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.
curl -O https://raw.githubusercontent.com/edilsonvilarinho/usage-monitor/main/.claude/skills/usage-monitor-test-report/SKILL.mdgit clone --depth 1 https://github.com/edilsonvilarinho/usage-monitorWrote 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/edilsonvilarinho/usage-monitor/usage-monitor-test-report)<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.
<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>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 | $0.00076 | $0.01855 |
| Opus 5.5 | $0.00030 | $0.00742 |
| Sonnet 5.5 | $0.00015 | $0.00371 |
| Haiku 4.5 | $0.00008 | $0.00186 |
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.
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 — 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 nãoallTests: no alvo único JVM os dois rodam a mesma suíte, mas--rerunsó 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=4só com~/.skikojá populado (ver CLAUDE.md). Cache frio:-PtestForks=1.- Sem display (SSH, contêiner): prefixe
xvfb-run -a. Parte dos testes consulta oGraphicsEnvironment. - 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.htmlebuild/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|darwintroca a plataforma do cabeçalho (padrão: a da máquina que gera).--cisó no CI: lá odesktopTestpode 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-reportdoci.yml, com a suíte do Windows e a do servidor. O HTML fica no artefatotest-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.
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.
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.
- yesterday First seen · 109 lines · 0 tokens per session scan A 1ef47bbd0905
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.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
react-patterns
React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.
golang-testing
Go testing best practices including table-driven tests, test helpers, benchmarking, race detection, coverage analysis, and integration testing patterns. Use when writing or improving Go tests.
cli-eval
Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.
verification-loop
A comprehensive verification system for Claude Code sessions. Use when verifying a Claude Code session's work before claiming it is complete.
qa-test-planner
Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.