Skip to main content
command CX Codex

pre-mortem — Claude Code command: risks and installation

The pre-mortem command stress-tests a PRD, launch plan, or feature before release by finding failure risks and turning them into follow-up actions.

MIT ★ 28,211 updated 2026-10-16

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add phuryn/pm-skills
/plugin install pm-execution@pm-skills
Open on GitHub

What pre-mortem does

pre-mortem asks Claude Code to assume that a launch failed, then trace the likely causes. It checks technical, user, business, operational, and dependency risks, covering issues such as integrations, adoption, support load, and cross-team handoffs.

The command sorts findings into Tigers, Paper Tigers, and Elephants. Tigers receive a launch priority and a concrete response; Paper Tigers get an explanation of why they are manageable; Elephants surface uncomfortable topics that the team has avoided. The output is a Markdown report with risk tables, owners, deadlines, monitoring triggers, and a go/no-go checklist.

You can provide a PRD, feature specification, launch plan, project brief, or plain-language description. More detail gives the analysis more substance. A rollout without a rollback plan leaves one checklist item unresolved.

What it helps with

  • trace likely causes of a failed launch
  • separate material risks from exaggerated concerns
  • surface risks the team avoids discussing
  • assign owners and responses to launch blockers
  • turn findings into a go/no-go checklist

Example prompts for the agent

  • Run /pre-mortem on this PRD and group the findings by risk category.
  • Use /pre-mortem for our self-serve billing portal launch and classify the findings as Tigers, Paper Tigers, or Elephants.
  • Apply /pre-mortem to this feature brief, then produce the Markdown report with mitigations and owners.

How to install pre-mortem

1Plugin marketplace

/plugin marketplace add phuryn/pm-skills
/plugin install pm-execution@pm-skills

2Manually: put the files in place

.claude/commands/pre-mortem.md

Call it with /pre-mortem. For all projects use ~/.claude/commands/

Questions about pre-mortem

How do I install pre-mortem in Claude Code?

Run /plugin marketplace add phuryn/pm-skills, then /plugin install pm-execution@pm-skills. The command file is .claude/commands/pre-mortem.md.

What does pre-mortem do?

It treats the launch as a failed event, works backward to identify causes, and groups them into Tigers, Paper Tigers, and Elephants. It then prepares a Markdown risk report and launch checklist.

What input can pre-mortem analyze?

It accepts a PRD, feature spec, launch plan, project brief, or a plain description of the work.

Source text

pre-mortem.md · MIT
---
description: Run a pre-mortem risk analysis on a PRD, launch plan, or feature — identify what could go wrong before it does
argument-hint: "<PRD, plan, or feature description>"
---

# /pre-mortem -- Pre-Launch Risk Analysis

Imagine your launch has failed. Now work backward to figure out why. This command applies the Tigers/Paper Tigers/Elephants framework to surface real risks and create mitigation plans.

## Invocation

```
/pre-mortem [paste or upload a PRD, launch plan, or feature spec]
/pre-mortem We're launching a self-serve billing portal next month
```

## Workflow

### Step 1: Accept the Plan

Accept in any format: PRD, feature spec, launch plan, project brief, or verbal description. The more detail provided, the sharper the risk analysis.

### Step 2: Risk Identification

Apply the **pre-mortem** skill:

Imagine the product has launched and failed. Generate risks across categories:
- **Technical**: Performance, scalability, integration failures, data issues
- **User**: Adoption barriers, usability problems, unmet expectations
- **Business**: Revenue impact, competitive response, market timing
- **Operational**: Support load, documentation gaps, training needs
- **Dependencies**: Third-party services, cross-team handoffs, regulatory

### Step 3: Classify Risks

Categorize each risk:

**Tigers** — Real, substantive risks that could cause failure
- Assess severity: Launch-blocking / Fast-follow / Track
- For launch-blocking Tigers: immediate mitigation required
- For fast-follow Tigers: plan to address within first sprint post-launch
- For track Tigers: monitor but don't delay launch

**Paper Tigers** — Risks that feel scary but are overblown
- Explain why the concern is manageable
- Note what would need to change for this to become a real Tiger

**Elephants** — Unspoken risks the team knows about but avoids discussing
- Surface political, organizational, or uncomfortable risks
- Frame constructively with suggested conversation starters

### Step 4: Generate Pre-Mortem Report

```
## Pre-Mortem: [Feature/Launch]

**Date**: [today]
**Status**: [Draft / Reviewed]

### Risk Summary
- **Tigers**: [count] ([launch-blocking], [fast-follow], [track])
- **Paper Tigers**: [count]
- **Elephants**: [count]

### Launch-Blocking Tigers
| # | Risk | Likelihood | Impact | Mitigation | Owner | Deadline |
|---|------|-----------|--------|-----------|-------|----------|

### Fast-Follow Tigers
| # | Risk | Likelihood | Impact | Planned Response | Owner |
|---|------|-----------|--------|-----------------|-------|

### Track Tigers
[Risks to monitor post-launch with trigger conditions]

### Paper Tigers
[Concerns that seem big but are manageable — with reasoning]

### Elephants in the Room
[Uncomfortable truths the team should discuss]

### Go/No-Go Checklist
- [ ] All launch-blocking Tigers mitigated
- [ ] Fast-follow plan documented and assigned
- [ ] Monitoring in place for Track Tigers
- [ ] Rollback plan defined
- [ ] Support team briefed
```

Save as markdown.

### Step 5: Offer Next Steps

- "Want me to **update the PRD** with risk mitigations?"
- "Should I **create test scenarios** for the riskiest areas?"
- "Want me to **draft a launch checklist** from these findings?"

## Notes

- The best pre-mortems happen when the plan is 80% done — early enough to change course, late enough to have substance
- Push past the obvious risks — the most dangerous risks are the ones nobody mentions
- Elephants are the highest-value output — surfacing what the team avoids discussing
- For each Tiger, the mitigation should be specific and assignable, not "be careful"
- If the pre-mortem reveals too many launch-blocking Tigers, recommend delaying or phasing the launch

© Paweł Huryn · MIT · phuryn/pm-skills

Similar slash commands

All slash commands for Notes, tasks and projects →

From the same set120

The whole set →
write-prd write-prd generates a lean Product Requirements Document from a brief idea, customer request, or uploaded problem summary. CX Codex +1 ★ 28,211repo stars competitive-analysis The competitive-analysis slash command maps a market, compares direct and indirect competitors, and surfaces ways to position a product differently. CX Codex +1 ★ 28,211repo stars plan-okrs plan-okrs generates three OKR sets that connect team goals to company strategy. Each OKR pairs a qualitative objective with three to five measurable key results. CX Codex +1 ★ 28,211repo stars analyze-feedback analyze-feedback processes reviews, NPS surveys, and support tickets into structured markdown reports with sentiment metrics and recurring themes. CX Codex +1 ★ 28,211repo stars stakeholder-map stakeholder-map — a command that maps stakeholders on a Power × Interest grid and builds a communication plan. Use it when a project affects different groups and you need to ensure each receives the right information at the right time. CX Codex +1 ★ 28,211repo stars battlecard Generates a concise, sales-focused competitive battlecard comparing two products. Useful before prospect calls to align pricing rebuttals and differentiators. CX Codex +1 ★ 28,211repo stars write-stories write-stories is a Claude Code command that turns a feature brief or PRD into backlog items with acceptance criteria. Choose user stories, job stories, or WWA. CX Codex +1 ★ 28,211repo stars analyze-test analyze-test is a Claude Code command that evaluates A/B test results, checks statistical significance and sample size, and recommends whether to ship, extend, or stop. CX Codex +1 ★ 28,211repo stars

Project sponsors

Companies that keep this analytics open