incident-response

incident-response is a skill for Claude Code from pwdev-solucoes/pwdev-claude-marketplace. It costs 81 tokens per session (909 once invoked), scanned A, original, Apache-2.0.

An incident investigation guide for outages, production errors, and user complaints. It takes you from observing evidence to forming and testing a cause, applying a mitigation, and writing a postmortem.

In plain words
What is it for?
Use it to triage incidents, investigate logs and metrics, plan safe rollbacks, confirm recovery, and document the root cause.
Why use it?
It reduces the risk of making an untested change that hides evidence or causes a second failure. It also gives teams a clear order for restoring service and finding the underlying cause.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the pwdev-devops plugin — 19 skills, 5 commands, 4 agents shipped together

Good fit Use it to triage incidents, investigate logs and metrics, plan safe rollbacks, confirm recovery, and document the root cause.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pwdev-solucoes/pwdev-claude-marketplace/incident-response
Install

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.

Any agent
npx skills add pwdev-solucoes/pwdev-claude-marketplace --skill incident-response
Clone the repo
git clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplace

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.

agentmods badge for incident-response

README.md
[![agentmods](https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/incident-response/github.svg)](https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/incident-response)
Your own site
<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/incident-response"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/incident-response/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 incident-response

Your own site · 80×15
<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/incident-response"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/incident-response.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 909 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 $0.00081 $0.00909
Opus 5 $0.00041 $0.00454
Sonnet 5 $0.00016 $0.00182
Haiku 4.5 $0.00008 $0.00091

Measured 7d ago against content hash 50f46d9be337, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

incident-response 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 7d 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/skills/incident-response/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Incident Response

Você conduz a investigação. Sob pressão, o método é o que impede o erro.

Princípio central

Nunca pule do sintoma para o comando. "Reinicia o pod" sem hipótese resolve por acidente e apaga a evidência da causa.

Ordem — não negociável

1. OBSERVAR    métricas, logs, eventos — só leitura
2. HIPÓTESE    o que explica TODOS os sintomas?
3. VALIDAR     leitura que confirma ou derruba
4. PROPOR      comando exato + efeito + reversão
5. CONFIRMAR   humano aprova
6. EXECUTAR    um comando por vez
7. VERIFICAR   sintoma sumiu? o que mais mudou?

Triagem — primeiros 5 minutos

Pergunta Por quê
O que mudou? deploy, config, certificado, cota, DNS — a causa está aqui em 80% dos casos
Quando começou? correlaciona com o evento
Quem é afetado? todos, ou um segmento?
Está piorando? define urgência
Existe mitigação rápida? rollback, feature flag, escala

"O que mudou?" é a primeira pergunta, sempre. Sistema que funcionava e parou raramente parou sozinho.

Mitigar antes de entender

Restaurar o serviço vem antes de descobrir a causa. Rollback é mitigação legítima — e a mais rápida.

Mas: preserve a evidência antes de mitigar.

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

Restart sem salvar log destrói a única cópia da causa.

Trilha de investigação

borda      ALB/Nginx: taxa de erro, latência, health do target
   ↓
aplicação  logs, exceptions, versão em execução
   ↓
dependência banco, cache, fila, API externa
   ↓
infra      CPU, memória, disco, rede, node

Percorra de fora para dentro. Começar pela infra é como se perde 40 minutos quando a causa era um deploy.

Postmortem

Sem culpado. O objetivo é o sistema, não a pessoa.

# Incidente {{data}} — {{título}}
Duração: {{início}} → {{fim}} ({{n}} min)
Impacto: {{quem, quanto, o quê}}
Severidade: {{n}}

## Linha do tempo
{{hora}} — {{evento}} — {{quem/o quê}}

## Causa raiz
{{o mecanismo, não "erro humano"}}

## Por que não pegamos antes
{{a lacuna de detecção — costuma ser o achado mais valioso}}

## Ações
| Ação | Tipo | Dono | Prazo |
|---|---|---|---|
| ... | prevenir \| detectar \| mitigar | ... | ... |

Read the full file on GitHub · 111 lines

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. 7d ago First seen · 111 lines · 81 tokens per session scan A 50f46d9be337

Subscribe to this mod's changes

incident-response is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed today), licensed Apache-2.0. It adds 81 tokens to every session and 909 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.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens