pre-mortem

A planning exercise that imagines a project has already failed, then works backward to identify the causes.

In plain words
What is it for?
Use it to find specific failure scenarios, rank the risks, and decide what preventive actions to take.
Why use it?
It brings hidden risks to light before launch, when the team can still address them.

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/tupe12334/instinct/pre-mortem
Any agent
npx skills add tupe12334/instinct --skill pre-mortem
Clone the repo
git clone --depth 1 https://github.com/tupe12334/instinct

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 2,150 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 $0.02150
Opus 5 $0.00012 $0.01075
Sonnet 5 $0.00005 $0.00430
Haiku 4.5 $0.00002 $0.00215

Measured yesterday against content hash 4576152a9cbd, 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 yesterday.

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.

skills/pre-mortem/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pre-Mortem

Overview

A pre-mortem is a prospective risk technique developed by Gary Klein. Before a project launches, the team imagines it is some future date and the project has already failed — then works backward to explain why. This "prospective hindsight" surfaces risks that standard risk registers and optimism bias routinely suppress.

NOW ──────────────────────────────────────────► FUTURE

  [Project              [Imagined          [Real
   Kickoff]              Failure Date]      Launch]
       │                      │                │
       │   Pre-Mortem         │                │
       │   runs HERE ◄────────┘                │
       │   "It failed. Why?"                   │
       │                                       │
       └──── fixes applied ───────────────────►│

Unlike a risk register (which lists vague probabilities), a pre-mortem produces a ranked, narrative list of specific failure stories that teams can act on immediately.

Core Concepts

Prospective Hindsight

Psychologically, people generate more and better reasons for an outcome when they treat it as having already happened rather than as a possibility. Declaring "it failed" — not "it might fail" — unlocks this effect. The team switches from defending their plan to explaining a known outcome.

Individual Brainstorm Before Group Discussion

Group dynamics suppress minority views. Each participant writes their own failure narrative silently before any sharing. This prevents anchoring on the first idea voiced and ensures quieter team members contribute genuine concerns.

Failure Categories

Structure the brainstorm across four domains to avoid blind spots:

┌─────────────────┬──────────────────────────────────────────┐
│ CATEGORY        │ EXAMPLES                                 │
├─────────────────┼──────────────────────────────────────────┤
│ Execution       │ missed deadlines, scope creep, key       │
│                 │ person leaves, quality shortcuts         │
├─────────────────┼──────────────────────────────────────────┤
│ Assumptions     │ market size wrong, customer need         │
│                 │ misunderstood, tech feasibility off      │
├─────────────────┼──────────────────────────────────────────┤
│ External        │ competitor moves, regulation change,     │
│                 │ economic shift, dependency failure       │
├─────────────────┼──────────────────────────────────────────┤
│ Team/Process    │ misaligned incentives, unclear ownership,│
│                 │ communication breakdown, wrong metrics   │
└─────────────────┴──────────────────────────────────────────┘

Read the full file on GitHub · 151 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. yesterday First seen · 151 lines · 23 tokens per session scan A 4576152a9cbd

Subscribe to this mod's changes

pre-mortem is a skill published in the GitHub repository tupe12334/instinct (1 stars, last pushed 16d ago), licensed MIT. It adds 23 tokens to every session and 2,150 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 2026-08-31.