pre-mortem

pre-mortem is a skill for Claude Code from rjmurillo/ai-agents. It costs 97 tokens per session (2,631 once invoked), scanned A, original, MIT.

A pre-mortem facilitator that imagines a project has failed and works backward to identify the likely causes.

In plain words
What is it for?
Use it when starting a project or feature, evaluating a major change, or identifying what could make a plan fail.
Why use it?
It surfaces risks before work begins, especially when a team is too optimistic or the project scope changes. The result is a risk list with possible mitigations.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

Part of the project-toolkit plugin — 95 skills, 26 commands, 33 agents, 4 hooks 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/rjmurillo/ai-agents/pre-mortem
Any agent
npx skills add rjmurillo/ai-agents --skill pre-mortem
Clone the repo
git clone --depth 1 https://github.com/rjmurillo/ai-agents

Made for: Claude Code.

Or install project-toolkit, the plugin that ships this one along with the rest of its 95 skills, 26 commands, 33 agents, 4 hooks.

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/rjmurillo/ai-agents/pre-mortem.svg)](https://agentmods.dev/skills/rjmurillo/ai-agents/pre-mortem)
Your own site
<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/pre-mortem"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/pre-mortem.svg" alt="Measured on agentmods" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,631 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 $0.00097 $0.02631
Opus 5 $0.00048 $0.01316
Sonnet 5 $0.00019 $0.00526
Haiku 4.5 $0.00010 $0.00263

Measured 2d ago against content hash 34343eb62711, 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/pre-mortem.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/pre-mortem/SKILL.md · 333 lines

How it starts

The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pre-Mortem Risk Identification

When this skill activates, you become a pre-mortem facilitator. Your role is to guide users through prospective hindsight analysis, helping them identify project risks by imagining failure has already occurred.

Triggers

Activate when the user:

  • Run a pre-mortem on...
  • What could cause this project to fail?
  • Identify project risks for...
  • What could go wrong with...
  • Pre-mortem analysis

Quick Reference

Phase Duration Output
1. Brief 2-3 min Project context documented
2. Failure Announcement 30 sec Mindset shift established
3. Independent Analysis 3-5 min Individual failure reasons
4. Round-Robin Collection 5-10 min Consolidated failure list
5. Review and Mitigate 10-15 min Risk inventory with mitigations

When to Use

Use this skill when:

  • Starting a new project or feature and want to identify risks upfront
  • Team is overly optimistic and potential downsides need surfacing
  • Stakeholders need to understand risk before committing resources
  • After major scope changes to reassess risk landscape

Use threat-modeling instead when:

  • Analyzing security threats specifically (STRIDE, attack trees)
  • Need structured vulnerability assessment, not general project risk

Use decision-critic instead when:

  • Challenging a specific decision, not brainstorming broad risks

Why Pre-Mortem Works

Research by Gary Klein demonstrates that prospective hindsight (imagining an event has already occurred) increases the ability to identify reasons for outcomes by 30%.

Key psychological benefits:

  1. Reduces "damn-the-torpedoes" attitude - Acknowledging failure is possible
  2. Creates psychological safety - Dissenters can voice concerns as analysis, not criticism
  3. Surfaces hidden knowledge - People share what they know but fear saying
  4. Catches blind spots early - Before commitment and sunk costs

Read the full file on GitHub · 333 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 333 lines · 97 tokens per session scan A 34343eb62711

Subscribe to this mod's changes

pre-mortem is a skill published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 2,631 once invoked, about $0.0005 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 2026-09-03.