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 procoders/superpowers-v --skill designgit clone --depth 1 https://github.com/procoders/superpowers-vWrote 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/procoders/superpowers-v/design)<a href="https://agentmods.dev/skills/procoders/superpowers-v/design"><img src="https://agentmods.dev/badge/skills/procoders/superpowers-v/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/procoders/superpowers-v/design"><img src="https://agentmods.dev/badge/skills/procoders/superpowers-v/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 | $0.00067 | $0.01044 |
| Opus 5.5 | $0.00027 | $0.00418 |
| Sonnet 5.5 | $0.00013 | $0.00209 |
| Haiku 4.5 | $0.00007 | $0.00104 |
Grade A, and why
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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design
Load this only when the change has a user interface. It adds no questions: the brainstorm asks at most one about identity, and only for a new project.
1. DESIGN.md is the one source of the look
The project's look lives in DESIGN.md at the repo root, in Google's open format
(https://github.com/google-labs-code/design.md): YAML tokens (colors, typography, spacing, rounded,
components) between --- fences, then prose sections in this order: Overview, Colors, Typography, Layout,
Elevation & Depth, Shapes, Components, Do's and Don'ts. Put DESIGN.md in the plan's change_set whenever you write it.
- It exists: follow it. New screens use its tokens and its existing components; a new colour, font or component
goes into
DESIGN.mdfirst, with its reason, never only into a stylesheet. - Existing UI, no DESIGN.md: write it from what is there (CSS variables, theme config, the colours, fonts and spacing the pages actually repeat), exactly as it is. Do not restyle the project; record the current look.
- New project: write it before the first screen, from the spec's
Identity:line and the subject itself (what a real business of this kind looks like, not a generic app). Where the owner left the look to you, say so in Overview.
Components, once. Before writing markup, list the project's existing components and partials (buttons, fields,
form rows, cards, tables, page shell, error summary) and build from them. A pattern that would appear a second time
becomes one shared component with parameters, and its first copy is replaced by it; never paste markup or a style
block from one screen into another. The Components section of DESIGN.md names each shared component and where it
lives.
Then run npx @google/[email protected] lint DESIGN.md and fix every error (it checks the structure, token references
and WCAG AA contrast). Load the tokens into the app as CSS custom properties, so a style never hard-codes a value.
2. The craft floor
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 · 60 lines · 67 tokens per session scan A c5f5c4d098c3
design is a skill published in the GitHub repository procoders/superpowers-v (42 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 1,044 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 2026-10-23.
Other skills, from other repositories
learn
Runs a six-phase research workflow from source bundle to publish-ready output. Use when researching an unfamiliar domain or compiling materials into one reference. Not for quick lookups or single-file reads.
sxo
Search Experience Optimization (SXO), the bridge between SEO and UX/CRO. Audits the journey from the SERP click to the on-page goal: click-through factors (title, meta, rich results), then post-click signals that keep users and drive conversions: above-the-fold relevance and intent match, page speed / Core Web Vitals…
shiny-bslib
Build modern Shiny dashboards and applications using bslib (Bootstrap 5). Use when creating new Shiny apps, modernizing legacy apps (fluidPage, fluidRow/column, tabsetPanel, wellPanel, shinythemes), or working with bslib page layouts, grid systems, cards, value boxes, navigation, sidebars, filling layouts, theming…
interface-craft
Raises the visual and interaction quality of an interface — layout, hierarchy, type, spacing, density, and the details that separate a considered product from a generic one. Use this when a screen works but looks unfinished or default, when a layout feels crowded or arbitrary, when a page has no clear focal point, or…
top-design
Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…
domscribe
Work with Domscribe — the pixel-to-code bridge. Use when setting up, initializing, or configuring Domscribe for a project, OR when editing or modifying UI components (React, Vue, Next.js, Nuxt), implementing features from captured UI annotations, querying runtime context for source locations, exploring component…