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 vlinx-io/VelaTerm --skill vartifactgit clone --depth 1 https://github.com/vlinx-io/VelaTermWrote 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/vlinx-io/velaterm/vartifact)<a href="https://agentmods.dev/skills/vlinx-io/velaterm/vartifact"><img src="https://agentmods.dev/badge/skills/vlinx-io/velaterm/vartifact/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/vlinx-io/velaterm/vartifact"><img src="https://agentmods.dev/badge/skills/vlinx-io/velaterm/vartifact.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 | $0.00088 | $0.00549 |
| Opus 5.5 | $0.00035 | $0.00220 |
| Sonnet 5.5 | $0.00018 | $0.00110 |
| Haiku 4.5 | $0.00009 | $0.00055 |
Grade A, and why
vartifact 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 2d 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
vartifact
VelaTerm previews HTML pages as artifacts. A page opened with vopen from this conversation appears in a panel
beside it, reloads whenever the file changes, and keeps each saved version so the user can step back through them.
Errors the page logs show in the panel's console, and the user can send them back to you.
User input:
$ARGUMENTS
Step 1: Decide where the page goes
- Use the path the user named. Otherwise put it next to the code it is about, or in the working directory, with a
short descriptive name such as
clone-dialog.html. - Keep editing the same file across rounds. A new file starts a new history; the same file builds one.
Step 2: Write the page
- One self-contained HTML file: inline
<style>and<script>. Files beside it (./style.css,./app.js, images) also load, if the page really needs them. - The preview starts offline: requests to the internet, including CDNs and web fonts, are blocked unless the user allows the network for that file. Use system fonts and inline everything the page needs.
- Use realistic sample content, not lorem ipsum, and make the layout work at narrow widths: the panel is often half a screen.
Step 3: Open it
vopen <absolute path>
Run it once; later edits reload the preview on their own, so there is no need to run it again.
Step 4: Report back
Say in one or two lines what the page shows and what to look at. Do not paste the HTML into the conversation; the user is looking at the page.
Notes
vopenneeds a VelaTerm-hosted local session. If it reports that it is not inside one, tell the user the preview is only available in VelaTerm and give the file path instead.- If the user reports errors from the preview, fix the page in place.
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.
- 2d ago First seen · 55 lines · 88 tokens per session scan A de949f65c316
vartifact is a skill published in the GitHub repository vlinx-io/VelaTerm (308 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 549 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 2026-10-19.
Other skills, from other repositories
token-map
Map an extracted Figma / source-code token bag onto the active OD design system, producing a deterministic mapping the generate stage can consume.
od-figma-migration
Default reference pipeline for the figma-migration taskKind — figma-extract → token-map → generate → critique.
ui-review-tahoe
Comprehensive UI/UX review for macOS Tahoe apps. Covers Liquid Glass design, HIG compliance, SwiftUI patterns, and accessibility. Use when reviewing macOS UI or checking HIG compliance.
od-nextjs-export
Use this plugin when the user wants to hand an accepted Open Design artifact to a Next.js App Router project.
od-react-export
Use this plugin when the user wants to hand an accepted Open Design artifact to a React app.
od-vue-export
Use this plugin when the user wants to hand an accepted Open Design artifact to a Vue 3 project.