usage-monitor: Skill for Claude Code

.claude/skills/usage-monitor-visual-options/SKILL.md

usage-monitor-visual-options is a skill for Claude Code from edilsonvilarinho/usage-monitor. It costs 65 tokens per session (5,680 once invoked), scanned A, original, MIT.

A visual prototyping workflow that creates several animated HTML versions of a Usage Monitor change side by side before the Kotlin implementation is written.

In plain words
What is it for?
Use it to explore animations, HUD changes, and other visual updates in the Usage Monitor app, then choose a direction for implementation.
Why use it?
It lets you compare visual directions early instead of rejecting finished interface code after seeing it. It also records past choices and avoids repeating rejected designs.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code; mentions Codex; mentions OpenCode.

This is edilsonvilarinho/usage-monitor's own configuration. It tells Claude Code how to work on usage-monitor itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything usage-monitor configures →

Reuse

Borrowing it

Nothing to install: this file belongs to edilsonvilarinho/usage-monitor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/edilsonvilarinho/usage-monitor/main/.claude/skills/usage-monitor-visual-options/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/edilsonvilarinho/usage-monitor

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 usage-monitor-visual-options

README.md
[![agentmods](https://agentmods.dev/badge/skills/edilsonvilarinho/usage-monitor/usage-monitor-visual-options/github.svg)](https://agentmods.dev/skills/edilsonvilarinho/usage-monitor/usage-monitor-visual-options)
Your own site
<a href="https://agentmods.dev/skills/edilsonvilarinho/usage-monitor/usage-monitor-visual-options"><img src="https://agentmods.dev/badge/skills/edilsonvilarinho/usage-monitor/usage-monitor-visual-options/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 usage-monitor-visual-options

Your own site · 80×15
<a href="https://agentmods.dev/skills/edilsonvilarinho/usage-monitor/usage-monitor-visual-options"><img src="https://agentmods.dev/badge/skills/edilsonvilarinho/usage-monitor/usage-monitor-visual-options.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,680 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 $0.00065 $0.05680
Opus 5.5 $0.00026 $0.02272
Sonnet 5.5 $0.00013 $0.01136
Haiku 4.5 $0.00006 $0.00568

Measured 2d ago against content hash fa9f41192231, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

usage-monitor-visual-options 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (assets/gargantua-ring.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/usage-monitor-visual-options/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Usage Monitor — opções visuais em HTML

O usuário escolhe mudança visual vendo, nunca no escuro: duas rodadas de visual feito direto no Kotlin foram recusadas ("muito 2D", "disco chamativo"), e todas as rodadas com opções lado a lado saíram escolhidas de primeira. O objetivo dele é a HUD "mais bonita, tema espacial", sem perder a leitura do dado. Esta skill recebe o que mudar e quantas opções (ex.: /usage-monitor-visual-options animação do balão 5) e entrega N protótipos animados lado a lado, no tema vigente, para ele escolher — e só depois disso vem o Compose.

Sem número no pedido, faça 5. Com menos de 3, faça 3.

1. Antes de desenhar

  1. Ler o tema vigente e o histórico do que já foi escolhido e recusado — a tabela no fim desta skill é a fonte. Não reproponha uma opção já recusada com o mesmo nome ou o mesmo gesto.
  2. Ler a seção da tela em docs/hud-notch.md (HUD) ou em docs/presentation.md (demais telas), e o contrato da primitiva em docs/design-system/components/**/*.prompt.md. A skill usage-monitor-design tem a precedência.
  3. Olhar o que existe hoje no código (tempo, curva, o que anima) — vira o card "Hoje (referência)", tracejado, quando a mudança substitui algo.
  4. Se o usuário mandou print, reproduzir o conteúdo real dele (textos, contas, valores) no mockup.

2. Regras de criação (valem para toda opção)

  • Vocabulário Gargantua: luz quente (--gargantua-gold #E8AE63, --gargantua-hot #FFF0CB, --gargantua-ember #B4501E), núcleo escuro (#030508), plasma com núcleo claro, clarão, ondas finas, lente, disco com Doppler (quente de um lado, brasa do outro). Cada opção nomeada por um fenômeno ("B3 · Jato relativístico", "D5 · Horizonte de eventos") com prefixo de letra da rodada.
  • Dado nunca anima errado: comprimento de barra/arco não cresce por efeito, número não passa do valor (sem overshoot/rebote), cor nunca informa sozinha. Efeito é por cima do dado, não no lugar dele.
  • Cenário discreto: o usuário recusou efeito "chamativo" (disco forte, 6 faixas). Efeito não compete com o dado nem com o cometa azul de sessão.
  • Finito por padrão: transição tem duração em ms (tipicamente 180–800). Animação infinita só se o pedido for de estado contínuo, e ela mora atrás de AppMotionPolicy.continuous no app.
  • "Reduzir animações" = corte seco em todas; diga isso no texto.
  • Geometria não muda por quadro: nada de janela ou notch redimensionando; revelar é recorte ou desenho por cima.
  • Opções distintas entre si no gesto (não cinco variações de fade). Se duas ficarem parecidas, troque uma.
  • Mesma animação aplicada a todas as superfícies pedidas (ex.: balão da conta e da engrenagem).
  • Opções só quando competem pelo mesmo lugar. Quando o pedido é um produto com várias peças complementares (rodada AG, modo terminal), a galeria de opções soltas confunde: mostre a proposta fechada, tela por tela, e deixe a escolha para o que de fato disputa a mesma tela.

Read the full file on GitHub · 133 lines

Files

What ships with it

2 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.

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. 2d ago Changed · +5 lines fa9f41192231
  2. 8d ago First seen · 128 lines · 65 tokens per session scan A 47e15b2e27ab

Subscribe to this mod's changes

usage-monitor-visual-options is a skill published in the GitHub repository edilsonvilarinho/usage-monitor (16 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 5,680 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 2026-10-16.