OpenScreen is a desktop screen-recording application that turns captured windows or screens, along with audio and optional webcam footage, into product demos and walkthroughs. It is for people creating demonstrations for social networks, video platforms, documentation, or landing pages.
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 getopenscreen/openscreen --skill designgit clone --depth 1 https://github.com/getopenscreen/openscreenWrote 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/getopenscreen/openscreen/design)<a href="https://agentmods.dev/skills/getopenscreen/openscreen/design"><img src="https://agentmods.dev/badge/skills/getopenscreen/openscreen/design/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/getopenscreen/openscreen/design"><img src="https://agentmods.dev/badge/skills/getopenscreen/openscreen/design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00062 | $0.00451 |
| Opus 5.5 | $0.00025 | $0.00180 |
| Sonnet 5.5 | $0.00012 | $0.00090 |
| Haiku 4.5 | $0.00006 | $0.00045 |
Grade A, and why
openscreen-design 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 18d 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
Read the README.md file within this skill, and explore the other available files. If creating visual artifacts (slides, mocks, throwaway prototypes, etc), copy assets out and create static HTML files for the user to view. If working on production code, you can copy assets and read the rules here to become an expert in designing with this brand. If the user invokes this skill without any other guidance, ask them what they want to build or design, ask some questions, and act as an expert designer who outputs HTML artifacts or production code, depending on the need.
Quick orientation:
styles.cssis the single CSS entry point — link it and use the CSS custom properties (never hard-code hex). Dark is the default; adddata-theme="light"on a wrapper for the light palette.- Type: Geist (UI) + Geist Mono (numbers/technical). Base 13px.
- One brand hue: emerald
--accent. Ration it. Timeline lanes add amber/orange/red semantic accents. - Components live in
components/(forms, display, editor); full-screen recreations inui_kits/editor/. Icons are Lucide. - No emoji, no gradients-as-decoration, no photographic backgrounds. Dense pro-tool density, glassy floating panels, hairline borders.
- Editor controls (full rules: "EDITOR CONTROLS" in readme.md): a fixed choice is a one-click
ChoiceRow, not a select; named levels instead of meaningless numbers; settings are free rows under sentence-case section labels, never cards; no hint text, and an option that does nothing is hidden, not disabled. - Timeline is "candy": the clip is the brand green, zooms blue, every lane solid with dark ink
#0b1220; playhead violet; no seek bar.
What ships with it
60 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.
- _ds_manifest.json 20 KB
- assets/logo-icon.png 10 KB
- components/display/Badge.jsx 1.5 KB
- components/display/Card.jsx 1.3 KB
- components/display/Chip.jsx 1.1 KB
- components/display/display.card.html 2.9 KB
- components/display/ProgressBar.jsx 751 B
- components/editor/ChatBubble.jsx 2.7 KB
- components/editor/editor.card.html 4.9 KB
- components/editor/FacetRailButton.jsx 951 B
- components/editor/MediaCard.jsx 2.6 KB
- components/editor/ProposalCard.jsx 3.6 KB
- components/editor/TimelinePill.jsx 1.8 KB
- components/forms/Button.jsx 2.2 KB
- components/forms/ChoiceRow.jsx 3.2 KB
- components/forms/forms.card.html 4.6 KB
- components/forms/IconButton.jsx 1.5 KB
- components/forms/SegmentedControl.jsx 1.8 KB
- components/forms/Select.jsx 1.1 KB
- components/forms/Slider.jsx 1.8 KB
- components/forms/Switch.jsx 1.3 KB
- components/forms/TextField.jsx 1.5 KB
- cursors/3d-concept.png 822 KB
- cursors/3d-direction.md 5.8 KB
- cursors/contact-sheet.png 206 KB
- cursors/dark-32px.png 35 KB
- cursors/glass-lens/renders.png 364 KB
- cursors/pixel-candy/source.png 15 KB
- cursors/pop-coral/source.png 1409 KB
- cursors/prism-glow/model/build_blend.py 11 KB runs code
- cursors/prism-glow/model/export_compositor.py 16 KB runs code
- cursors/prism-glow/model/prism_geo.py 6.7 KB runs code
- cursors/prism-glow/model/prism-glow.blend 201 KB
- cursors/prism-glow/model/prism-glow.glb 75 KB
- cursors/prism-glow/model/prism.json 8.1 KB
- cursors/prism-glow/source.png 981 KB
- cursors/README.md 2.5 KB
- cursors/requirements.md 4.4 KB
- cursors/star-sprout/3d-reference.png 390 KB
- cursors/star-sprout/source.png 580 KB
- cursors/studio-ink/source.png 1224 KB
- DESIGN.md 6.7 KB
- guidelines/brand-elevation.card.html 1008 B
- guidelines/brand-logo.card.html 1.0 KB
- guidelines/brand-motion.card.html 1.3 KB
- guidelines/brand-radii.card.html 1.5 KB
- guidelines/colors-brand.card.html 1.7 KB
- guidelines/colors-semantic.card.html 1.8 KB
- guidelines/colors-surfaces.card.html 1.8 KB
- guidelines/colors-text.card.html 1.2 KB
- guidelines/spacing-scale.card.html 1.5 KB
- guidelines/type-families.card.html 975 B
- guidelines/type-reading.card.html 936 B
- guidelines/type-scale.card.html 1.5 KB
- openscreen-editor-v2.html 2097 KB
- openscreen-editor.html 217 KB
- openscreen-widget.html 274 KB
- readme.md 12 KB
- styles.css 1.1 KB
- tokens/base.css 2.7 KB
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.
- 18d ago Changed · +2 lines 27e23140326a
- 1mo ago First seen · 17 lines · 62 tokens per session scan A 8aaf89d7f034
openscreen-design is a skill published in the GitHub repository getopenscreen/openscreen (4,371 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 451 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 2026-08-30.
Other skills, from other repositories
create-canvas
Create a project Copilot extension canvas for the current workspace.
figma
Import Figma content into a HyperFrames composition — rendered assets, brand tokens, components, storyboard sections → reconstructed motion (frames read as states, not slides) (REST/CLI), connector-assisted motion when available, and shaders from a connector or native export. Use when the user pastes a figma.com link…
motion-graphics
A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…
open-pencil
Work with Figma .fig design files and the running OpenPencil editor — inspect structure, query nodes, analyze design tokens, export PNG/SVG/PDF/JSX, and modify designs programmatically. Use when asked to open, inspect, export, analyze, or edit .fig files, or to control the running OpenPencil app.
winui-design
Read before writing or changing WinUI 3 XAML: choosing controls, pages and navigation, layout, Fluent Design, theming, accessibility, x:Bind, real samples, and checking that APIs exist with winapp find-api. Not for WPF or WinForms UI, even if the app uses the Windows App SDK.
visualize
Render a polished visual inline in the chat as part of your answer — a diagram, a chart, an interactive explainer, or a UI mockup. Load it proactively whenever an explanation would land better as a picture than as prose. Do not wait to be asked.