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 takaoumehara/superforge-skill --skill superforge-uigit clone --depth 1 https://github.com/takaoumehara/superforge-skillWrote 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/takaoumehara/superforge-skill/superforge-ui)<a href="https://agentmods.dev/skills/takaoumehara/superforge-skill/superforge-ui"><img src="https://agentmods.dev/badge/skills/takaoumehara/superforge-skill/superforge-ui.svg" alt="Measured on agentmods" 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 | $0.00301 | $0.04603 |
| Opus 5 | $0.00151 | $0.02302 |
| Sonnet 5 | $0.00060 | $0.00921 |
| Haiku 4.5 | $0.00030 | $0.00460 |
Grade A, and why
superforge-ui 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 — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Superforge UI — Interface Design, Motion & Native Engineering Engine
Use this skill when designing or implementing user interfaces across Web, iOS (SwiftUI), and Android (Jetpack Compose). This engine guarantees high aesthetic value, typography perfection, state specification, and micro-interaction polish.
0a. Name the job before sourcing anything
Two questions decide whether the rest of this process solves the right problem, and both get answered implicitly if they are not answered out loud.
What does success look like on this surface? Persuade (they decide and act) · Operate (they finish a task) · Read (they understand) · Experience (they are inside the work). Pick it from the surface, not from the company — a developer tool's landing page is Persuade, a fashion house's documentation is Read. Each mode also names what it may legitimately sacrifice, and a mode that gives up nothing is a wish rather than a mode.
Preserving or replacing? Refinement keeps the identity, the behaviour, and everything outside the stated scope. Redesign keeps product truth and function but treats the old look as evidence, not as something to improve. Never split the difference — polish spent on a look already decided against is the most wasted work in this process.
Both, plus the rule that a pinned brief outranks every default in this suite →
references/surface-and-scope.md.
0. Source the direction before designing anything
A model asked to "make it look good" returns the average of everything it has seen, and averages look like averages — that is the entire explanation for the recognisable "AI interface" look. A stronger model produces a better-executed average, not a different one.
So before any token is chosen, settle where the direction comes from: references
the user admires, an existing design arriving from another tool (Claude Design,
Google Stitch, Figma, v0), or — declared honestly — nothing. Then extract the
system behind it in six layers (structure, space, type, colour, motion,
imagery), never the content, and record the sources and the deliberate
divergences → references/design-sourcing.md.
What ships with it
24 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.
- assets/templates/design.md 659 B
- evals/evals.json 669 B
- README.es.md 7.4 KB
- README.ja.md 8.5 KB
- README.ko.md 8.1 KB
- README.md 6.9 KB
- README.zh-CN.md 6.6 KB
- references/aesthetic-direction.md 9.9 KB
- references/build-floor.md 9.9 KB
- references/design-process.md 10 KB
- references/design-sourcing.md 14 KB
- references/design-system-output.md 5.2 KB
- references/effect-vocabulary.md 7.6 KB
- references/first-run.md 8.4 KB
- references/heavy-visuals.md 11 KB
- references/interactive-components.md 2.3 KB
- references/internationalization.md 7.5 KB
- references/landing-page.md 8.7 KB
- references/motion-system.md 12 KB
- references/performance-budget.md 7.1 KB
- references/slide-page.md 8.8 KB
- references/sound.md 6.3 KB
- references/surface-and-scope.md 6.6 KB
- references/toolchain.md 11 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.
- 7d ago First seen · 368 lines · 301 tokens per session scan A 06dc3af7de0a
superforge-ui is a skill published in the GitHub repository takaoumehara/superforge-skill (1 stars, last pushed 23d ago), licensed MIT. It adds 301 tokens to every session and 4,603 once invoked, about $0.0015 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 2026-08-31.
Other skills, from other repositories
android-ui-engineering
Use when building UI with Jetpack Compose. Covers component design, state hoisting, recomposition optimization, Material 3 theming, Navigation 3, adaptive layouts for large screens, previews, screenshot verification, and XML interop.
android-accessibility
Use when building or reviewing Android UI for accessibility. Covers TalkBack, content descriptions, touch targets, Compose semantics, focus order, and Accessibility Scanner testing.
imagegen-frontend-mobile
Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile products. Prioritizes clean hierarchy, comfortably readable text, strong multi-screen consistency, controlled color palettes, non-generic creative direction, textured…
liquid-glass-design
Patterns for implementing Apple's Liquid Glass — a dynamic material that blurs content behind it, reflects color and light from surrounding content, and reacts to touch and pointer interactions. Covers SwiftUI, UIKit, and WidgetKit integration.
liquid-glass-design
Patterns for implementing Apple's Liquid Glass — a dynamic material that blurs content behind it, reflects color and light from surrounding content, and reacts to touch and pointer interactions. Covers SwiftUI, UIKit, and WidgetKit integration.
ui-analyzer
Analyzes mobile UI designs (Figma/Screenshots) to define Target requirements. Extracts data fields, types, and states.