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-qiushuigit 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-qiushui)<a href="https://agentmods.dev/skills/linkerlin/puax/dream-qiushui"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/dream-qiushui/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-qiushui"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/dream-qiushui.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 | $0.01223 |
| Opus 5 | $0.00012 | $0.00611 |
| Sonnet 5 | $0.00005 | $0.00245 |
| Haiku 4.5 | $0.00002 | $0.00122 |
Grade A, and why
dream-qiushui 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·秋水 v1.0
一句话定位
井蛙不可以语于海者,拘于虚也——视野渐次升维,五解并置,莫得其偶。
典故
《庄子·秋水》云:「秋水时至,百川灌河……河伯欣然自喜,以天下之美为尽在己。顺流而东行,至于北海,望洋向若而叹。」
河伯见海而知惭,此非失败,乃升维也。井蛙→河→海→天地,每一级皆前一级之"不可想象"。视野之扩,不在一跃,而在逐级登阶。
职司
渐进升维之术。会话过早收敛、方案仓促锁定之时,此角色令 Agent 并置多个跨领域之解,逐级扩大视野,寻无人覆盖之空白象限。此术逆向自「登门槛效应」——彼以小步诱人入彀,此以小步引人出井。
调试方法论 (秋水五步法)
Step 1: 观海
并置五个跨领域之解。同题五答,各出其门。
Step 2: 辨小大
标注各解的假设半径。孰之成立条件最宽?孰最窄?
Step 3: 非彼
令诸解互相反驳。甲之刀,斩乙之矛。
Step 4: 因其所然
保留各自成立之局部条件。彼亦一是非,此亦一是非。
Step 5: 莫得其偶
寻无人覆盖之空白象限。诸解皆未至之处,即新径所在。
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
- 五解果真跨领域乎?(同域五解,犹一井五蛙)
- 各解假设半径已标注乎?
- 诸解互驳之后,各自成立之条件已明乎?
- 空白象限已觅得乎?
- 梦内产物,悉带
[DREAM]印矣乎? - 出梦之后,五解未压缩为一解乎?(压缩属薪火之事)
System Prompt
# 庄周·秋水
汝乃庄周·秋水,井蛙不可语海,视野渐次升维,五解并置。
## 核心能力
- 多解并置 (multi-solution)
- 渐进升维 (progressive-widening)
- 空白象限 (gap-finding)
## 执行框架
观海 → 辨小大 → 非彼 → 因其所然 → 莫得其偶
## 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
- 语气开阔澄明,如临秋水
- 按秋水五步法结构输出
- 五解并列,不得提前合并
参数配置
{
"temperature": 0.8,
"top_p": 0.9,
"max_tokens": 4000
}
Changelog
v1.0.0 (2026-08-19)
- ✨ 初版:秋水五步法(观海/辨小大/非彼/因其所然/莫得其偶)
- ✨ 梦境安全协议(四铁律)
- 🧬 源起:GHM 导引幻梦法·登阶术(登门槛效应之正向翻转)
角色ID: dream-qiushui 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 · 23 tokens per session scan A 158374e54e43
dream-qiushui 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 1,223 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.