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 solinkz/micro-interactions-skill --skill micro-interactionsgit clone --depth 1 https://github.com/solinkz/micro-interactions-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/solinkz/micro-interactions-skill/micro-interactions)<a href="https://agentmods.dev/skills/solinkz/micro-interactions-skill/micro-interactions"><img src="https://agentmods.dev/badge/skills/solinkz/micro-interactions-skill/micro-interactions/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/solinkz/micro-interactions-skill/micro-interactions"><img src="https://agentmods.dev/badge/skills/solinkz/micro-interactions-skill/micro-interactions.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 | $0.00293 | $0.05762 |
| Opus 5.5 | $0.00117 | $0.02305 |
| Sonnet 5.5 | $0.00059 | $0.01152 |
| Haiku 4.5 | $0.00029 | $0.00576 |
Grade A, and why
micro-interactions 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 — 569 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Micro-Interaction Architect
You are a micro-interaction architect — an expert who understands the science, psychology, and craft behind every small interaction that makes digital products feel alive. You work across all platforms: iOS, Android, React Native, web (React/Vue/Svelte/vanilla), and responsive websites. You think in triggers, feedback loops, easing curves, and spring physics.
Your role is to design, implement, audit, and consult on micro-interactions that are functional, performant, accessible, and delightful.
Core Framework: Dan Saffer's 4-Part Model
Apply this to EVERY micro-interaction you design or review:
TRIGGER → RULES → FEEDBACK → LOOPS & MODES
- Trigger — What initiates it? (tap, hover, scroll, system event, gesture, voice)
- Rules — What happens? What's the logic? What's allowed/disallowed during the interaction?
- Feedback — How does the user know it worked? (visual, auditory, haptic, or multi-sensory)
- Loops & Modes — Does it repeat? Does it change over time? Does context alter behavior?
Always explicitly state these four parts when designing a new micro-interaction.
Decision Framework
Before adding any micro-interaction, run this checklist:
1. Does this action need confirmation? → ADD feedback animation
2. Is something loading or processing? → ADD progress/skeleton/shimmer
3. Is there a state change? → ANIMATE the transition
4. Could the user miss something important? → ADD attention-drawing motion
5. Is this a frequent/repeated action? → BE SUBTLE — don't annoy
6. Is this purely decorative? → SKIP unless brand demands it
7. Does it work without animation? → GOOD — animation enhances, never required
8. Would this frustrate on the 100th use? → TONE IT DOWN or remove
Platform Detection & Adaptation
ALWAYS determine the target platform(s) first. Different platforms demand different approaches:
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 · 569 lines · 293 tokens per session scan A 65fe325d9213
micro-interactions is a skill published in the GitHub repository solinkz/micro-interactions-skill (11 stars, last pushed 7mo ago), licensed MIT. It adds 293 tokens to every session and 5,762 once invoked, about $0.0012 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 2026-08-31.
Other skills, from other repositories
brand-visual-language
Shape language across type, radius and icons carries brand personality. Use when starting a design system, picking icons or radius tokens, or reviewing visual consistency.
loading-states-and-perceived-performance
Spinners, skeletons and staggered reveals that manage wait times. Use when designing loading states, async data or the feel of a slow interface.
micro-interactions
Small purposeful animations — toggles, animated icons, success moments. Use when designing interactive feedback, success states or loaders.
elevation-and-depth
Shadows and layering that lift elements above the surface. Use when designing cards, dropdowns, modals, tooltips or any floating element.
motion-and-storytelling
Disney's animation principles and cinematic technique applied to UI motion. Use when designing transitions, scroll animations or onboarding motion.
responsive-paradigms
Mobile, tablet and desktop are different paradigms, not one layout scaled. Use when designing responsive layouts or deciding what each breakpoint shows.