usage-monitor: Skill for Claude Code

.claude/skills/usage-monitor-design/SKILL.md

usage-monitor-design is a skill for Claude Code from edilsonvilarinho/usage-monitor. It costs 54 tokens per session (1,062 once invoked), scanned A, original, MIT.

A project-specific design guide for the Usage Monitor app. It tells contributors which visual rules, reusable interface parts, and design files to follow when changing screens or prototypes.

In plain words
What is it for?
Use it when designing, changing, or reviewing screens, dialogs, tray interfaces, PDF reports, or visual prototypes.
Why use it?
It prevents the app's Compose screens and other visible surfaces from drifting away from the approved design.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; 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-design/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-design

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/edilsonvilarinho/usage-monitor/usage-monitor-design"><img src="https://agentmods.dev/badge/skills/edilsonvilarinho/usage-monitor/usage-monitor-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,062 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 $0.00054 $0.01062
Opus 5.5 $0.00022 $0.00425
Sonnet 5.5 $0.00011 $0.00212
Haiku 4.5 $0.00005 $0.00106

Measured yesterday against content hash a5cbefa89242, 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-design 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 yesterday.

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-design/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Usage Monitor — design system

A fonte de verdade visual deste repositório é docs/design-system/. Ela é normativa: divergência entre o Compose e o design system é defeito do Compose. A tabela completa de precedência está em CLAUDE.md, seção Sistema visual → Design system — precedência.

Antes de desenhar qualquer coisa

  1. Ler docs/design-system/readme.md inteiro. Ele carrega os fundamentos de conteúdo (voz, casing, "todo estado carrega uma palavra", "controle desabilitado sempre diz por quê") e as fundações visuais.
  2. Ler os tokens em docs/design-system/tokens/. Eles já têm equivalente exato em Kotlin — AppSpacing, AppShapes, AppElevation, AppMotion, AppThemePreset.OBSIDIANA_DARK/PORCELANA_LIGHT e AppAccents em src/commonMain/kotlin/com/usagemonitor/presentation/ui/theme/. Não introduza um valor novo: se falta um degrau, a decisão vai para o design system antes de ir para o código.
  3. Ler o contrato da primitiva que você vai usar em docs/design-system/components/. Cada *.prompt.md diz o que a primitiva resolve e o que é proibido dentro dela.
  4. Abrir o mockup da tela no protótipo aprovado, docs/planos/prototipo-visual-opencode.html, e o kit correspondente em docs/design-system/ui_kits/desktop-app/.

Regras que não se negociam

  • Nenhuma tela reimplementa uma primitiva. Antes de escrever Surface, Card, Modifier.border, .background com cor de superfície ou RoundedCornerShape, procure em presentation/ui/components/AppStructure.kt, AppControls.kt, AppStates.kt e nos vizinhos AppTabs.kt, AppSettingsNav.kt, AppSurfaceDepth.kt, AppChips.kt, AppMenu.kt, AppTooltip.kt e AppStatusPill.kt.
  • Primitiva construída e não adotada não conserta nada. O commit que cria e o que consome são o mesmo.
  • Cor de acento vem de AppAccents.current e AppTone, nunca de darkAppAccents / lightAppAccents diretamente — val de topo de arquivo não lê o tema em vigor.
  • Cor nunca informa sozinha. Todo estado carrega ponto e palavra (AppStatusIndicator).
  • Animação infinita só atrás de AppMotionPolicy.continuous. Fora dela, trava o waitForIdle dos testes de componente. Carregamento é esqueleto estático, sem shimmer e sem spinner.
  • Sem emoji. Os ícones são marcas Unicode em IBM Plex Mono, e a lista está no readme.md.
  • Escala tipográfica fechada em 10/12/14/16/20/28; raio com teto de 10dp; elevação 8 só para janela, diálogo, menu e overlay.

Read the full file on GitHub · 67 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. yesterday Changed · +5 lines a5cbefa89242
  2. 8d ago First seen · 62 lines · 54 tokens per session scan A 70b40b70e6df

Subscribe to this mod's changes

usage-monitor-design is a skill published in the GitHub repository edilsonvilarinho/usage-monitor (16 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 1,062 once invoked, about $0.0002 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.