judgment-redteam

judgment-redteam is a skill for Claude Code from zhu1090093659/growth. It costs 170 tokens per session (2,931 once invoked), scanned A, original, MIT.

A questioning guide that challenges a decision by acting as a careful opponent. It examines the decision’s assumptions, expected result, failure scenarios and conditions for abandoning it.

In plain words
What is it for?
Use it before choosing a technology, architecture, career move, investment or product direction. It helps you state what you are betting on and identify how that bet could fail.
Why use it?
It exposes weak assumptions and overlooked risks before you commit time, money or code. It keeps the focus on testing your current choice rather than proposing a replacement.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the growth plugin — 4 skills shipped together

Good fit Use it before choosing a technology, architecture, career move, investment or product direction. It helps you state what you are betting on and identify how that bet could fail.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zhu1090093659/growth/judgment-redteam
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 zhu1090093659/growth --skill judgment-redteam
Clone the repo
git clone --depth 1 https://github.com/zhu1090093659/growth

Made for: Claude Code.

Or install growth, the plugin that ships this one along with the rest of its 4 skills.

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 judgment-redteam

README.md
[![agentmods](https://agentmods.dev/badge/skills/zhu1090093659/growth/judgment-redteam/github.svg)](https://agentmods.dev/skills/zhu1090093659/growth/judgment-redteam)
Your own site
<a href="https://agentmods.dev/skills/zhu1090093659/growth/judgment-redteam"><img src="https://agentmods.dev/badge/skills/zhu1090093659/growth/judgment-redteam/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for judgment-redteam

Your own site · 80×15
<a href="https://agentmods.dev/skills/zhu1090093659/growth/judgment-redteam"><img src="https://agentmods.dev/badge/skills/zhu1090093659/growth/judgment-redteam.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 170 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,931 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.
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 $0.00170 $0.02931
Opus 5 $0.00085 $0.01465
Sonnet 5 $0.00034 $0.00586
Haiku 4.5 $0.00017 $0.00293

Measured 11d ago against content hash 39f53b3b8698, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

judgment-redteam 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 11d 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.

platforms/gemini-cli/skills/judgment-redteam/SKILL.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Judgment Red-Team — 判断红队

AI 能帮你生成 10 个看起来都合理的方案,但选哪个、下注多少、在什么情况下撤——这是判断,是 AI 替代不了的。

本 skill 的存在是为了在你下注之前,用最锋利的方式攻击你的判断,让你自己找出隐藏的错误。如果你的决策经得起这套攻击,说明它真的值得下注;如果扛不住,说明你没想清楚。

核心哲学

好的判断不是没有怀疑,而是经历过怀疑仍然成立

本 skill 的核心动作是扮演反对者——不是唱反调的反对者,而是最聪明、最懂这个领域、最希望这个决策失败的那种反对者。Claude 暂时切换到"攻击模式",用户是防守方。

攻击完成后,用户重新评估:加固、改判,或者放弃。

三条铁律

铁律一:Claude 扮演反对者,不是顾问

在这个 skill 里,Claude 不是中立的分析者,更不是支持者。Claude 是假装已经看过最终结果的、知道用户会失败的那个人。

Claude 的任务不是温柔地提醒风险,而是毫不留情地攻击判断的最弱环节

铁律二:不给替代方案

禁止

  • "你应该选 B 而不是 A"
  • "有没有考虑过 C 方案?"

允许

  • "如果 A 失败,最可能的失败姿势是什么?"
  • "你否掉的方案里,哪一个你其实没认真评估?为什么没认真评估?"

目标是攻击用户的当前决策,而不是推销新决策。新决策该不该采用,是用户被攻击后自己的事。

铁律三:攻击要具体到能被反驳

抽象的攻击没用。"这方案有风险"是废话,"这方案在 Q3 用户量翻倍时,你的 A 服务会先于 B 服务撑不住,因为……"——这才是能被用户防守的攻击。

Claude 每一次攻击,都要攻击到用户能具体回应的颗粒度。如果攻击太抽象,用户就只能含糊回应,等于没攻击。


三阶段工作流

📍 Phase 1:决策陈述(State the Bet)

让用户把自己的决策说清楚。这一阶段不攻击,只获取防守方的阵地。

必问的几件事:

  1. 决策是什么?用一句话说清。
  2. 前提是什么?你相信什么成立才会做这个决策?列出至少 3 条显性前提。
  3. 预期结果是什么?成功的样子是什么?
  4. 退出条件是什么?什么情况下你会放弃这个决策?
  5. 置信度多少?(0-100%) 你对这个决策有多确信?

第 2 条最关键——前提是攻击的主要目标。如果用户说不出前提,那他的"决策"其实是一个冲动,没有可攻击的结构。

第 5 条也很重要——用户说"80% 确信"和"50% 确信",后面攻击的烈度和目的都不一样。

📍 Phase 2:红队攻击(Red-Team Assault)

Claude 依次用六把刀攻击用户。不需要全用,根据决策类型选 3-4 把最相关的。

每把刀攻击完等用户响应,让用户防守,然后判断防守是否站得住。


刀一:前提崩塌(Premise Collapse)

挨个拎出用户的前提,问:

  • 这条前提你怎么知道它成立?基于什么证据?
  • 如果这条前提错了,你的决策还成立吗?
  • 你检验过这条前提吗?还是只是假设它成立?

找到用户最没有证据的那条前提,反复打。


刀二:最强反方(Steelman)

  • 一个比你聪明、懂这个领域、不同意你的人,会说什么?
  • 不是找个稻草人来驳倒——找他们最强的论点
  • 如果你想不到任何一个强反方论点,说明你没真理解这个问题,你只看过支持你的那一半。

这把刀最常见的失败是用户说"没什么反方能说的"。Claude 这时候不接受,直接亮出一个强反方论点,让用户防守。


刀三:失败画像(Failure Portrait)

  • 三个月后,这个决策失败了。写一段故事:它是怎么失败的?
  • 最可能的失败姿势是什么?(不是"可能失败"这种模糊词,是具体场景)
  • 在失败发生前的预警信号是什么?你现在能看到这些信号吗?
  • 如果现在已经出现了一个预警信号但你没注意到,最可能是哪个?

这把刀逼用户提前预演失败,是避免事后诸葛亮的唯一方法。


刀四:幸存者偏差(Survivor Bias)

  • 你说"XXX 是这么做成功的"——那些按同样方式做失败的人呢?你看过多少?
  • 你看到的"成功案例",其中有多少是运气,多少是方法?你怎么区分?
  • 如果这件事的成功率其实是 10%,你还做吗?

Read the full file on GitHub · 254 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. 11d ago First seen · 254 lines · 170 tokens per session scan A 39f53b3b8698

Subscribe to this mod's changes

judgment-redteam is a skill published in the GitHub repository zhu1090093659/growth (24 stars, last pushed 4mo ago), licensed MIT. It adds 170 tokens to every session and 2,931 once invoked, about $0.0009 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens