incident-postmortem

incident-postmortem is a skill for Claude Code, Codex from mohitagw15856/pm-claude-skills. It costs 87 tokens per session (3,591 once invoked), scanned A, original, MIT.

An incident-postmortem writing skill that documents an outage or other serious problem, including its timeline, impact, root cause, contributing factors, and follow-up actions. A postmortem is a review held after an incident to learn how to prevent a repeat.

In plain words
What is it for?
Use it for outage reports, P1 or P2 incident reviews, root-cause analysis, and other post-incident documents.
Why use it?
It turns a stressful event into a clear record without blaming individuals. It helps teams move from understanding what happened to assigning specific corrective work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for outage reports, P1 or P2 incident reviews, root-cause analysis, and other post-incident documents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mohitagw15856/pm-claude-skills/incident-postmortem
About the project

PM Skills is a collection of plain-Markdown instructions that teach AI assistants structured methods for handling professional, personal, and life-admin tasks. People use it with Claude, ChatGPT, Gemini, Cursor, Codex, and other supported agents for work such as writing product requirements, reviewing documents, or planning difficult situations.

mohitagw15856/pm-claude-skills · 1,449 stars · on GitHub · mohitagw15856.github.io

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 mohitagw15856/pm-claude-skills --skill incident-postmortem
Clone the repo
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills

Made for: Claude Code, Codex.

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-postmortem

README.md
[![agentmods](https://agentmods.dev/badge/skills/mohitagw15856/pm-claude-skills/incident-postmortem/github.svg)](https://agentmods.dev/skills/mohitagw15856/pm-claude-skills/incident-postmortem)
Your own site
<a href="https://agentmods.dev/skills/mohitagw15856/pm-claude-skills/incident-postmortem"><img src="https://agentmods.dev/badge/skills/mohitagw15856/pm-claude-skills/incident-postmortem/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-postmortem

Your own site · 80×15
<a href="https://agentmods.dev/skills/mohitagw15856/pm-claude-skills/incident-postmortem"><img src="https://agentmods.dev/badge/skills/mohitagw15856/pm-claude-skills/incident-postmortem.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,591 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 $0.00087 $0.03591
Opus 5.5 $0.00035 $0.01436
Sonnet 5.5 $0.00017 $0.00718
Haiku 4.5 $0.00009 $0.00359

Measured 2d ago against content hash 978700a3063d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

incident-postmortem 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 2d 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.

i18n/es/skills/incident-postmortem/SKILL.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill de Postmortem de Incidente

Este skill produce un documento completo de postmortem de incidente que sigue el formato estándar de la industria. El resultado aplica un enfoque sin culpables en todo el documento — brechas del sistema sobre fallos individuales — e impulsa hacia ítems de acción específicos y cerrables en lugar de compromisos de proceso vagos.

¿No es exactamente esto? Usa agent-incident-postmortem cuando un agente de IA causó el incidente (uso desenfrenado de herramientas, una alucinación enviada).

Propone Acciones

Los ítems de acción no tienen que quedarse en la página: pásalos a action-runner, que los vista previa (dry-run, valorados por riesgo), ejecuta solo lo que apruebas a través del MCP de acción conectado, y registra lo que se hizo en el brain. Típico: crear un issue de seguimiento por ítem de acción (🟡), asignado a su propietario con una fecha de vencimiento. Este skill propone; action-runner controla y ejecuta — nunca en silencio.

Dónde se ubica esto — convertir un incidente en soluciones

Tercero en la columna vertebral de respuesta ante incidentes: /slo-error-budget (marco) → /debugging-log-analyser → incident-postmortem → /oncall-runbook. Recibe el diagnóstico de causa raíz de /debugging-log-analyser (léelo en lugar de re-diagnosticar) y entrega a /oncall-runbook los factores contribuyentes e ítems de acción priorizados — y el presupuesto de error de /slo-error-budget decide cuán urgentes son esas acciones. Sin culpables, causa raíz vs factores contribuyentes e ítem de acción se definen una sola vez en docs/craft/incident-response.md; ser sin culpables es la regla que carga el peso.

El bucle

Un postmortem falla en el momento en que asigna culpa — los datos honestos se secan y cada incidente futuro es reportado insuficientemente. La Fase 1 establece ese marco; todo depende de ello.

  1. Establece el enfoque sin culpables primero. Establece claramente que esto examina el sistema que permitió que una persona competente tome esa acción, nunca la persona. Esto no es educación — es la precondición para la cronología veraz que el resto del skill necesita. Hecho cuando: el enfoque es explícito y ninguna oración en el documento culpa a un individuo; los fallos se atribuyen a brechas del sistema.
  2. Construye la cronología a partir de evidencia. Reconstruye inicio → detección → mitigación → resolución con timestamps reales (del diagnóstico y logs, no de la memoria). Detección, mitigación y resolución son eventos distintos — rastrea cada uno. Hecho cuando: la cronología tiene timestamps reales y separa detección/mitigación/ resolución, y el impacto está cuantificado (usuarios, duración, alcance).
  3. Encuentra la causa raíz Y los factores contribuyentes. La causa raíz es una sola cosa; los factores contribuyentes son lo que permitió que llegue a los usuarios y persista (la alerta perdida, el canary saltado, el runbook poco claro). Un postmortem con causa raíz y sin factores contribuyentes no ha buscado lo suficientemente. Hecho cuando: al menos se nombren los factores contribuyentes que cargan peso, cada uno apuntando a una brecha del sistema que es reparable.
  4. Impulsa hacia ítems de acción con propietario y fecha — gobernados por el presupuesto. Convierte factores en ítems de acción específicos, cada uno con propietario y fecha; los ítems vagas como "mejorar monitoreo" se deterioran. Priorízalos contra el presupuesto de error (gastado → ahora; saludable → pronto). Hecho cuando: cada ítem de acción tiene propietario y fecha, y /oncall-runbook podría convertir los aprendizajes de detección/mitigación en una entrada sin re-analizar el incidente.

Read the full file on GitHub · 249 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. 2d ago First seen · 249 lines · 87 tokens per session scan A 978700a3063d

Subscribe to this mod's changes

incident-postmortem is a skill published in the GitHub repository mohitagw15856/pm-claude-skills (1,449 stars, last pushed today), licensed MIT. It adds 87 tokens to every session and 3,591 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 2026-10-12.

Related

Other skills, from other repositories

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens