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.
npx skills add linkerlin/PUAX --skill dream-qiwugit clone --depth 1 https://github.com/linkerlin/PUAXWrote 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.
[](https://agentmods.dev/skills/linkerlin/puax/dream-qiwu)<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.
<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>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once 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 |
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.
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
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.
- 10d ago First seen · 134 lines · 23 tokens per session scan A 358a3182669d
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.
Other skills, from other repositories
pua-ja
A Japanese-language debugging and persistence skill based on strict review practices and systematic troubleshooting.
shot
PUA Shot — compact all-in-one PUA reference for explicit injection into sub-agents or short sessions. Strong flavor, same evidence-first behavior.
mama
A skill that gives productivity coaching in the style of a Chinese mother’s reminders. Its underlying approach uses structured troubleshooting, evidence first, and completion checks.
ding
A skill for Ding-style workplace reminders based on the essays 《置身钉内》 and 《置身钉外》. Ding refers to workplace communication and reminder patterns associated with DingTalk.
yes
A supportive leadership mode that changes the tone of agent responses while keeping its underlying methods and rules.
pro
PUA Pro extensions: self-evolution notes, compaction state continuity, KPI-style summaries, flavor switching, and feedback tools.