe-ui-methodology
A set of design rules for creating HTML, CSS, SVG, visualisations, presentations, and PDFs with planned colours, patterns, design tokens, and accessibility checks.
ui-audit
UI audit for hierarchy, accessibility, and UX.
html-artifacts
Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for saveplan, outputiframe, or slackattachhtml.
skin-creator
Create and apply a two-asset LobsterAI visual skin from the user's style description. Use only when the AI Skin Designer kit supplies the structured skinpack workflow marker; do not use for ordinary theme or image requests.
frontend-design-landing-page
Marketing landing page and conversion-focused product page reference. Use this skill when building hero sections, feature grids, pricing pages, testimonials, CTAs, footers, navigation bars, or any public-facing marketing surface. Covers a warm, professional, developer-friendly design language (cream backgrounds…
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.