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 Insajin/autopus-adk --skill make-interfaces-feel-bettergit clone --depth 1 https://github.com/Insajin/autopus-adkWrote 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/insajin/autopus-adk/make-interfaces-feel-better)<a href="https://agentmods.dev/skills/insajin/autopus-adk/make-interfaces-feel-better"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/make-interfaces-feel-better/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/insajin/autopus-adk/make-interfaces-feel-better"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/make-interfaces-feel-better.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Memory Poisoning · line 81 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00040 | $0.01131 |
| Opus 5 | $0.00020 | $0.00566 |
| Sonnet 5 | $0.00008 | $0.00226 |
| Haiku 4.5 | $0.00004 | $0.00113 |
Grade A, and why
make-interfaces-feel-better 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Make Interfaces Feel Better
Use this skill after the core layout and behavior exist, or during review when a UI feels technically correct but visually rough. It focuses on small design-engineering details that compound into a more polished interface.
This is a polish pass, not a new visual identity. Read the project's DESIGN.md, tokens, shared components, and existing screens first. Apply the details through the project's current stack and naming conventions.
Detail Pass
Typography
- Use balanced wrapping for short headings and titles when the platform supports it.
- Use prettier wrapping for short-to-medium paragraphs, descriptions, captions, and list text.
- Leave long prose, code, and preformatted text on normal browser wrapping.
- Apply font smoothing once at the root when the stack supports it, rather than per element.
- Use tabular numerals for changing numbers: timers, counters, prices, dashboard metrics, scoreboards, and numeric table columns.
Surfaces
- For nested rounded surfaces, make the outer radius visually account for the padding between the outer and inner element.
- Use optical alignment when geometric centering looks wrong, especially text+icon buttons, play icons, arrows, carets, stars, and asymmetric SVGs.
- Use shadows or ring-like shadow layers for element depth when a solid border would look harsh on varied backgrounds.
- Keep real dividers, table boundaries, and accessibility-critical input outlines as borders when they are serving structure.
- Add subtle inset outlines to images/media when the surrounding system uses depth or framed surfaces; use neutral black or white opacity, not tinted brand colors.
- Interactive controls should expose a stable hit area: at least 44px where touch is possible, and never below 40px for compact pointer-only controls unless the surrounding component already expands the target.
- Do not let invisible hit areas overlap.
Motion
- Use transitions for interactive state changes so they can be interrupted and retargeted mid-action.
- Reserve keyframe or staged motion for one-shot entrance, loading, or storytelling sequences.
- Split entrance motion into semantic chunks, then stagger lightly so the page reads in order.
- Make exits shorter and quieter than entrances; use small fixed movement instead of large dramatic travel unless spatial context truly matters.
- Animate contextual icons with opacity, scale, and light blur rather than abruptly toggling visibility.
- Use a restrained press scale on tactile controls; avoid exaggerated shrink effects.
- Respect reduced-motion settings and keep critical state changes understandable with motion disabled.
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 · 88 lines · 40 tokens per session scan A 37114f59f3a0
make-interfaces-feel-better is a skill published in the GitHub repository Insajin/autopus-adk (111 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 1,131 once invoked, about $0.0002 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
css-architecture
CSS architecture, design token strategy, Tailwind conventions, CSS Modules, container queries, dark mode, responsive patterns, and animation architecture. Use for design token naming, CSS custom properties, Tailwind config, container queries, dark mode implementation, fluid typography, or CSS animation decisions.…
design-system-tokens
Token architecture and component specifications. Three-layer tokens (primitive → semantic → component), CSS variables, spacing/typography scales, and component state definitions. Use for design token creation and systematic design.
design-md
Google's open DESIGN.md specification for describing visual identities to coding agents. YAML tokens + Markdown rationale + npx CLI for WCAG validation and W3C DTCG/Tailwind export. Use for formal, agent-consumable design system documentation.
popular-web-designs
54 real-world design systems (Stripe, Linear, Vercel, Supabase, Apple, Notion, Cursor, etc.) as ready-to-use HTML/CSS reference. Exact color palettes, typography hierarchies, component specs, spacing, shadow systems, and font substitutions. Use when building UI that should match a specific company's aesthetic.
artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
warm-editorial-ui
Apply the "Warm Editorial Refinement" design system — a sophisticated, executive-grade aesthetic with warm cream surfaces (light mode) and warm charcoal surfaces (dark mode), Bahnschrift + Plus Jakarta Sans typography, generous rounded corners, multi-layer shadows, and a warm neutral palette. Supports both light and…