Agent Plugins Marketplace
← All plugins

pre-mortem

v1.1.0

Pre-mortem analysis skill — define success/failure criteria before execution. Forces agents to articulate what bad output looks like before starting multi-step work. Based on Gary Klein's prospective hindsight research.

Claude Code1 Skill

By Kyle TaborLicense: MIT1 GitHub starsUpdated last week

Directory evidence

Runtimes
Claude Code
Parsed components
1 skill or MCP entry
Source updated
Sep 16, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install pre-mortem for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install pre-mortem@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/kyletabor/claude_plugins

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is pre-mortem/.

Plugin files

pre-mortem/
├── .claude-plugin/plugin.json
└── skills/pre-mortem/SKILL.md

Included Skills1

pre-mortemskills/pre-mortem/SKILL.md

Use when about to begin multi-step autonomous work, before writing code or executing plans. Defines success/failure criteria and verification plan BEFORE execution starts. Trigger: /pre-mortem [task description], or implicitly before ANY work where you're about to act — code, data pipelines, research, content. A 20-second "how could this go wrong?" is always worth it. The point is right-sizing DEPTH, not deciding whether to do one at all: Micro (one line) for tiny/reversible work, Light (inline) for moderate, Full card for epics/high-stakes. Never skip entirely; never force deep analysis on a typo.

Plugin manifests1

pre-mortem/.claude-plugin/plugin.json
{
  "name": "pre-mortem",
  "version": "1.1.0",
  "description": "Pre-mortem analysis skill — define success/failure criteria before execution. Forces agents to articulate what bad output looks like before starting multi-step work. Based on Gary Klein's prospective hindsight research.",
  "author": {
    "name": "Kyle Tabor",
    "url": "https://github.com/kyletabor"
  },
  "repository": "https://github.com/kyletabor/claude_plugins",
  "license": "MIT",
  "keywords": [
    "pre-mortem",
    "planning",
    "quality",
    "verification",
    "risk-analysis"
  ]
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[pre-mortem on Agent Plugins Marketplace](https://pluginsmp.com/plugins/pre-mortem)