pre-mortem

pre-mortem is a command for coding agents from phuryn/pm-skills. It costs 27 tokens per session (864 once invoked), scanned A, original, MIT.

A pre-launch risk review that imagines a product or project has failed and works backward to identify possible causes. It examines technical, user, business, operational, dependency, and regulatory risks.

In plain words
What is it for?
Use it to review a product requirement document, feature plan, launch plan, project brief, or verbal idea before committing to it.
Why use it?
It helps reveal problems while changes are still affordable, before they become launch failures. It also separates serious risks from less important concerns and suggests ways to reduce them.

Command

Part of the pm-execution plugin — 16 skills, 11 commands shipped together

About the project

phuryn/pm-skills is a marketplace of reusable skills, commands, and plugins that guide AI assistants through product-management work such as discovery, strategy, planning, metrics, launches, and growth. It is for product managers and teams using Claude Code, Cowork, or compatible assistants. The catalogue entries are the project's own workflows and extensions.

phuryn/pm-skills · 25,964 stars · on GitHub

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 commands/phuryn/pm-skills/pre-mortem
Clone the repo
git clone --depth 1 https://github.com/phuryn/pm-skills

Or install pm-execution, the plugin that ships this one along with the rest of its 16 skills, 11 commands.

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 pre-mortem

README.md
[![agentmods](https://agentmods.dev/badge/commands/phuryn/pm-skills/pre-mortem.svg)](https://agentmods.dev/commands/phuryn/pm-skills/pre-mortem)
Your own site
<a href="https://agentmods.dev/commands/phuryn/pm-skills/pre-mortem"><img src="https://agentmods.dev/badge/commands/phuryn/pm-skills/pre-mortem.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 864 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 $0.00027 $0.00864
Opus 5 $0.00014 $0.00432
Sonnet 5 $0.00005 $0.00173
Haiku 4.5 $0.00003 $0.00086

Measured 5d ago against content hash 48bd6de2d7c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pre-mortem 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

pm-execution/commands/pre-mortem.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/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

Read the full file on GitHub · 105 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 · 105 lines · 27 tokens per session scan A 48bd6de2d7c4

Subscribe to this mod's changes

pre-mortem is a command published in the GitHub repository phuryn/pm-skills (25,964 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 864 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.