premortem-skill

premortem-skill is a skill for Claude Code, Codex from peterfei/forge-skill. It costs 85 tokens per session (2,844 once invoked), scanned A, original, MIT.

A structured premortem method for imagining that a project has already failed and working backward to find why. It is a planning exercise based on research by Gary Klein and others.

In plain words
What is it for?
Use it when planning a project or making a decision, especially to identify likely failure causes and preventive actions. It can also be combined with scenario planning.
Why use it?
It helps teams notice risks before work begins, including concerns people may hesitate to raise openly. The imagined failure turns vague worry into specific problems to prevent.

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

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-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/peterfei/forge-skill/premortem-skill.svg)](https://agentmods.dev/skills/peterfei/forge-skill/premortem-skill)
Your own site
<a href="https://agentmods.dev/skills/peterfei/forge-skill/premortem-skill"><img src="https://agentmods.dev/badge/skills/peterfei/forge-skill/premortem-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,844 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 $0.00085 $0.02844
Opus 5 $0.00043 $0.01422
Sonnet 5 $0.00017 $0.00569
Haiku 4.5 $0.00009 $0.00284

Measured 4d ago against content hash 4fd0df0001b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

premortem-skill 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.

methods/premortem-skill/SKILL.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

事前验尸(Premortem)· 思维工具

"A premortem is the hypothetical opposite of a postmortem. A postmortem in a medical setting allows health professionals and the family to learn what caused a patient's death. A premortem in a business setting comes at the beginning of a project rather than the end, so that the project can be improved rather than autopsied." — Gary Klein

激活条件与触发词

  • 直接调用:「用事前验尸分析...」「premortem这个项目」「假设已失败」
  • 语义触发:用户计划一个新项目或决策,想提前识别风险
  • 组合调用:「先用事前验尸识别风险,再用场景规划构建应对」

方法框架概览

事前验尸的核心是假设项目已失败并反推失败原因,它通过心理时间旅行释放想象力、心理安全感释放真实观点、失败场景可视化触发预防行动来提前识别并消除风险。

核心原理(3-7个,每个须附 ≥2 个跨域证据)

原理 1: 前瞻性后见之明释放想象力

一句话定义:当你站在未来假设已经失败时,你会看到"现在"看不到的风险。

跨域证据

  1. 认知心理学:Klein 在实验中发现 premortem 能识别出 30% 更多的项目风险(来源:Klein, Performing a Project Premortem, HBR, 2007)
  2. 油气工业:British Petroleum 在部分项目上实施 premortem 后显著降低了安全事故率(来源:Klein, Streetlights and Shadows, 2009)

应用方式:正式开会时,说"今天我们假设这个项目在 6 个月后死透了。每个人用 10 分钟写下来:它为什么会死?"

局限:如果团队缺乏相关领域经验,他们可能想不出有意义的风险。

原理 2: 群体智慧需要心理安全感

一句话定义:人们天然不愿意在领导面前说"我觉得这要翻车"。premortem 通过"假设已经翻了"降低心理障碍。

跨域证据

  1. 组织心理学:Google Project Aristotle 发现心理安全感是高效团队的最强预测因子(来源:Google re:Work, Project Aristotle, 2016)
  2. 核工业:国际核电行业的事故报告系统依靠匿名报告制度降低恐惧(来源:IAEA, Safety Culture in Nuclear Installations, 2001)

应用方式:领导在 premortem 中最后一个发言。如果领导先发言,其他人就会"聪明地"附和。

局限:如果在惩罚文化严重的组织,仅靠 premortem 的形式不足以建立真实安全感。

原理 3: 时间距离降低确认偏差

一句话定义:现在看未来总是乐观的。站在未来回头看,乐观偏差自然消退。

跨域证据

  1. 行为经济学:Kahneman & Tversky 的前景理论表明人在收益域厌恶风险但在损失域追求风险(来源:Kahneman, Thinking Fast and Slow, 2011)
  2. 投资决策:行为金融学发现基金经理在持有时(当下视角)高估成功概率,但在回顾评估时(事后视角)更准确(来源:Barberis & Thaler, A Survey of Behavioral Finance, 2003)

应用方式:用"为什么死了"代替"什么会出错",前者迫使站在未来视角回答。

局限:虚构未来失败的场景可能引发过度悲观,需要平衡。

原理 4: 失败可视化触发预防行动

一句话定义:当你具体想象失败的画面时,你会自动产生"怎么预防它发生"的冲动。

跨域证据

  1. 航空安全:NASA 和航空业广泛使用 Failure Mode and Effects Analysis (FMEA) 将想象到的失效模式转化为预防措施(来源:NASA, FMEA Handbook, 2008)
  2. 医疗安全:手术安全清单来自对手术失败场景的系统性想象(来源:Gawande, The Checklist Manifesto, 2009)

应用方式:不是列一堆模糊的"风险",每个风险要具体到触发场景:"如果______发生,项目会死。"

Read the full file on GitHub · 176 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 · 176 lines · 85 tokens per session scan A 4fd0df0001b9

Subscribe to this mod's changes

premortem-skill is a skill published in the GitHub repository peterfei/forge-skill (13 stars, last pushed 2mo ago), licensed MIT. It adds 85 tokens to every session and 2,844 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

descend

Verifies whether the problem was correctly identified before solving, auditing pattern matches against first principles.

Kshitijpalsinghtomar/depth-skills · 21 tokens

fundraising-narrative

This skill should be used when the user asks about "pitch deck", "fundraising story", "investor pitch", "VC narrative", "pitch narrative", "fundraising deck", "pitch structure", "Sequoia format", "why now slide", "market size slide", "TAM SAM SOM", "earned secret", "value hypothesis", "product-market fit"…

tjboudreaux/cc-skills-vc-fundraising · 112 tokens

investor-relations

This skill should be used when the user asks about "investor update", "board deck", "board meeting", "investor communication", "monthly update", "quarterly update", "investor email", "bad news investors", "pivot communication", "crisis communication investors", "investor ask", "warm intro", "VC relationship"…

tjboudreaux/cc-skills-vc-fundraising · 101 tokens

ux-principles

User research, usability heuristics, user psychology, accessibility, inclusive design, user testing, and UX metrics.

manutej/luxor-claude-marketplace · 26 tokens

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

golden-rss

Use when testing the rss golden build.

yusufkaraaslan/Skill_Seekers · 12 tokens