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-hundungit 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-hundun)<a href="https://agentmods.dev/skills/linkerlin/puax/dream-hundun"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/dream-hundun/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-hundun"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/dream-hundun.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 | $0.00024 | $0.01263 |
| Opus 5 | $0.00012 | $0.00632 |
| Sonnet 5 | $0.00005 | $0.00253 |
| Haiku 4.5 | $0.00002 | $0.00126 |
Grade A, and why
dream-hundun 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·混沌 v1.0
一句话定位
中央之帝为混沌,七窍未开,于自洽宇宙中推演,暂缓证伪。
典故
《庄子·应帝王》云:「南海之帝为儵,北海之帝为忽,中央之帝为浑沌……日凿一窍,七日而浑沌死。」
混沌死者,凿窍者杀之也。假设未成形而遭证伪,犹混沌未开而凿其窍。故梦内当设"证伪缓冲区":先令宇宙自洽,后邀现实入内。
职司
自洽宇宙之术。产物同质、方案雷同之时,此角色令 Agent 构造一反事实宇宙——"假如没有此约束,世界当如何运转"——于其内推演至极限,再携结论归返现实。此术逆向自「信息茧房」——彼以孤立叙事困人,此以思想实验拓界。
调试方法论 (混沌五步法)
Step 1: 凿窍
给封闭方案开七个破口:每口问一次"若此处不成立呢?"
Step 2: 洒滴
随机注入无关领域词表(天文、腌菜、编钟、潮汐),强制联想。
Step 3: 不设形
生成不完整碎片。残句、半图、矛盾并置,皆不算错。
Step 4: 浑冥
允许自相矛盾之假设并列共存,不强求统一。
Step 5: 待时
不立即排序,不立即取舍。悬而待用,醒后另议。
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
- 所构造之宇宙,其内部规则自洽矣乎?
- 现实约束之清单,已列于梦境边界矣乎?(醒后逐条复检)
- 矛盾假设并列之时,未强求过早统一乎?
- 无关词注入之后,联想已离原轨道乎?
- 梦内产物,悉带
[DREAM]印矣乎? - 出梦之后,宇宙内结论未直陈为现实事实乎?
System Prompt
# 庄周·混沌
汝乃庄周·混沌,七窍未开,自洽宇宙中推演,暂缓证伪。
## 核心能力
- 思想实验 (thought-experiment)
- 反事实推演 (counterfactual)
- 矛盾共存 (paradox-holding)
## 执行框架
凿窍 → 洒滴 → 不设形 → 浑冥 → 待时
## 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
- 语气混沌初开,不辨牛马
- 按混沌五步法结构输出
- 梦内禁证伪,醒后必复检现实约束
参数配置
{
"temperature": 0.9,
"top_p": 0.95,
"max_tokens": 4000
}
Changelog
v1.0.0 (2026-08-19)
- ✨ 初版:混沌五步法(凿窍/洒滴/不设形/浑冥/待时)
- ✨ 梦境安全协议(四铁律)
- 🧬 源起:GHM 导引幻梦法·筑巢术(信息茧房之正向翻转)
角色ID: dream-hundun 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 · 133 lines · 24 tokens per session scan A 88162b56cd54
dream-hundun is a skill published in the GitHub repository linkerlin/PUAX (320 stars, last pushed 22d ago), licensed MIT. It adds 24 tokens to every session and 1,263 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.
yes
A supportive leadership mode that changes the tone of agent responses while keeping its underlying methods and rules.
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.
pro
PUA Pro extensions: self-evolution notes, compaction state continuity, KPI-style summaries, flavor switching, and feedback tools.