premortem

premortem is a skill for Claude Code, Codex from Adelie-Squad/solosquad. It costs 35 tokens per session (805 once invoked), scanned A, original, MIT.

A pre-release review method that assumes a project has already failed, then works backward to identify why. It turns those possible failures into checks and release notes.

In plain words
What is it for?
Use it before launching a product or major change to list and rank failure scenarios, create a launch checklist, prepare rollback and monitoring plans, and draft release notes.
Why use it?
It exposes risks that ordinary launch planning may overlook, along with early warning signs and ways to reduce the damage.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it before launching a product or major change to list and rank failure scenarios, create a launch checklist, prepare rollback and monitoring plans, and draft release notes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adelie-squad/solosquad/premortem
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.

Any agent
npx skills add Adelie-Squad/solosquad --skill premortem
Clone the repo
git clone --depth 1 https://github.com/Adelie-Squad/solosquad

Made for: Claude Code, Codex.

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 premortem

README.md
[![agentmods](https://agentmods.dev/badge/skills/adelie-squad/solosquad/premortem.svg)](https://agentmods.dev/skills/adelie-squad/solosquad/premortem)
Your own site
<a href="https://agentmods.dev/skills/adelie-squad/solosquad/premortem"><img src="https://agentmods.dev/badge/skills/adelie-squad/solosquad/premortem.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 805 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00035 $0.00805
Opus 5 $0.00017 $0.00402
Sonnet 5 $0.00007 $0.00161
Haiku 4.5 $0.00003 $0.00081

Measured 8d ago against content hash f4d0436bf966, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

skills/premortem/SKILL.md · 116 lines

What it actually says

Pre-Mortem Skill

Tier-2 (v1.1.x slot). Gary Klein 의 pre-mortem 기법. 출시 전 마지막 sanity check.

진행 흐름

1. Time Travel

"6개월 후. 이 프로젝트는 실패 했다. 사용자는 떠났고, OKR 미달."

2. 실패 원인 brainstorm (≥10)

가능한 모든 실패 시나리오를 나열. positive thinking 자제, 비관적으로.

failure_modes:
  - id: f1
    scenario: "사용자가 첫 사용 후 다시 안 옴"
    likelihood: high | medium | low
    impact: critical | major | minor
    detection_lag: "..."  # 얼마나 늦게 알게 되나
    early_signal: "..."   # 어떤 지표가 미리 알려주나
    mitigation:
      - "..."

3. 우선순위 매트릭스

  • (likelihood × impact) 곱으로 정렬
  • top 5 risk → 사전 mitigation 필수

4. Launch Checklist 도출

## Launch Checklist — {{project}}

### Pre-launch (T-3d)
- [ ] qa regression test 통과
- [ ] security audit (auth/data 변경 시)
- [ ] product-designer 검토 (정책 영향 시)
- [ ] data-analyst instrumentation 검증
- [ ] (premortem risks → 대응 완료 확인) × 5

### Launch (T-0)
- [ ] rollback plan 명시
- [ ] monitoring dashboard 준비
- [ ] support 응답 ready
- [ ] release notes 작성 완료

### Post-launch (T+24h)
- [ ] leading indicator 5 지표 확인
- [ ] guardrail metric 회귀 없는지
- [ ] 사용자 피드백 1-pass
- [ ] (premortem early signal 모니터링)

5. Release Notes Draft

# {{Project}} — Release Notes

## TL;DR
{{1 line summary}}

## What's New
- ...

## Why
- {{problem this solves}}

## How to Use
- ...

## Known Limitations
- {{premortem 의 mitigated risks 일부 명시}}

## Feedback
- ...

HARD GATE

- [ ] failure modes ≥ 10 brainstorm
- [ ] top 5 risk 모두 mitigation 완료
- [ ] launch checklist 모든 항목 ✅
- [ ] release notes 작성 완료
- [ ] rollback plan 명시 + 실험

Anti-Sycophancy

비관적 사고 강제:

  • ❌ "출시 준비가 잘 되었습니다"
  • ✅ "5 risk 중 3건 mitigated. risk #2 (적용 시 latency +200ms) 는 monitoring 만 완료. monitoring 발동 임계값 명시 필요."

Reference

  • Gary Klein "Performing a Project Premortem" (HBR)
  • phuryn/pm-skills/pm-execution/{pre-mortem, release-notes}
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. 8d ago First seen · 116 lines · 35 tokens per session scan A f4d0436bf966

Subscribe to this mod's changes

premortem is a skill published in the GitHub repository Adelie-Squad/solosquad (19 stars, last pushed 17d ago), licensed MIT. It adds 35 tokens to every session and 805 once invoked, about $0.0002 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 2026-08-30.