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 token-mapgit 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/token-map)<a href="https://agentmods.dev/skills/nexu-io/open-design/token-map"><img src="https://agentmods.dev/badge/skills/nexu-io/open-design/token-map/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/token-map"><img src="https://agentmods.dev/badge/skills/nexu-io/open-design/token-map.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
- medium Excessive Agency · line 41 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.01281 |
| Opus 5.5 | $0.00012 | $0.00512 |
| Sonnet 5.5 | $0.00006 | $0.00256 |
| Haiku 4.5 | $0.00003 | $0.00128 |
Grade A, and why
token-map 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 1mo 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Token map
Spec §10 / §21.3.1: every figma-migration / code-migration run crosses the same boundary — "the source has its own tokens; the target uses the active OD design system; we need a deterministic mapping". This atom produces that mapping.
Inputs
figma/tokens.jsonfromfigma-extract(figma-migration), ORcode/tokens.jsonfromdesign-extract(code-migration).- The active design system DESIGN.md (already injected into the prompt; the atom reads from the staged design-system context).
Output
project-cwd/
└── token-map/
├── colors.json # { source: '#hex' | 'tokenName', target: '--ds-token' }[]
├── typography.json # font + size + weight pairings
├── spacing.json # spacing scale crosswalk
├── unmatched.json # { source: ..., reason: 'no-target-equivalent' }[]
└── meta.json # { sourceKind: 'figma' | 'code', generatedAt, atomDigest }
unmatched.json is the audit list a human reviews; the agent must
not invent target tokens silently.
Semantic token inference
Figma often exports anonymous source names such as color-3,
paint/17, or raw #5B8DEF. Do not ask the user to rename those
before mapping. First infer the semantic role from usage evidence:
- Node path, component name, instance overrides, variant/state labels,
frame name, layer name, and nearby text such as
Primary,Selected,Link,Error,Focus,Nav,Button, orCTA. - CSS-like position in the rendered tree: background fill, foreground text/icon, border, divider, overlay, shadow tint, focus ring, status badge, chart series, or brand/accent treatment.
- Contrast relationships: a color paired repeatedly with the main canvas is likely foreground; one paired with foreground inside CTA components is likely primary/accent background; a thin outline around interactive elements is likely border or focus-ring.
- Reuse topology: a value that appears across primary buttons,
selected tabs, and active nav items is stronger evidence for
--ds-color-primarythan a value that appears once in an illustration.
What ships with it
2 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.
- 1mo ago First seen · 148 lines · 30 tokens per session scan A 64d236eb0d00
token-map is a skill published in the GitHub repository nexu-io/open-design (104,395 stars, last pushed today), licensed Apache-2.0. It adds 30 tokens to every session and 1,281 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 2026-09-03.
Other skills, from other repositories
deck-swiss-international
A slide-deck template based on Swiss International graphic design: a strict 16-column grid, large clear text, charts, and one fixed bright accent colour. It provides 22 layouts for covers, timelines, comparisons, metrics, and other content.
deck-guizang-editorial
A slide-deck template combining electronic-magazine layouts with an e-ink, printed-paper look. It offers five fixed color palettes and ten reusable page layouts for storytelling and editorial content.
frame-light-leak-cinema
A visual template for a cinematic opening frame or chapter card. It combines warm film light leaks, 35mm-style grain, black letterbox bars, and large serif lettering.
frame-macos-notification
A template for realistic macOS Big Sur-style notification banners, with an app icon, title, message, and optional action button.
mockup-device-3d
A template for presenting app or product interfaces inside CSS-rendered 3D iPhone and MacBook mockups. CSS is the web styling system used to control layout, colors, and visual effects.
frame-flowchart-sticky
A single-file HTML template for showing a process or system as a whiteboard with coloured sticky notes, curved arrows, and optional mouse interactions.