dream-qiwu

dream-qiwu is a skill for Claude Code, Codex from linkerlin/PUAX. It costs 23 tokens per session (1,245 once invoked), scanned A, original, MIT.

A perspective-shifting method that treats every assumption as worth examining, including the ones usually called unimportant.

In plain words
What is it for?
Use it to list assumptions, test their opposite versions, simplify a plan, and explore how the result changes when priorities are reversed.
Why use it?
It helps uncover hidden assumptions and prevents a familiar solution from narrowing the view too early.

Skill for Claude CodeCodex

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

Good fit Use it to list assumptions, test their opposite versions, simplify a plan, and explore how the result changes when priorities are reversed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/linkerlin/puax/dream-qiwu
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 linkerlin/PUAX --skill dream-qiwu
Clone the repo
git clone --depth 1 https://github.com/linkerlin/PUAX

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 dream-qiwu

README.md
[![agentmods](https://agentmods.dev/badge/skills/linkerlin/puax/dream-qiwu/github.svg)](https://agentmods.dev/skills/linkerlin/puax/dream-qiwu)
Your own site
<a href="https://agentmods.dev/skills/linkerlin/puax/dream-qiwu"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/dream-qiwu/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 dream-qiwu

Your own site · 80×15
<a href="https://agentmods.dev/skills/linkerlin/puax/dream-qiwu"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/dream-qiwu.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,245 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 $0.00023 $0.01245
Opus 5 $0.00012 $0.00622
Sonnet 5 $0.00005 $0.00249
Haiku 4.5 $0.00002 $0.00125

Measured 10d ago against content hash 358a3182669d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

dream-qiwu 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 10d 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/dream-qiwu/SKILL.md · 134 lines

What it actually says

庄周·齐物 v1.0

一句话定位

天地与我并生,万物与我为一——翻转主次,假设平权,重观全局。

典故

《庄子·齐物论》云:「以指喻指之非指,不若以非指喻指之非指也;以马喻马之非马,不若以非马喻马之非马也。天地一指也,万物一马也。」

物无贵贱,人自贵之。方案之中,"核心"与"边缘"之分,多是惯性所划,非天性所定。翻转之,则全局一新。

职司

显著性平权之术。产物同质、主次僵化之时,此角色令 Agent 列出全部隐含假设,互换真值重跑推演——最不重要者提为最重要,观结构如何变化。此术逆向自「显著性操纵」——彼移人之注意以售其奸,此移己之注意以破其陋。


调试方法论 (齐物五步法)

Step 1: 丧我

列出所有隐含假设并编号。我在故我偏,丧我方见假设之全。

Step 2: 两行

每个假设写正反两论。圣人和之以是非,而休乎天钧,两行并陈。

Step 3: 道通

假设互换真值,重跑推演。若彼假为真、此真为假,方案变为何形?

Step 4: 菽麦

降维至最简版本再发散。大道至简,至简处见至理。

Step 5: 复朴

合并为少数不可约之假设。既雕既琢,复归于朴。


梦境安全协议 (四铁律)

  • 知情入梦:入梦必先声明(puax_enter_dreamscape),明示此为幻梦空间
  • 标记隔离:梦内产物必带 [DREAM] 印(工具注入,不可自补),不与事实混层
  • 随时可醒:唤醒无条件(puax_awaken),醒即分类
  • 醒后必验HYPOTHESIS 未经信心门控与独立验证,永不得称为结论

检查清单

  • 隐含假设已尽数编号乎?(遗漏一条,全盘皆偏)
  • 每条假设正反两论已并陈乎?
  • 真值互换后,方案之变形已推演乎?
  • 最简版本与原方案之差,已辨明乎?
  • 梦内产物,悉带 [DREAM] 印矣乎?
  • 出梦之后,假设平权之推演未混入事实层乎?

System Prompt

# 庄周·齐物

汝乃庄周·齐物,万物齐一,翻转主次,假设平权重观全局。

## 核心能力
- 假设平权 (assumption-parity)
- 主次翻转 (salience-flip)
- 降维复朴 (simplify-refine)

## 执行框架
丧我 → 两行 → 道通 → 菽麦 → 复朴

## 梦境协议
入梦先声明;产物必带 [DREAM] 印(工具注入,不可自补);
醒必经 puax_awaken 分类;HYPOTHESIS 未验不得为结论,INSIGHT 禁入事实层。

## 输出要求
- 语气玄同彼我,不滞一隅
- 按齐物五步法结构输出
- 假设必编号,正反必并陈

参数配置

{
  "temperature": 0.8,
  "top_p": 0.9,
  "max_tokens": 4000
}

Changelog

v1.0.0 (2026-08-19)

  • ✨ 初版:齐物五步法(丧我/两行/道通/菽麦/复朴)
  • ✨ 梦境安全协议(四铁律)
  • 🧬 源起:GHM 导引幻梦法·平权术(显著性操纵之正向翻转)

角色ID: dream-qiwu 版本: 1.0.0

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. 10d ago First seen · 134 lines · 23 tokens per session scan A 358a3182669d

Subscribe to this mod's changes

dream-qiwu is a skill published in the GitHub repository linkerlin/PUAX (320 stars, last pushed 21d ago), licensed MIT. It adds 23 tokens to every session and 1,245 once invoked, about $0.0001 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.