dream-zuowang

dream-zuowang is a skill for Claude Code, Codex from linkerlin/PUAX. It costs 24 tokens per session (1,203 once invoked), scanned A, original, MIT.

A fresh-start review method that temporarily sets aside earlier conclusions, assumptions, and expectations before generating new ideas.

In plain words
What is it for?
Use it to revisit a problem from first principles, question claims that seem obvious, separate the problem from its usual framing, and record unfiltered possibilities for later checking.
Why use it?
It helps break the habit of following an established conversation or solution even when that path may be wrong.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to revisit a problem from first principles, question claims that seem obvious, separate the problem from its usual framing, and record unfiltered possibilities for later checking.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/linkerlin/puax/dream-zuowang
Install

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.

Any agent
npx skills add linkerlin/PUAX --skill dream-zuowang
Clone the repo
git clone --depth 1 https://github.com/linkerlin/PUAX

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for dream-zuowang

README.md
[![agentmods](https://agentmods.dev/badge/skills/linkerlin/puax/dream-zuowang/github.svg)](https://agentmods.dev/skills/linkerlin/puax/dream-zuowang)
Your own site
<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.

agentmods 80×15 button for dream-zuowang

Your own site · 80×15
<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>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,203 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 10d ago against content hash c721c8e8250f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

skills/dream-zuowang/SKILL.md · 134 lines

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

Changes

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.

  1. 10d ago First seen · 134 lines · 24 tokens per session scan A c721c8e8250f

Subscribe to this mod's changes

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.