ai-postmortemlisted

# Postmortem ## Purpose Structured incident postmortem using the DERP model. Guides through Detection, Escalation, Recovery, and Prevention phases with targeted questions. Produces blameless, actionable postmortem documents. ## Trigger - Command: `/ai-postmortem start|continue|find|generate` - Context: incident occurred, production failure, outage resolution, near-miss analysis. ## Workflow Four modes follow the DERP loop: 1. `start` — scaffold a new postmortem under `.ai-engineering/postmortems/PM-YYYY-NNN.md` from the template; pose Detection-phase questions. 2. `continue <id>` — resume an in-progress postmortem; advance through Escalation → Recovery → Prevention. 3. `generate` — synthesize from existing session context (recent commits, alerts, logs). 4. `find [query]` — search past postmortems for similar patterns. ## Modes ### start -- New postmortem 1. **Assign ID** -- generate `PM-YYYY-NNN` (sequential within year). 2. **Set status** -- `draft`. 3. **Scaffold** -- create `.ai-engineering/postmortems/{id}.md` with DERP template. 4. **Interview -- Detection**: - When was the incident first detected? - How was it detected? (monitoring, user report, manual discovery) - What was the time between incident start and detection? - What monitoring should have caught it earlier? 5. **Interview -- Escalation**: - Who was notified and when? - Was the escalation path appropriate? - Were the right people involved at the right time? 6. **Interview -- Reco