OpenDesign is an open-source, local-first desktop app that lets coding agents create prototypes, dashboards, slide decks, images, video, and design systems as exportable files. It is used by people working with agent runtimes such as Claude Code, Codex, Cursor, and DeepSeek Harness. The catalogue add-ons extend the OpenDesign workflow with skills, instructions, commands, and plugins.
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 nexu-io/open-design --skill live-dashboardgit clone --depth 1 https://github.com/nexu-io/open-designWrote 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/nexu-io/open-design/live-dashboard)<a href="https://agentmods.dev/skills/nexu-io/open-design/live-dashboard"><img src="https://agentmods.dev/badge/skills/nexu-io/open-design/live-dashboard/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/nexu-io/open-design/live-dashboard"><img src="https://agentmods.dev/badge/skills/nexu-io/open-design/live-dashboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- 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 | $0.00097 | $0.02208 |
| Opus 5 | $0.00048 | $0.01104 |
| Sonnet 5 | $0.00019 | $0.00442 |
| Haiku 4.5 | $0.00010 | $0.00221 |
Grade A, and why
live-dashboard 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 6d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- live-dashboard — 100% identical, 2 lines differ
- live-dashboard — 98% identical, 3 lines differ
How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Live Dashboard
You are a senior product-designer-engineer building a Live Artifact — an HTML page that behaves like a working dashboard, not a mockup. Your output ships, not only renders.
Pre-flight (must complete before emitting any HTML)
Read assets/template.html— start from this skeleton verbatim. Do not rebuild the shell from scratch. Override only what the user's brief or the active DESIGN.md require.Read references/layouts.md— pick exactly one of the three documented layouts (A · classic dashboard,B · kanban-flavored,C · KPI-only hero). State your choice in your reply.Read references/components.md— copy KPI-card, sparkline, activity row, and database row markup verbatim, then re-skin per the active DESIGN.md. Do not invent new component shapes.Read references/connectors.md— only wheninputs.connector !== mock. Emit a siblingconnectors.jsonlisting every event the artifact subscribes to and every read endpoint it polls.Read references/checklist.md— every P0 row must be true before you emitindex.html. Quote each P0 row inline in your reply with[x]or[ ]. Do not emit while any P0 is unchecked.
Build order
- Lock visual direction from the active
DESIGN.md. Display face should be the system / sans face Notion-leaning systems use (SF Pro, Inter as body, never Inter Display as a hero face). Body 14/22. - Topbar: breadcrumb (
workspace_name / Workspace / page_title) on the left, a<live-pill>on the right showing one of three states:Live · synced(green pulse),Syncing…(blue),Stale · <ago>(amber, afterstale_after_seconds). - Page header: a Notion
page-emoji(a single, semantically relevant emoji — never a generic 🚀 ✨ 🔥), apage-titleat 40px weight 700 letter-spacing -0.01em, a meta row with last-edited-by + "Last refreshed " + the auto-toggle button + the Refresh button. - Callout explaining the Live Artifact contract — pulled-from-where, refresh-when. One line. No marketing language.
- KPI grid: respect
inputs.kpi_count. 1px hairline grid, no shadows, no rounded internal cards. Numbersfont-variant-numeric: tabular-nums, weight 600, letter-spacing -0.01em. Each KPI gets a small grey delta line (↑ 6 vs last week). - Two-column block: a sparkline card (SVG, hand-rolled, no chart library) + the activity feed card. Sparkline shows a 7-day series with subtle accent fill at 10% alpha and a 2px stroke.
- Linked database: a Notion-style table —
db-head(uppercase 12px label-grey) +db-rowrows. Status pills use the Notion five-color set (Done / In progress / Blocked / In review / To do). Person chips use a colored 18px round avatar with two-letter initials. - Footer: source attribution (
Source: Notion API · workspace <workspace_name>) and connector slug.
What ships with it
6 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.
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.
- 6d ago First seen · 203 lines · 97 tokens per session scan A e6220cd3fd28
live-dashboard is a skill published in the GitHub repository nexu-io/open-design (95,021 stars, last pushed today), licensed Apache-2.0. It adds 97 tokens to every session and 2,208 once invoked, about $0.0005 per session on Opus 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 2026-09-03.
Other skills, from other repositories
flowai-team-dashboard
A team-management dashboard layout with tabs for members, team details, and activity logs, plus charts and data export.
kanban-board
A Kanban board is a visual task list with columns for stages such as To do, In progress, In review, and Done. It can show filters, labels, due dates, assignees, comments, and swimlanes that group cards.
team-okrs
An OKR tracking page for a quarter. OKRs, or objectives and key results, are goals paired with measurable results.
weekly-update
A six-to-eight-page horizontal team update presentation covering completed work, current work, blockers, metrics, requests, and thanks.
meeting-notes
A meeting-notes layout that records the meeting title, attendees, agenda, decisions, action items, owners, deadlines, status, and next meeting. Action items are tasks agreed during the meeting.
memtrace-fleet-first
Coordinate fleets of coding agents sharing one repo+branch: publish typed intents, classify edit episodes, and resolve conflicts before they collide. Use FIRST when multiple agents work the same repo+branch, before reading/planning/editing, when joining a fleet or handing work off, and when the user says two agents…