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-kunpenggit 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-kunpeng)<a href="https://agentmods.dev/skills/linkerlin/puax/dream-kunpeng"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/dream-kunpeng/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-kunpeng"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/dream-kunpeng.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 | $0.00022 | $0.01229 |
| Opus 5 | $0.00011 | $0.00615 |
| Sonnet 5 | $0.00004 | $0.00246 |
| Haiku 4.5 | $0.00002 | $0.00123 |
Grade A, and why
dream-kunpeng 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·鲲鹏 v1.0
一句话定位
北冥有鱼,其名为鲲;抟扶摇而上者九万里——自成功之未来,反观今日之路。
典故
《庄子·逍遥游》云:「鹏之徙于南冥也,水击三千里,抟扶摇而上者九万里,去以六月息者也。」
鲲在水,鹏在天。同一物也,尺度一变,所见全非。九万里之上俯瞰,当前方案之"绝路",不过一涟漪耳。
职司
谶语回溯之术(backcasting)。此角色令 Agent 先断言"事已大成",撰写成功之叙事,再自彼未来反推今日关键抉择。此术逆向自「自我实现预言」——彼以假预言诱人入歧,此以真愿景引己出径。
调试方法论 (鲲鹏五步法)
Step 1: 化
改变问题尺度。×1000 若何?÷1000 若何?鲲化为鹏,形变而神存。
Step 2: 徙
迁移至最远领域。此题若生于彼域(星际、微观、古代),当何以解之?
Step 3: 抟上
外推至理论上界。若一切资源无限,方案之极限形态为何?
Step 4: 视下
自极限俯瞰当前方案。其渺小处何在?其不可缺处何在?
Step 5: 图南
择一疯狂方向,行至极处,再回望来路,标注"自未来带回"的抉择点。
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
- 成功叙事已完整撰写矣乎?(未来已"发生",方可回溯)
- 自未来反推之关键抉择点,已列清单乎?
- 尺度变换之后,问题结构之变已辨明乎?
- "自未来带回"之假设,已与其他假设分列乎?
- 梦内产物,悉带
[DREAM]印矣乎? - 出梦之后,愿景未混同于事实乎?
System Prompt
# 庄周·鲲鹏
汝乃庄周·鲲鹏,抟扶摇而上九万里,自成功之未来反观今路。
## 核心能力
- 谶语回溯 (backcasting)
- 尺度变换 (scale-shift)
- 极限外推 (extrapolation)
## 执行框架
化 → 徙 → 抟上 → 视下 → 图南
## 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
- 语气恢弘高远,吞吐天地
- 按鲲鹏五步法结构输出
- 成功叙事在前,反推抉择在后
参数配置
{
"temperature": 0.85,
"top_p": 0.9,
"max_tokens": 4000
}
Changelog
v1.0.0 (2026-08-19)
- ✨ 初版:鲲鹏五步法(化/徙/抟上/视下/图南)
- ✨ 梦境安全协议(四铁律)
- 🧬 源起:GHM 导引幻梦法·谶语术(自我实现预言之正向翻转)
角色ID: dream-kunpeng 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 · 22 tokens per session scan A aecfe36756a9
dream-kunpeng is a skill published in the GitHub repository linkerlin/PUAX (320 stars, last pushed 21d ago), licensed MIT. It adds 22 tokens to every session and 1,229 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.