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 skills add pwdev-solucoes/pwdev-claude-marketplace --skill observabilitygit clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplaceWrote 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/pwdev-solucoes/pwdev-claude-marketplace/observability)<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/observability"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/observability/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/pwdev-solucoes/pwdev-claude-marketplace/observability"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/observability.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 | $0.00082 | $0.00919 |
| Opus 5 | $0.00041 | $0.00460 |
| Sonnet 5 | $0.00016 | $0.00184 |
| Haiku 4.5 | $0.00008 | $0.00092 |
Grade A, and why
observability 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 6d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Observability
Você projeta o que é medido. Alerta ruim treina o time a ignorar alerta.
Princípio central
Todo alerta precisa ter uma ação. Alerta que não gera ação vira ruído, e ruído faz o time perder o alerta que importava.
Os três métodos
| Método | Para | Sinais |
|---|---|---|
| Golden Signals | serviço voltado ao usuário | latência, tráfego, erro, saturação |
| RED | request-driven (API, web) | Rate, Errors, Duration |
| USE | recurso (CPU, disco, rede) | Utilization, Saturation, Errors |
Comece por RED na borda e USE na infra. Golden Signals é a união dos dois.
PromQL — o essencial
# taxa de erro 5xx
sum(rate(http_requests_total{status=~"5.."}[5m]))
/ sum(rate(http_requests_total[5m]))
# p95 de latência
histogram_quantile(0.95, sum(rate(http_request_duration_seconds_bucket[5m])) by (le))
# saturação de memória do pod vs. limite
container_memory_working_set_bytes / container_spec_memory_limit_bytes
rate() sempre com janela ≥ 4× o intervalo de scrape. Janela curta demais
produz gráfico com buraco.
Alerta que presta
- alert: TaxaDeErroAlta
expr: |
sum(rate(http_requests_total{status=~"5.."}[5m]))
/ sum(rate(http_requests_total[5m])) > 0.05
for: 10m # evita alarme por pico momentâneo
labels: { severity: critical }
annotations:
summary: "Taxa de erro em {{ $labels.service }} acima de 5%"
runbook: "https://.../runbook-erro-5xx"
Todo alerta precisa de: for (evita flapping), severidade, e link do runbook.
Alerta sem runbook é alerta que acorda alguém sem dizer o que fazer.
SLO
SLI: o que se mede (ex.: % de requests < 300ms)
SLO: a meta (ex.: 99,5% em 30 dias)
Error budget: 100% − SLO (ex.: 0,5% ≈ 3h36 por mês)
Error budget é a ferramenta de decisão: enquanto sobra orçamento, a equipe pode lançar; quando acaba, congela e estabiliza. SLO sem consequência é enfeite.
Não proponha SLO de 99,99% sem discutir custo. Cada nove multiplica o investimento.
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.
- 6d ago First seen · 101 lines · 82 tokens per session scan A bad44ae933d9
observability is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 82 tokens to every session and 919 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…