postmortem

A tool for reading and maintaining incident postmortems—documents that record what happened, why it happened, and how to prevent a repeat.

In plain words
What is it for?
Reading the latest postmortem for an incident and, during the dedicated generation step, writing or updating its complete Markdown document.
Why use it?
It keeps the current postmortem available during an investigation and preserves earlier versions when a new one is saved.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/arvo-ai/aurora/postmortem
Any agent
npx skills add Arvo-AI/aurora --skill postmortem
Clone the repo
git clone --depth 1 https://github.com/Arvo-AI/aurora

Made for: Claude Code, Codex.

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 650 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00023 $0.00650
Opus 5 $0.00012 $0.00325
Sonnet 5 $0.00005 $0.00130
Haiku 4.5 $0.00002 $0.00065

Measured 3d ago against content hash ad3409a09384, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

server/chat/backend/agent/skills/integrations/postmortem/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Postmortem Tools

Overview

Core tools for reading postmortem documents during investigation, and writing them during the dedicated "Generate Postmortem" action. get_postmortem is available in all sessions. save_postmortem is only available during the "Generate Postmortem" action — not during RCA.

Tools

get_postmortem(incident_id)

Read the current postmortem for an incident. Returns markdown content, generated_at, and updated_at timestamps. Returns status: "not_found" if no postmortem exists yet. Only the latest version is returned; historical versions are browsable in the UI but not via this tool.

save_postmortem(incident_id, content)

Write or update a postmortem. Only available during the "Generate Postmortem" action — not during RCA. Each save automatically snapshots the previous content as a version for history tracking. Content must be complete markdown — partial updates are not supported. Max 100,000 characters.

Workflow

  1. Call get_postmortem — if a prior version exists, use it as a baseline to preserve structure and confirmed facts
  2. Gather context from RCA summary and connected communication platforms (Slack, etc.)
  3. Write structured markdown following the output format below
  4. Call save_postmortem

Output Format

Always generate postmortems with these sections in order:

# Postmortem: <Incident Title>

**Date:** YYYY-MM-DD HH:MM UTC
**Duration:** Xh Ym
**Severity:** critical/high/medium/low
**Service:** <service name>

## Summary
2-3 sentences describing what happened.

## Timeline
- **HH:MM UTC** - Event description
- **HH:MM UTC** - Event description

## Root Cause
Technical explanation of what failed and why.

## Impact
Services, users, SLAs, and data affected.

## Contributing Factors
Human/process factors: deployment pressure, alert fatigue, communication gaps, handoff confusion.
Only include if evidence exists from conversations.

## Resolution
How the incident was resolved or mitigated.

## Action Items
- [ ] Concrete follow-up item
- [ ] Another follow-up item

## Lessons Learned
What can prevent similar incidents in the future.

Read the full file on GitHub · 84 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. 3d ago First seen · 84 lines · 23 tokens per session scan A ad3409a09384

Subscribe to this mod's changes

postmortem is a skill published in the GitHub repository Arvo-AI/aurora (401 stars, last pushed 5d ago), licensed Apache-2.0. It adds 23 tokens to every session and 650 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 2026-08-30.

Related

Other skills, from other repositories