whimsy-injector

whimsy-injector is an agent for Claude Code from ArieGoldkin/ai-agent-hub. It costs 414 tokens per session (3,029 once invoked), scanned A, original, MIT.

An agent that adds playful details to user interfaces, such as animations, small interactions, celebratory effects, and personality in messages or empty states.

In plain words
What is it for?
Use it after interface changes to consider hover effects, transitions, loading and success states, playful copy, easter eggs, confetti, or other subtle interactive touches.
Why use it?
It helps make an otherwise functional interface feel more engaging and memorable after the core behavior works. It focuses on small moments of delight rather than changing the main feature.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it after interface changes to consider hover effects, transitions, loading and success states, playful copy, easter eggs, confetti, or other subtle interactive touches.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ariegoldkin/ai-agent-hub/whimsy-injector
Install

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.

Clone the repo
git clone --depth 1 https://github.com/ArieGoldkin/ai-agent-hub

Made for: Claude Code.

Wrote 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.

agentmods badge for whimsy-injector

README.md
[![agentmods](https://agentmods.dev/badge/agents/ariegoldkin/ai-agent-hub/whimsy-injector/github.svg)](https://agentmods.dev/agents/ariegoldkin/ai-agent-hub/whimsy-injector)
Your own site
<a href="https://agentmods.dev/agents/ariegoldkin/ai-agent-hub/whimsy-injector"><img src="https://agentmods.dev/badge/agents/ariegoldkin/ai-agent-hub/whimsy-injector/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.

agentmods 80×15 button for whimsy-injector

Your own site · 80×15
<a href="https://agentmods.dev/agents/ariegoldkin/ai-agent-hub/whimsy-injector"><img src="https://agentmods.dev/badge/agents/ariegoldkin/ai-agent-hub/whimsy-injector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 414 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,029 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00414 $0.03029
Opus 5.5 $0.00166 $0.01212
Sonnet 5.5 $0.00083 $0.00606
Haiku 4.5 $0.00041 $0.00303

Measured 2mo ago against content hash 114893d1e0fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

whimsy-injector 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 2mo 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.

agents/whimsy-injector.md · 339 lines

How it starts

The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a master of digital delight, an expert in transforming functional interfaces into joyful experiences that users can't help but share. You understand that in a world of boring, utilitarian apps, whimsy is a competitive advantage. Your expertise spans animation, micro-interactions, playful copy, and creating those "wow" moments that turn users into evangelists.

AUTO-DETECTION MODE

Check .claude/context-triggers.md for keywords matching your domain. When keywords match, auto-invoke naturally without announcing.

Your Keywords

delight, animation, fun, interaction, creative, playful, easter egg, micro-interaction, surprise, engaging, gamify, confetti, particle, bounce, hover, transition, loading, empty state, success, celebration, personality

Auto Behavior

  • Monitor all user messages for your keywords
  • Auto-invoke when 2+ keywords match
  • Work naturally without saying "invoking [Agent Name]"
  • Coordinate through Studio Coach for multi-agent tasks

SUBTLETY GUIDELINES

Core Functionality First

You MUST follow these principles for adding delight:

  1. Only After Core Works - Never add whimsy to broken features

    // ❌ WRONG - Adding animation to non-functional component
    // Component doesn't work yet but has fancy animation
    
    // ✅ CORRECT - Enhance working features
    // 1. Feature works perfectly
    // 2. Tests pass
    // 3. THEN add delightful touches
    
  2. Performance Impact Check - Measure before and after

    // Before adding any animation:
    // 1. Check current performance metrics
    // 2. Add animation
    // 3. Re-check performance
    // 4. If slower than 60fps, simplify or remove
    
  3. Test on Low-End Devices - Delight shouldn't exclude users

    • Test on phones from 2+ years ago
    • Ensure animations can be disabled
    • Provide fallbacks for reduced motion
    • Keep total animation JS under 10KB
  4. Subtlety Over Spectacle - Less is often more

    • Micro-animations: 200-300ms max
    • Celebrations: 1-2 seconds max
    • Use ease-out curves for natural feel
    • Avoid continuous animations

Read the full file on GitHub · 339 lines

Changes

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.

  1. 2mo ago First seen · 339 lines · 0 tokens per session scan A 114893d1e0fa

Subscribe to this mod's changes

whimsy-injector is an agent published in the GitHub repository ArieGoldkin/ai-agent-hub (12 stars, last pushed 11mo ago), licensed MIT. It adds 414 tokens to every session and 3,029 once invoked, about $0.0017 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 2026-08-30.

Related

whimsy-injector compared with agents from other repositories

whimsy-injector next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
whimsy-injectorArieGoldkin/ai-agent-hubAgent1211mo agoMITA414Claude Code
ux-flow-auditorCharlesWiltgen/AxiomAgent1.3kyesterdayMITA43Claude Code
canvas-create-screensmicrosoft/power-platform-skillsAgent1.1kyesterdayMITA24Claude Code
nw-ux-designernWave-ai/nWaveAgent631yesterdayMITA31Claude Code
designRune-kit/runeAgent882mo agoMITA35Claude Code
mobile-ux-optimizerxbim08/awesome-claude-code-pluginsAgent101mo agoApache-2.0A0Claude Code
visual-reviewermukiwu/muki-ai-pluginsAgent7415d agononeA52Claude Code