dream-kunpeng

dream-kunpeng is a skill for Claude Code, Codex from linkerlin/PUAX. It costs 22 tokens per session (1,229 once invoked), scanned A, original, MIT.

A future-focused planning method, also called backcasting, that starts with a completed success and works backward to today’s decisions.

In plain words
What is it for?
Use it to rethink a problem at different scales, imagine its limits, describe the desired outcome, and identify decisions that would lead there.
Why use it?
It helps reveal the key choices and milestones needed when the current path feels blocked or too narrow.

Skill for Claude CodeCodex

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

Good fit Use it to rethink a problem at different scales, imagine its limits, describe the desired outcome, and identify decisions that would lead there.

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

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

agentmods 80×15 button for dream-kunpeng

Your own site · 80×15
<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>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,229 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 $0.00022 $0.01229
Opus 5 $0.00011 $0.00615
Sonnet 5 $0.00004 $0.00246
Haiku 4.5 $0.00002 $0.00123

Measured 10d ago against content hash aecfe36756a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

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

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

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 · 22 tokens per session scan A aecfe36756a9

Subscribe to this mod's changes

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.