postmortem

postmortem is a command for Claude Code from luanpdd/kit-mcp. It costs 50 tokens per session (2,317 once invoked), scanned A, original, MIT.

A command for writing a blameless incident postmortem, which is a record of what happened, why it happened, and what should change. It can use an existing investigation or guide you through questions from scratch.

In plain words
What is it for?
Use it to document production incidents, near-misses, triggers, root causes, impact, severity, and corrective actions.
Why use it?
It turns incident findings into a reviewable document and concrete follow-up tasks, so lessons are not lost after an outage or near-miss.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; positional $N argument.

Good fit Use it to document production incidents, near-misses, triggers, root causes, impact, severity, and corrective actions.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/luanpdd/kit-mcp/postmortem
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.

Clone the repo
git clone --depth 1 https://github.com/luanpdd/kit-mcp

Made for: Claude Code.

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 postmortem

README.md
[![agentmods](https://agentmods.dev/badge/commands/luanpdd/kit-mcp/postmortem/github.svg)](https://agentmods.dev/commands/luanpdd/kit-mcp/postmortem)
Your own site
<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/postmortem"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/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 postmortem

Your own site · 80×15
<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/postmortem"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/postmortem.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,317 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 $0.00050 $0.02317
Opus 5 $0.00025 $0.01158
Sonnet 5 $0.00010 $0.00463
Haiku 4.5 $0.00005 $0.00232

Measured 5d ago against content hash c0f1ae7530e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

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 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.

kit/commands/postmortem.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cria/Atualiza:

  • .planning/postmortems/<id>.md — postmortem blameless completo

Após: o user tem postmortem revisável + action items concretos. Phase 40 INT-FW-V2-01 chained do /forense automaticamente após Core Analysis Loop fechar.

Modo A: --from-investigation <id> (preferido — continuação de v1.9)

.planning/investigations/<id>.md produzido pelo incident-investigator (v1.9 — Core Analysis Loop). Extrai automaticamente: trigger, root cause, hipóteses validadas, action items. Campos faltantes (impact quantificado, severity, autores) são perguntados via AskUserQuestion.

Modo B: --incident "<descrição>" (standalone)

Para postmortem sem investigation prévia (incident menor, near-miss, lições retrospectivas). Agent gera template e usa AskUserQuestion para 9 perguntas guiadas — uma por seção canônica.

Flags adicionais:

  • --severity <SEV1|SEV2|SEV3> — severity do incident (default: AskUserQuestion)
  • --output <path> — caminho do postmortem (default: .planning/postmortems/<id>.md — id auto-gerado)

Exemplos:

/postmortem --from-investigation incident-2026-05-06-1432-checkout-burn   # Modo A
/postmortem --incident "checkout SLO burn às 14:32 — RCA N+1 query orders" --severity SEV2  # Modo B
/postmortem --incident "near-miss: deploy bloqueou 2min antes do PR-1234"                    # near-miss

Pré-requisito (Modo A): arquivo .planning/investigations/<id>.md existe (criado por /investigar-producao ou /forense).

1. Parsear argumentos (2 modos)

INV_ID=$(echo "$ARGUMENTS" | grep -oE -- '--from-investigation [^ ]+' | awk '{print $2}')
INCIDENT=$(echo "$ARGUMENTS" | grep -oE -- '--incident "[^"]+"' | sed 's/--incident //; s/^"//; s/"$//')
SEVERITY=$(echo "$ARGUMENTS" | grep -oE -- '--severity [^ ]+' | awk '{print $2}')
OUTPUT_PATH=$(echo "$ARGUMENTS" | grep -oE -- '--output [^ ]+' | awk '{print $2}')

# PT-BR: validar mutuamente exclusivos
if [ -n "$INV_ID" ] && [ -n "$INCIDENT" ]; then
  echo "✗ Erro: --from-investigation e --incident são mutuamente exclusivos. Escolha um."
  exit 1
fi

# PT-BR: se nenhum dos 2 → AskUserQuestion (Modo C — interativo)
if [ -z "$INV_ID" ] && [ -z "$INCIDENT" ]; then
  # Listar investigations recentes para sugestão
  RECENT_INVS=$(ls -t .planning/investigations/*.md 2>/dev/null | head -5 | while read f; do basename "$f" .md; done | tr '\n' ',')
  # AskUserQuestion: "Modo? Continuar de investigation existente OU postmortem standalone?"
  # Opções: Continuar de <ID> (uma por investigation recente) | Standalone (texto livre)
  echo "ℹ Sem flag explícita. Use --from-investigation <id> ou --incident \"<descrição>\"."
  [ -n "$RECENT_INVS" ] && echo "  Investigations recentes: $RECENT_INVS"
  exit 1
fi

Read the full file on GitHub · 180 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. 5d ago First seen · 180 lines · 50 tokens per session scan A c0f1ae7530e7

Subscribe to this mod's changes

postmortem is a command published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 2,317 once invoked, about $0.0003 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.