An incident-response workflow for an outage or other active production problem. It preserves logs and other evidence, investigates possible causes, and proposes a mitigation such as a rollback.

It is for triaging incidents, recording what changed and who is affected, saving Kubernetes evidence, testing hypotheses, proposing reversible mitigations, and preparing a postmortem.

It helps teams restore service while keeping enough evidence to understand what happened later. Changes require human confirmation, so an urgent response does not become an uncontrolled one.

incidente — Command for Claude Code by pwdev-solucoes

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add pwdev-solucoes/pwdev-claude-marketplace

Claude Code

/plugin install pwdev-devops

Made for: Claude Code.

Or install pwdev-devops, the plugin that ships this one along with the rest of its 19 skills, 5 commands, 4 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/pwdev-solucoes/pwdev-claude-marketplace/incidente/github.svg)](https://agentmods.dev/commands/pwdev-solucoes/pwdev-claude-marketplace/incidente)

Your own site

<a href="https://agentmods.dev/commands/pwdev-solucoes/pwdev-claude-marketplace/incidente"><img src="https://agentmods.dev/badge/commands/pwdev-solucoes/pwdev-claude-marketplace/incidente/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/pwdev-solucoes/pwdev-claude-marketplace/incidente"><img src="https://agentmods.dev/badge/commands/pwdev-solucoes/pwdev-claude-marketplace/incidente.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 368 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.

Model	Per session	Once invoked
Fable 5.1	$0.00019	$0.00368
Opus 5	$0.00010	$0.00184
Sonnet 5	$0.00004	$0.00074
Haiku 4.5	$0.00002	$0.00037

Measured 6d ago against content hash 581532303467, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

incidente 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.

plugins/pwdev-devops/commands/incidente.md · 41 lines

What it actually says

/pwdev-devops:incidente

STEP 0 — Idioma e ambiente

${CLAUDE_PLUGIN_ROOT}/references/language.md. Confirme conta e contexto.

STEP 1 — Triagem (5 min)

O que mudou? deploy, config, certificado, cota, DNS — a causa está aqui na maioria dos casos
Quando começou?
Quem é afetado?
Está piorando?
Existe mitigação rápida — rollback, flag, escala?

STEP 2 — Preservar evidência ANTES de mitigar

kubectl logs POD --previous > /tmp/inc-$(date +%s).log
kubectl describe pod POD > /tmp/inc-describe.txt
kubectl get events -n NS --sort-by=.lastTimestamp > /tmp/inc-events.txt

Restart sem salvar log destrói a única cópia da causa.

STEP 3 — Investigar

Spawn do incident-commander. Trilha: borda → app → dependência → infra.

STEP 4 — Mitigar

Restaurar vem antes de entender. Rollback é mitigação legítima. Mesmo em incidente, mutação exige confirmação — apresente comando, efeito e reversão.

STEP 5 — Verificar e registrar

Sintoma sumiu? Linha do tempo registrada?

STEP 6 — Postmortem

platform-docs gera o esboço. Sem culpado — "erro humano" não é causa raiz; a pergunta é por que o sistema permitiu.

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.

6d ago First seen · 41 lines · 19 tokens per session scan A 581532303467

Subscribe to this mod's changes

incidente is a command published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 19 tokens to every session and 368 once invoked, about $0.0001 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.

Containers Debugging DevOps and cloud

incidente