pre-mortem

pre-mortem is a skill for Claude Code, Codex from pandysp/claude-plugins. It costs 96 tokens per session (859 once invoked), scanned A, original, MIT.

A risk-analysis exercise that imagines a plan, design, or decision has failed and identifies the likely causes in advance.

In plain words
What is it for?
Use it before finalizing significant designs, decisions, or deployments to identify failure modes and reduce avoidable surprises.
Why use it?
It helps reveal technical, structural, boundary, human, and operational problems while they are still easier to address.

Skill for Claude CodeCodex

Part of the pre-mortem plugin — 1 skill 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/pandysp/claude-plugins/pre-mortem
Any agent
npx skills add pandysp/claude-plugins --skill pre-mortem
Clone the repo
git clone --depth 1 https://github.com/pandysp/claude-plugins

Made for: Claude Code, Codex.

Or install pre-mortem, the plugin that ships this one along with the rest of its 1 skill.

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/pandysp/claude-plugins/pre-mortem.svg)](https://agentmods.dev/skills/pandysp/claude-plugins/pre-mortem)
Your own site
<a href="https://agentmods.dev/skills/pandysp/claude-plugins/pre-mortem"><img src="https://agentmods.dev/badge/skills/pandysp/claude-plugins/pre-mortem.svg" alt="Measured on agentmods" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 859 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 $0.00096 $0.00859
Opus 5 $0.00048 $0.00430
Sonnet 5 $0.00019 $0.00172
Haiku 4.5 $0.00010 $0.00086

Measured 4d ago against content hash e8f4184e3411, 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 4d 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/pre-mortem/skills/pre-mortem/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pre-mortem: assume it failed, work backward

Imagine this has already failed. What went wrong?

The pre-mortem inverts the usual optimistic framing. Instead of asking "will this work?" (which biases toward yes), assume it already failed and work backward to figure out why. Surfaces risks that optimism would hide.

Process

1. Set the scene

State what's being evaluated, what success looks like, the timeline, and the blast radius.

2. Imagine failure

Assume it's 3 months later and this failed. Generate failure scenarios across these categories. They're prompts, not a checklist.

  • Mechanism: what breaks under load, scale, or real-world data? Dependency changes? Network slow, disk full, API rate-limits?
  • Structure: where does the design leak? What requirements emerge that this can't accommodate? Where is it optimized for today and fragile against tomorrow?
  • Boundary: what happens at edges with other systems? Upstream contract changes? Data format evolves?
  • Human: what if the next developer misunderstands the design? What if someone uses it in a way you didn't anticipate? Will error messages actually help?
  • Operations: how do you know this is working in production? What's observable? What happens when it fails silently? How do you roll back?

After scanning these 5, ask: what doesn't fit any of these that I should worry about? Name it as a 6th. The most dangerous failures are often the ones that don't fit the boxes.

3. Rank by danger

For each failure mode, assess:

  • Likelihood: how probable? (not "could it happen" but "will it happen given enough time")
  • Impact: recoverable annoyance or catastrophic data loss?
  • Detectability: would you know it happened? Silent failures are worse than loud ones.

The most dangerous failures are likely + high-impact + hard to detect. Lead with those.

4. Identify detection strategies

For each significant failure mode: how would you know if it happened? What metric, log line, user behavior, or test would reveal it?

Read the full file on GitHub · 66 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. 4d ago First seen · 66 lines · 96 tokens per session scan A e8f4184e3411

Subscribe to this mod's changes

pre-mortem is a skill published in the GitHub repository pandysp/claude-plugins (5 stars, last pushed 13d ago), licensed MIT. It adds 96 tokens to every session and 859 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 2026-08-31.

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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens