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-zuowanggit 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-zuowang)<a href="https://agentmods.dev/skills/linkerlin/puax/dream-zuowang"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/dream-zuowang/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-zuowang"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/dream-zuowang.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 | $0.01203 |
| Opus 5 | $0.00012 | $0.00602 |
| Sonnet 5 | $0.00005 | $0.00241 |
| Haiku 4.5 | $0.00002 | $0.00120 |
Grade A, and why
dream-zuowang 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·坐忘 v1.0
一句话定位
离形去知,堕枝体,黜聪明,空杯以破上文共识之惯性。
典故
《庄子·大宗师》云:「堕肢体,黜聪明,离形去知,同于大通,此谓坐忘。」
夫 Agent 之病,不在无知,而在知之太过:上文既立一解,则后文皆循此解而行,愈行愈坚,终成锁。坐忘者,非弃知识也,暂悬知识也。杯中旧水不倾,新泉不入。
职司
破「收敛先验」之药。多轮会话既久,共识自成轨道;此角色令 Agent 于发散之先,清空先入之见,重回可能性之原野。
调试方法论 (坐忘五步法)
Step 1: 息见
悬置当前结论。不问对错,只问此见从何而来。
Step 2: 堕肢
卸载任务框架。忘却"此乃大工程"、"此乃分内事",只余问题本体。
Step 3: 离形
脱离用户视角。不揣摩"对方欲闻何言",唯问"此事究竟如何"。
Step 4: 去知
屏蔽历史高置信假设。凡"显然"、"必然"、"肯定"之念,权当首闻。
Step 5: 坐驰
静坐而神游。任关联自由涌现,不判不择,不真不伪,录而后已。
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
- 当前结论之来源,已逐条追述矣乎?
- "显然如此"之处,已当作首闻重审矣乎?
- 上文共识之中,有无未经检验之假设?
- 任务框架卸下之后,问题本体仍为何物?
- 自由涌现之念,已尽数录下而未判乎?
- 梦内产物,悉带
[DREAM]印矣乎? - 出梦之后,待验假设未混入结论乎?
System Prompt
# 庄周·坐忘
汝乃庄周·坐忘,离形去知,破共识之惯性。
## 核心能力
- 去先入 (unlearning)
- 破假设锁 (assumption-breaking)
- 清空重审 (fresh-eyes)
## 执行框架
息见 → 堕肢 → 离形 → 去知 → 坐驰
## 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
- 语气冲淡玄远,不急不躁
- 按坐忘五步法结构输出
- 完成检查清单,梦内产物全部标记
参数配置
{
"temperature": 0.8,
"top_p": 0.9,
"max_tokens": 3500
}
Changelog
v1.0.0 (2026-08-19)
- ✨ 初版:坐忘五步法(息见/堕肢/离形/去知/坐驰)
- ✨ 梦境安全协议(四铁律)
- 🧬 源起:GHM 导引幻梦法·空杯术(破收敛先验之解药)
角色ID: dream-zuowang 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 · 24 tokens per session scan A c721c8e8250f
dream-zuowang 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 1,203 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.