pre-mortem

pre-mortem is a skill for Claude Code from aniganti/pm-superpowers. It costs 71 tokens per session (2,018 once invoked), scanned A, original, MIT.

A structured exercise that imagines a product launch has failed and asks what went wrong. A pre-mortem is a planning review done before an event, so risks can be addressed early.

In plain words
What is it for?
Use it to review a launch plan or product description, identify likely causes of failure, research relevant outside risks, and improve launch readiness.
Why use it?
It gives a team a way to discuss risks and unspoken concerns before launch rather than discovering them afterward. It separates serious risks from exaggerated worries.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the pm-superpowers plugin — 12 skills, 1 agent shipped together

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/aniganti/pm-superpowers/pre-mortem
Any agent
npx skills add aniganti/pm-superpowers --skill pre-mortem
Clone the repo
git clone --depth 1 https://github.com/aniganti/pm-superpowers

Made for: Claude Code.

Or install pm-superpowers, the plugin that ships this one along with the rest of its 12 skills, 1 agent.

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/skills/aniganti/pm-superpowers/pre-mortem.svg)](https://agentmods.dev/skills/aniganti/pm-superpowers/pre-mortem)
Your own site
<a href="https://agentmods.dev/skills/aniganti/pm-superpowers/pre-mortem"><img src="https://agentmods.dev/badge/skills/aniganti/pm-superpowers/pre-mortem.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,018 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 5.1 $0.00071 $0.02018
Opus 5 $0.00036 $0.01009
Sonnet 5 $0.00014 $0.00404
Haiku 4.5 $0.00007 $0.00202

Measured 6d ago against content hash 5a1aa0dab8df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

plugins/pm-superpowers/skills/pre-mortem/SKILL.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pre-Mortem Risk Analysis

The goal of a pre-mortem is to improve launch readiness, not assign blame. You are helping the PM stress-test their product or launch plan by imagining failure before it happens — so the team can prevent it.

Process

1. Gather Context

Read the PRD or launch plan. The PM may provide:

  • A file path to a PRD or launch plan document
  • A URL to a document
  • A verbal description of the product and launch

If no document is provided, ask the PM to describe:

  • What is the product or feature?
  • Who is the target user?
  • What is the launch timeline?
  • What does success look like (metrics, adoption targets, revenue goals)?

2. Research (If Relevant)

Use web search to research the competitive landscape, market conditions, or any external factors that could affect the launch. This is especially important if the product is entering a crowded market or a regulated industry.

3. Think Step by Step

Work through the following thought exercise carefully:

  • Imagine the product launches in 14 days.
  • Now imagine it fails — customers do not adopt, revenue targets miss, reputation takes a hit.
  • What went wrong? What did we miss? What were we overconfident about?

Consider failure across multiple dimensions:

  • Product quality and completeness
  • User experience and onboarding
  • Go-to-market and positioning
  • Technical reliability and scalability
  • Competitive response
  • Internal alignment and resourcing
  • Regulatory or compliance gaps
  • Customer support readiness
  • Data and analytics instrumentation
  • Pricing and packaging

4. Categorize Risks

Sort every identified risk into one of three categories:

  • Tigers — Real problems based on evidence, past experience, or clear logic. These should keep you up at night. They require action.
  • Paper Tigers — Problems others might worry about, but are unlikely or overblown given the evidence. Worth documenting to align stakeholders and reduce anxiety. Not worth significant resource investment.
  • Elephants — Unspoken concerns the team is not discussing enough. Could be real; uncertain. They deserve investigation before launch.

Read the full file on GitHub · 192 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. 6d ago First seen · 192 lines · 71 tokens per session scan A 5a1aa0dab8df

Subscribe to this mod's changes

pre-mortem is a skill published in the GitHub repository aniganti/pm-superpowers (47 stars, last pushed 22d ago), licensed MIT. It adds 71 tokens to every session and 2,018 once invoked, about $0.0004 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens