pre-mortem

A planning exercise that imagines a project has already failed and works backward to identify why.

In plain words
What is it for?
Use it before committing to a plan, migration, launch, or other project to identify concrete causes of failure, mitigations, and early warning signs.
Why use it?
It turns vague risk discussion into specific failure scenarios, then ranks them by likelihood and impact. This helps teams focus on the most important safeguards.

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/3243dwon/clear-eye/pre-mortem
Any agent
npx skills add 3243dwon/clear-eye --skill pre-mortem
Clone the repo
git clone --depth 1 https://github.com/3243dwon/clear-eye

Made for: Claude Code, Codex.

Per session 162 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 926 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 $0.00162 $0.00926
Opus 5 $0.00081 $0.00463
Sonnet 5 $0.00032 $0.00185
Haiku 4.5 $0.00016 $0.00093

Measured 2d ago against content hash 191533c53fa0, 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 2d 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.

pre-mortem/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pre-Mortem

A post-mortem asks why something died. A pre-mortem runs it before you commit: imagine the plan has already failed, then reason backward to why. Prospective hindsight makes people name risks they'd otherwise stay politely quiet about.

Core principle

Don't ask "what are the risks?" (vague, easy to wave away). Say "It's six months later and this failed badly. What happened?" — then explain the failure as if it already occurred.

The process

  1. Fix the plan and a horizon. What's being attempted, and by when do we judge it?
  2. Declare failure. Vividly: "It's [horizon]. The plan failed. It was a disaster." Sit in that world.
  3. Generate causes. List the reasons it failed — concrete, specific, in past tense ("the migration corrupted prod data because the dry-run skipped foreign keys"), not abstractions ("poor execution").
  4. Rank by likelihood × impact. Score each cause on both; sort. The top of that list is where attention belongs.
  5. Prescribe the one fix that matters most. For the top risks, the single highest-leverage mitigation — and a cheap early-warning signal that tells you it's materializing.

Output format

  1. The failure scenario — 2–3 vivid sentences, past tense.
  2. Ranked failure causes — a table or list: cause · likelihood (H/M/L) · impact (H/M/L). Lead with high×high.
  3. The one fix — the single most leverage-rich mitigation. If you do nothing else, do this.
  4. Early-warning signals — the cheap canaries that tell you a top risk is happening while there's still time.
  5. (Optional) Kill criteria — the line that, if crossed, means stop.

Worked example

Plan: Ship a payments rewrite to all users in 6 weeks.

Failure scenario: It's week 7. The cutover dropped ~2% of transactions for three days before anyone noticed; finance can't reconcile, support is on fire, and we've rolled back to a codebase nobody remembers.

Ranked causes:

Cause Likelihood Impact
No transaction-level reconciliation between old/new during rollout High High
Big-bang cutover instead of % rollout High High
Edge-case currencies untested (only USD in staging) Med High
On-call didn't know the new system Med Med

The one fix: Don't big-bang it. Run new + old in shadow mode reconciling every transaction, then ramp 1% → 100%. This alone defuses the top two risks.

Early-warning signals: Any non-zero reconciliation mismatch in shadow mode; a rise in payment-retry rate; support tickets mentioning "charged twice".

Kill criteria: >0.1% unreconciled at any rollout step → halt and roll back the increment.

Read the full file on GitHub · 61 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. 2d ago First seen · 61 lines · 162 tokens per session scan A 191533c53fa0

Subscribe to this mod's changes

pre-mortem is a skill published in the GitHub repository 3243dwon/clear-eye (1 stars, last pushed 3mo ago), licensed MIT. It adds 162 tokens to every session and 926 once invoked, about $0.0008 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.