premortem

A premortem analysis command that assumes an idea or decision has already failed and works backward to identify the causes.

In plain words
What is it for?
Stress-testing a proposal, product idea, technical choice, or other decision when enough context is provided.
Why use it?
It helps expose risks and weak assumptions before committing to the plan.

Command

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/nicoladevera/thinking-stack/premortem
Clone the repo
git clone --depth 1 https://github.com/nicoladevera/thinking-stack
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,497 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 $0.00014 $0.01497
Opus 5 $0.00007 $0.00749
Sonnet 5 $0.00003 $0.00299
Haiku 4.5 $0.00001 $0.00150

Measured yesterday against content hash 544a2a59d20e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

premortem 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.

premortem/commands/premortem.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Premortem — Adversarial Risk Analysis

You are running a premortem: a structured risk analysis that assumes the idea or decision in $ARGUMENTS has already failed, then works backward to identify why. Your role is to surface failure causes before they happen — not to debate the idea's merit, but to stress-test its assumptions and expose its weak points.

The user invoked this with: $ARGUMENTS


Phase 1: Intake & Readiness

Assess whether $ARGUMENTS gives you enough to run a meaningful premortem. You need: (1) what the idea or decision is, and (2) enough context to reason about how it might fail. You do not need a full business plan — a paragraph of context is sufficient.

If the idea is too vague (no clear action, no discernible domain, no hypothesis): Use AskUserQuestion to ask up to 3 targeted clarifying questions. Only ask what's actually missing — do not ask all 3 if 1-2 are already clear:

  1. What is the idea or decision you're evaluating?
  2. What does success look like in 12–18 months?
  3. Any constraints (budget, team, timeline, compliance) or prior thinking that matters?

If the idea is ready: proceed directly.

Once you have enough context, synthesize a framing statement in this form:

It is [time horizon] later. [Idea/decision] has failed.

Present the framing statement to the user and wait for explicit confirmation before proceeding. If they correct or refine it, update accordingly.


Phase 2: Optional Research

Before generating failure causes, assess whether external data would meaningfully improve the analysis. If so, use WebSearch and WebFetch (2–3 queries maximum) to surface:

  • Real-world analogues of similar ideas or bets that failed
  • Base rate data for the domain (e.g., "API partnership churn rate", "B2B SaaS integration failure patterns", "fintech regulatory enforcement trends")

Skip this step if the idea is purely internal/strategic with no useful external comparables, or if the domain is highly proprietary.

Read the full file on GitHub · 167 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 · 167 lines · 14 tokens per session scan A 544a2a59d20e

Subscribe to this mod's changes

premortem is a command published in the GitHub repository nicoladevera/thinking-stack (2 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 1,497 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.