usage-monitor: Skill for Claude Code

.claude/skills/usage-monitor-test-report/SKILL.md

usage-monitor-test-report is a skill for Claude Code from edilsonvilarinho/usage-monitor. It costs 76 tokens per session (1,855 once invoked), scanned A, original, MIT.

A test-reporting workflow that runs the Usage Monitor test suites, measures coverage, and creates an HTML report plus machine-readable JSON.

In plain words
What is it for?
It is for running Kotlin and server tests, collecting coverage, reporting failures, and checking whether the project is ready for a pull request or merge.
Why use it?
It replaces a general impression of test safety with test results, coverage, failures, and readiness information before a pull request or merge.

Skill for Claude Code

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

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-test-report/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-test-report

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/edilsonvilarinho/usage-monitor/usage-monitor-test-report"><img src="https://agentmods.dev/badge/skills/edilsonvilarinho/usage-monitor/usage-monitor-test-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,855 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 $0.00076 $0.01855
Opus 5.5 $0.00030 $0.00742
Sonnet 5.5 $0.00015 $0.00371
Haiku 4.5 $0.00008 $0.00186

Measured yesterday against content hash 1ef47bbd0905, 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-test-report 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/build-test-report.mjs, scripts/report-html.mjs), 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-test-report/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Usage Monitor — relatório de testes e cobertura

O dono do repositório delega o ciclo inteiro (código, PR, CI, merge) e precisa de uma medida, não de uma impressão, de quanto a suíte protege o produto. Esta skill roda todas as suítes com cobertura e escreve um relatório HTML no design system do app, mais um report.json para leitura por máquina.

O gerador só lê o que as suítes escreveram. Rodar a suíte é responsabilidade desta skill: o mesmo script serve para Windows, Linux e para o artefato baixado do CI.

1. Rodar as suítes

Na raiz do repositório (ou da worktree). Não pare no primeiro vermelho: o relatório existe justamente para mostrar a falha.

Kotlin (domínio, dados, view models, UI, terminal, arquitetura):

# Linux/macOS — `bash ./gradlew`, nunca `chmod +x`: o gradlew está no git sem o bit de execução
bash ./gradlew desktopTest --rerun -Pcoverage -PtestForks=4
bash ./gradlew koverXmlReport -Pcoverage
:: Windows
gradlew.bat desktopTest --rerun -Pcoverage -PtestForks=4
gradlew.bat koverXmlReport -Pcoverage
  • desktopTest, e não allTests: no alvo único JVM os dois rodam a mesma suíte, mas --rerun só vale para a tarefa nomeada. Sem ele o build cache (org.gradle.caching=true) devolve XML de uma passada antiga e o relatório descreve outro código.
  • -PtestForks=4 só com ~/.skiko já populado (ver CLAUDE.md). Cache frio: -PtestForks=1.
  • Sem display (SSH, contêiner): prefixe xvfb-run -a. Parte dos testes consulta o GraphicsEnvironment.
  • Medido em 2026-10-22, Linux, 16 processadores, 4 forks: ~55 s de suíte mais ~5 s de Kover.

Servidor de time (server/, vitest + supertest):

cd server && npm ci && npm run test:coverage

test:coverage escreve test-results/junit.xml e coverage/coverage-summary.json (v8 sobre src/).

2. Gerar o relatório

node .claude/skills/usage-monitor-test-report/scripts/build-test-report.mjs
  • Saída: build/test-report/index.html e build/test-report/report.json (pasta ignorada pelo git).
  • Imprime um resumo no console e sai com 1 quando algum portão bloqueia (suíte não rodou, falha, regra de arquitetura quebrada). Quem automatiza decide pelo código de saída.
  • Opções: --root <repo> (padrão: diretório atual) e --out <pasta relativa>.
  • --platform win32|linux|darwin troca a plataforma do cabeçalho (padrão: a da máquina que gera).
  • --ci só no CI: lá o desktopTest pode vir do build cache (FROM-CACHE) com o carimbo da execução original, e o portão "Resultado do código atual" deixa de comparar horário com o commit.
  • Todo run do CI em que a suíte do desktop roda já gera este relatório: job test-report do ci.yml, com a suíte do Windows e a do servidor. O HTML fica no artefato test-report (14 dias) e os portões no resumo do run. Para ler o de um PR sem rodar nada: gh run download <run-id> -n test-report -D build/test-report-ci. Rodar localmente continua valendo antes do push, porque o CI só responde depois dele.

Read the full file on GitHub · 109 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. yesterday First seen · 109 lines · 0 tokens per session scan A 1ef47bbd0905

Subscribe to this mod's changes

usage-monitor-test-report is a skill published in the GitHub repository edilsonvilarinho/usage-monitor (16 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 1,855 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 2026-10-24.