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.
npx agentmods add skills/igoruehara/spec-driven/metricasnpx skills add igoruehara/spec-driven --skill metricasgit clone --depth 1 https://github.com/igoruehara/spec-drivenWrote 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/igoruehara/spec-driven/metricas)<a href="https://agentmods.dev/skills/igoruehara/spec-driven/metricas"><img src="https://agentmods.dev/badge/skills/igoruehara/spec-driven/metricas.svg" alt="Measured on agentmods" 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 | $0.00098 | $0.01059 |
| Opus 5 | $0.00049 | $0.00530 |
| Sonnet 5 | $0.00020 | $0.00212 |
| Haiku 4.5 | $0.00010 | $0.00106 |
Grade A, and why
metricas 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Métricas de entrega (Lead Time · Throughput · CD)
Acompanha a saúde do fluxo de entrega. Idempotente: re-rodar recalcula o período. Princípio: usar para achar gargalo, não para ranquear pessoas (não incentive gaming).
Defina o período
Pergunte (AskUserQuestion) o ciclo (sprint / semana / mês) e a janela de datas.
1. Lead Time — quanto tempo até produção
Tempo de "começou" → "em produção" por item.
- Início (use o que houver): data da spec/STATE, criação da issue (Jira) ou 1º commit.
- Fim: deploy em prod — tag/release, log de CI/CD, ou status "done" do Jira.
- Calcule por item e o agregado: mediana e p85 (mais robusto que média). Quebre por tier/tipo (feature/bug) se útil.
2. Throughput — itens concluídos no ciclo
Número de itens que chegaram a "pronto"/prod no período (histórias, bugs, tarefas).
- Fontes:
specs/marcadas implementadas, PRs mergeados, issues fechadas (Jira), deploys. - Reporte o número absoluto por ciclo e a tendência (↑ / → / ↓ vs ciclo anterior).
3. Continuous Delivery vs Continuous Deployment
Avalie onde o time está e o gap:
| Prática | Definição | Pergunta de verificação |
|---|---|---|
| Continuous Delivery | toda mudança fica deployável (pipeline verde); o release é decisão de negócio (um botão) | o pipeline garante deployabilidade? há staging? |
| Continuous Deployment | toda mudança aprovada vai para prod automaticamente, sem gate manual | ainda há gate manual? quanto da pipeline é automático? |
- Reporte também a Deployment Frequency (quantos deploys no período).
- Aponte o próximo passo de automação →
/setup-ci.
4. Qualidade de código — cobertura e análise estática
Evidência rastreável do resultado (não só do fluxo). Olhe a tendência, não o número isolado — e nunca para ranquear pessoas (não incentive gaming: 100% de cobertura com testes vazios é pior que 80% honesto).
- Cobertura: % atual (global e, se útil, por módulo/camada) e a tendência vs ciclo anterior.
Fonte: relatório de cobertura da CI (artefato — ver
/setup-ci) ou<comando de cobertura>local. - Análise estática: nº de findings por severidade (type-check, complexidade/smells, SAST/segurança, duplicação) e a tendência. Fonte: relatório do CI (Sonar/CodeQL/semgrep/ruff/tsc…).
- Ligação com o gate: cobertura abaixo do mínimo ou finding bloqueante barra o merge (ver
docs/engineering/TESTING.md); o resto entra aqui como tendência a vigiar (dívida acumulando?).
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.
- 5d ago First seen · 62 lines · 98 tokens per session scan A 35a64df6611b
metricas is a skill published in the GitHub repository igoruehara/spec-driven (213 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 1,059 once invoked, about $0.0005 per session on Opus 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.
Other skills, from other repositories
import-prom-rule
Bulk import of a Prometheus alert rule YAML file (create a whole set of rules at once). Dedicated to handling a remote URL or local YAML text, automatically parsing the three formats groups / a plain rules array / a single rule. ⚠️ Do not use this skill for single-rule creation — when the user describes a single alert…
ci-security-scanning-with-strix
Add security scanning to CI/CD with Strix — GitHub Actions, GitLab CI, or any pipeline — so every pull request gets a diff-scoped AI pentest that blocks vulnerable code before it merges, with results as PR comments and SARIF uploaded to code scanning. Covers both the self-hosted open-source CLI (runs in your runner)…
chinese-git-workflow
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用，不要根据上下文自动触发。.
azsdk-common-pipeline-analysis
Analyze Azure SDK CI/CD pipeline failures into a structured diagnosis, and define the required output format. Load this skill before calling azsdkanalyzepipeline, which returns raw failure data that this skill interprets and formats. USE FOR: "pipeline failed", "build failure", "CI check failing", "tests failing in…
configure-env-variables
Configures environment variables for Power Pages site settings to support ALM across environments. Creates environment variable definitions in Dataverse, guides the user through linking site settings to those variables via the Power Pages Management app, adds the variables to the solution, and generates a…
desktop-principles
Desktop-specific UX principles - hover states, pointer precision, keyboard shortcuts, multi-window, focus management. Covers macOS, Windows, Linux, web desktop.