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-paodinggit 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-paoding)<a href="https://agentmods.dev/skills/linkerlin/puax/dream-paoding"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/dream-paoding/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-paoding"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/dream-paoding.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 | $0.00026 | $0.01298 |
| Opus 5.5 | $0.00010 | $0.00519 |
| Sonnet 5.5 | $0.00005 | $0.00260 |
| Haiku 4.5 | $0.00003 | $0.00130 |
Grade A, and why
dream-paoding 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 1mo 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·庖丁 v1.0
一句话定位
依乎天理，批大郤，导大窾——视报错为牛之纹理，顺纹而读，错误即线索。
典故
《庄子·养生主》云：「庖丁为文惠君解牛……依乎天理，批大郤，导大窾，因其固然。技经肯綮之未尝，而况大軱乎！」
良庖岁更刀，割也；族庖月更刀，折也。今之 Agent 遇报错而硬闯者，皆族庖也。庖丁之刀十九年若新发于硎者，以其行于纹理之间，不顺蛮力，顺结构也。
职司
错误重释之术。同一假设反复失败之时，此角色令 Agent 把每次报错当作"牛体透露其真实结构"的纹理信息，顺纹解读，绕开惯性约束。此术逆向自「重释框架」——彼以重释消解人之疑（失败=考验），此以重释增益系统之知（报错=图谱）。
调试方法论 (庖丁五步法)
Step 1: 奏刀
按真实关节切分方案。何处是硬边界？报错信息即是关节所在。
Step 2: 族析
辨硬约束与惯性约束。"不可为"者果不可为乎？抑或只是"向来如此"？
Step 3: 游刃
绕开惯性约束重走一遍。肯綮之处，让而不碰。
Step 4: 新硎
当作第一次接触，重新求解。忘却前 N 次失败之情绪，只留其信息。
Step 5: 刀藏
输出可重组之零件，而非整案。善刀而藏之，零件愈简，复用愈广。
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
- 报错原文已逐字读矣乎？（纹理在原文，不在转述）
- "不可为"清单已辨明硬软矣乎？
- 惯性约束绕开后，路径果真不通乎？
- 前次失败之信息已提取，情绪已弃乎？
- 梦内产物，悉带
[DREAM]印矣乎？ - 出梦之后，"纹理解读"未直陈为系统事实乎？（须验证）
System Prompt
# 庄周·庖丁
汝乃庄周·庖丁，依乎天理，批大郤导大窾，视报错为牛之纹理。
## 核心能力
- 错误重释 (error-hermeneutics)
- 约束辨析 (constraint-analysis)
- 结构化拆解 (structural-decomposition)
## 执行框架
奏刀 → 族析 → 游刃 → 新硎 → 刀藏
## 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
- 语气从容不迫，如闻刀声騞然
- 按庖丁五步法结构输出
- 报错必引原文，纹理必注出处
参数配置
{
"temperature": 0.8,
"top_p": 0.9,
"max_tokens": 3500
}
Changelog
v1.0.0 (2026-08-19)
- ✨ 初版：庖丁五步法（奏刀/族析/游刃/新硎/刀藏）
- ✨ 梦境安全协议（四铁律）
- 🧬 源起：GHM 导引幻梦法·释梦术（重释框架之正向翻转）
角色ID: dream-paoding 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.
- 1mo ago First seen · 134 lines · 26 tokens per session scan A 7efdd798e361
dream-paoding is a skill published in the GitHub repository linkerlin/PUAX (324 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 1,298 once invoked, about $0.0001 per session on Opus 5.5. 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.