agentmods.dev

postmortem

postmortem is a skill for Claude Code from bouob/sysadmin-skills. It costs 209 tokens per session (2,094 once invoked), scanned A, original, MIT.

A structured report about a resolved production incident, outage, or failure. It follows a blameless approach, which looks for system conditions that enabled the problem instead of blaming individuals.

In plain words
What is it for?
Use it to record what happened, identify contributing factors, and define improvements after an outage or other production failure.
Why use it?
It turns a failure into documented learning and follow-up work. This helps teams address underlying causes rather than only restoring service.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the sysadmin-skills plugin — 9 skills shipped together

not rated 2repo 6mo ago A scan 209 tokens original MIT

Good fit Use it to record what happened, identify contributing factors, and define improvements after an outage or other production failure.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bouob/sysadmin-skills/postmortem
View source ↗ bouob/sysadmin-skills
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 bouob/sysadmin-skills --skill postmortem
Clone the repo
git clone --depth 1 https://github.com/bouob/sysadmin-skills

Made for: Claude Code.

Or install sysadmin-skills, the plugin that ships this one along with the rest of its 9 skills.

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/skills/bouob/sysadmin-skills/postmortem/github.svg)](https://agentmods.dev/skills/bouob/sysadmin-skills/postmortem)
Your own site
<a href="https://agentmods.dev/skills/bouob/sysadmin-skills/postmortem"><img src="https://agentmods.dev/badge/skills/bouob/sysadmin-skills/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/skills/bouob/sysadmin-skills/postmortem"><img src="https://agentmods.dev/badge/skills/bouob/sysadmin-skills/postmortem.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 209 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,094 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 $0.00209 $0.02094
Opus 5.5 $0.00084 $0.00838
Sonnet 5.5 $0.00042 $0.00419
Haiku 4.5 $0.00021 $0.00209

Measured 2mo ago against content hash 54c00f292a06, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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.

skills/postmortem/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Blameless Postmortem Workflow

Structured post-incident learning following Google SRE blameless postmortem culture. Produces a postmortem document that focuses on systemic contributing factors and actionable improvements — not individual blame.

  • itil — reads references/sre-integration.md for blameless culture principles and error budget context
  • done-ops — confirmation that the incident is fully resolved before starting the postmortem

Blameless Culture — Why It Matters

Traditional post-incident reviews can become blame-focused, which creates incentives to hide mistakes. Blameless postmortems assume:

Everyone involved was acting in good faith with the information and tools available to them at the time.

The goal is to find what made the failure possible at the system level — and fix those things. People don't fail; systems create conditions where failures become likely.

For full blameless culture guidance, read references/blameless-templates.md.

Output

File: {OUTPUT_DIR}/postmortem-{YYYY-MM-DD}-{slug}.md

  • slug: kebab-case summary of the incident, e.g. payment-api-timeout, auth-service-outage
  • Link to the incident report if one exists from the /incident skill

Default output directory: ./postmortems/. If a docs/postmortems/ directory exists, use that instead.

All postmortem documents are written in English. Preview for the user in their preferred language before writing.

When to Use Each Review Type

Situation Use
SEV-1 or SEV-2 incident, regardless of root cause /postmortem (mandatory)
SEV-3 with complex contributing factors /postmortem (recommended)
Root cause unknown, likely to recur /problem (for technical tracking) + /postmortem (for learning)
Formal compliance/regulatory PIR required Traditional ITIL PIR (can run alongside /postmortem)
Sprint retrospective Use team's agile retro format — not this skill

Read the full file on GitHub · 201 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago First seen · 201 lines · 209 tokens per session scan A 54c00f292a06

Subscribe to this mod's changes

postmortem is a skill published in the GitHub repository bouob/sysadmin-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 209 tokens to every session and 2,094 once invoked, about $0.0008 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 2026-08-31.

Claude CodeWriting and docschange-managementclaude-code-pluginincident-responseitilitsm
Related

postmortem compared with skills from other repositories

postmortem next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
postmortembouob/sysadmin-skillsSkill26mo agoMITA209Claude Code
servicenow-change-managementKnuckles-Team/servicenow-apiSkill20yesterdayMITA137Claude Code, Codex
binary-analysisDeepBitsTechnology/claude-pluginsSkill493mo agoApache-2.0A132Claude Code
kernel-cve-analysisDeepBitsTechnology/claude-pluginsSkill493mo agoApache-2.0A136Claude Code
pace-changearch-team/devpaceSkill736mo agoMITA124Claude Code
pace-releasearch-team/devpaceSkill736mo agoMITA54Claude Code
pace-retroarch-team/devpaceSkill736mo agoMITA117Claude Code