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 itonys/7onic --skill 7onic-designgit clone --depth 1 https://github.com/itonys/7onicWrote 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/itonys/7onic/7onic-design)<a href="https://agentmods.dev/skills/itonys/7onic/7onic-design"><img src="https://agentmods.dev/badge/skills/itonys/7onic/7onic-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/itonys/7onic/7onic-design"><img src="https://agentmods.dev/badge/skills/itonys/7onic/7onic-design.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 | $0.00068 | $0.00770 |
| Opus 5.5 | $0.00027 | $0.00308 |
| Sonnet 5.5 | $0.00014 | $0.00154 |
| Haiku 4.5 | $0.00007 | $0.00077 |
Grade A, and why
7onic-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 7d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
7onic Design — guided, validated UI building
Turn a request ("build a settings page", "SaaSダッシュボード", "가격 페이지") into token-accurate 7onic code. This skill is an orchestrator: the knowledge lives in the 7onic MCP server tools — your job is to call them in the right order and refuse to hand over unvalidated code.
If the 7onic-design MCP tools are not available, stop and have the user
install the plugin (claude plugin install 7onic-design@7onic) or wire
the server manually — do not improvise from memory.
Step 0 — Scope the request
Break the request into screens/sections and list them back in the user's language. For a multi-screen request, confirm the breakdown before writing code (e.g. dashboard → layout shell / metric row / chart panel / table). For a single component or section, skip the confirmation and go.
Step 1 — Components first
For every UI element, discover before you write:
list_componentswith a natural-language query (en/ja/ko all fine) — prefer a 7onic component over any hand-rolled HTML.get_componentfor props/variants/sizes of each component you will use — never guess a prop name or enum value.get_component_examplesand copy the import lines exactly — named exports only, charts from@7onic-ui/react/chart.
Step 2 — Tokens for everything visual
search_tokens/get_tokenfor colors, spacing, typography, shadows. Token NAMES are the API; values are user-configurable — never hardcode.- About to write any raw value (hex color, px size, ms duration)?
Call
suggest_tokensfirst. If it returns an exact token, use the token class. If not, it returns a user-confirmation prompt — relay that prompt and wait; never bypass tokens silently. - Semantic colors theme-switch automatically: no
dark:prefixes. Typography tokens pair font-size with line-height: noleading-*.
Step 3 — Layout
get_layout_pattern for the structural skeleton — symmetric grids,
reading column, section rhythm, element rows, inline groups. Grid system
is 4/8/12 columns (mobile/tablet/desktop); icon+text rows always use
items-center.
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.
- 7d ago First seen · 71 lines · 68 tokens per session scan A 08bf4457c587
7onic-design is a skill published in the GitHub repository itonys/7onic (5 stars, last pushed 7d ago), licensed MIT. It adds 68 tokens to every session and 770 once invoked, about $0.0003 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 2026-10-09.
Other skills, from other repositories
sigil-playbook
The Sigil Playbook codifies the small vocabulary of structural patterns that make any new page "just work." Originating from the Reticle design language (Dedalus monorepo), these 10 rules — 6 compositional moves + 4 supporting patterns — replace dozens of ad-hoc layout decisions.
sigil-polish
Design engineering principles for making Sigil interfaces feel polished. Use when building UI components, reviewing frontend code, implementing animations, hover states, shadows, borders, typography, micro-interactions, enter/exit animations, or any visual detail work. Triggers on UI polish, design details, "make it…
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
ui-components
UI component library patterns for shadcn/ui and Radix Primitives. Use when building accessible component libraries, customizing shadcn components, using Radix unstyled primitives, or creating design system foundations.
s2-docs
Look up Spectrum 2 (S2) component documentation, design guidelines, and usage patterns when building with React Spectrum or Spectrum Web Components. Use when the user mentions Spectrum, S2, React Spectrum, RSP, Spectrum Web Components, or SWC, or names a Spectrum component (Button, Picker, ComboBox, TextField…
better-design
Build, improve, and review production interfaces with the Better Design MCP. Use for frontend design, UI, UX, interactions, flows, forms, navigation, components, styling, design systems, accessibility, responsive layouts, motion, React Native, Expo, Shopify, Three.js, and product video work, especially when creating…