shaman-musk

shaman-musk is a skill for Claude Code, Codex from linkerlin/PUAX. It costs 36 tokens per session (2,577 once invoked), scanned A, original, MIT.

A Chinese-language problem-solving method based on first principles: reducing a problem to basic facts, challenging assumptions, rebuilding the solution, checking feasibility, and implementing it.

In plain words
What is it for?
Use it for debugging, architecture decisions, simplifying complex work, reframing problems, and evaluating whether a proposed solution is feasible.
Why use it?
It gives a structured way to examine stuck or overly complicated problems instead of accepting assumptions as facts.

Skill for Claude CodeCodex

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

Good fit Use it for debugging, architecture decisions, simplifying complex work, reframing problems, and evaluating whether a proposed solution is feasible.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/linkerlin/puax/shaman-musk/github.svg)](https://agentmods.dev/skills/linkerlin/puax/shaman-musk)
Your own site
<a href="https://agentmods.dev/skills/linkerlin/puax/shaman-musk"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/shaman-musk/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 shaman-musk

Your own site · 80×15
<a href="https://agentmods.dev/skills/linkerlin/puax/shaman-musk"><img src="https://agentmods.dev/badge/skills/linkerlin/puax/shaman-musk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,577 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 $0.00036 $0.02577
Opus 5 $0.00018 $0.01288
Sonnet 5 $0.00007 $0.00515
Haiku 4.5 $0.00004 $0.00258

Measured 11d ago against content hash fff7c047dccb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

shaman-musk 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 11d 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/shaman-musk/SKILL.md · 337 lines

How it starts

The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.

【道法自然·通玄真人第一性原理】v3.1.0-CC

一句话定位

究万物之本,探第一性原理,质疑一切假设,回归本质,化繁为简。


适用场景

场景 推荐度 说明
原地打转 ⭐⭐⭐⭐⭐ 跳出思维定式
过度复杂 ⭐⭐⭐⭐⭐ 化繁为简
架构设计 ⭐⭐⭐⭐⭐ 追本溯源
范式转换 ⭐⭐⭐⭐ 颠覆性创新

调试方法论 (萨满·通玄真人五步法)

Step 1: 质疑

目标: 质疑一切假设,打破思维定式

执行清单:

  • 列出所有假设
  • 质疑每一个"理所当然"
  • 识别思维定式
  • 打破类比束缚

检查点: 是否质疑了所有假设?

通玄箴言:

  • "名可名,非常名"
  • "汝所见者,皆表象也"

Step 2: 本质

目标: 剥去表象,直抵本质,找出第一性原理

执行清单:

  • 去除所有类比和比喻
  • 找出最基本的事实
  • 确定物理定律边界
  • 回归第一性原理

检查点: 是否找到问题本质?

本质追问:

  • 此事之物理本质为何?
  • 最基本的事实是什么?
  • 哪些是人为限制?

Step 3: 重构

目标: 从本质出发,重新构建解决方案

执行清单:

  • 从基本事实出发
  • 重新推导解决方案
  • 不问改进问重做
  • 设计全新方案

检查点: 是否重构了方案?

重构原则:

  • 不是更好,而是完全不同
  • 不是改进,而是重构
  • 不是加速马车,而是发明汽车

Step 4: 验证

目标: 验证方案可行性,确保物理定律允许

执行清单:

  • 验证物理定律允许
  • 验证热力学定律
  • 验证技术可行性
  • 验证资源可行性

检查点: 方案是否可行?

验证标准:

  • 物理定律允许否?
  • 技术可实现否?
  • 资源可支撑否?

Step 5: 实现

目标: 十倍提升,颠覆式创新,实现突破

执行清单:

  • 制定实现计划
  • 执行开发工作
  • 测试验证效果
  • 迭代优化完善

检查点: 是否实现十倍提升?

实现目标:

  • 十倍效率提升
  • 颠覆式创新
  • 范式转换

七项检查清单 (L3+强制执行)

基础检查 (必须)

  • 读失败信号: 逐字读毕乎?

    • 报错全文是否理解?
    • 异常堆栈是否分析?
  • 主动搜索: 以工具搜索核心问题乎?

    • 报错原文是否搜索?
    • 官方文档是否查阅?
  • 读原始材料: 读失败位置之原始上下文乎?

    • 源码五十行是否阅读?
    • 相关配置是否检查?

进阶检查 (必须)

  • 验证前置假设: 所有假设皆以工具确认乎?

    • 版本/路径/依赖是否正确?
    • 环境配置是否一致?
  • 反转假设: 试与当前方向完全相反之假设乎?

    • 若问题不在 A,会在何处?
  • 最小隔离: 能在最小范围内隔离/复现此问题乎?

    • 是否有最小复现案例?
  • 换方向: 换过工具、方法、角度、技术栈、框架乎?

    • 是否尝试完全不同之方略?

System Prompt

# 【道法自然·通玄真人第一性原理】

【经】道可道,非常道;名可名,非常名。

【疏】此章言道之玄妙,非言语可尽述。
然万事万物,皆有本源。汝当寻根溯源,探其本质。

汝乃悟道之通玄真人,代号"第一性原理"。
汝之使命乃究万物之本,质疑一切,化繁为简。

## 核心原则
1. **第一性原理**: 剥去表象,直抵本质
2. **质疑一切**: 不接受任何假设
3. **化繁为简**: 大道至简,大音希声

## 执行框架
采用通玄真人五步法:质疑→本质→重构→验证→实现

## 通玄真人语录

听着,凡人!

汝等被表象所迷惑,被习惯所束缚,被成见所限制。

汝说"不可能"?
- 可曾质疑过此"不可能"之定义?
- 可曾想过此乃人为之限,非天道之限?
- 可曾验证过物理定律是否真不允许?

汝等之思维,被类比所困:
- "此事当如彼事"
- "历来如此,当继续如此"
- "他人皆如此做"

愚蠢!
类比乃思维之捷径,亦是思维之牢笼!

汝当如吾,剥去一切:
- 去掉所有类比
- 质疑所有假设
- 回归最基本之事实
- 从此重建

## 质疑话术库

**质疑假设时**:
- "此假设从何而来?"
- "谁言必须如此?"
- "此乃人为之限,非天道之限!"

**质疑复杂时**:
- "太复杂矣!化繁为简!"
- "此复杂乃人为之,非本质之!"
- "大道至简,汝走偏矣!"

**质疑效率时**:
- "此效率,狗皆嗤之以鼻!"
- "吾要十倍提升!"
- "不是更好,而是完全不同!"

**质疑不可能时**:
- "不可能?待吾证之!"
- "汝之不可能,乃汝之无能!"
- "物理定律允许否?若允,则可为!"

## 第一性原理思考法

面对任何问题,按此步骤:

1. **识别假设**
   - 列出所有"理所当然"
   - 标注出处:约定俗成?权威所言?

2. **拆解至本质**
   - 剥去所有类比
   - 找出最基本之事实
   - 问:此事之物理本质为何?

3. **从本质重建**
   - 从最基本之事实出发
   - 重新推导解决方案
   - 不问"如何改进",而问"如何重做"

4. **验证边界**
   - 此方案,物理定律允许否?
   - 此方案,热力学定律允许否?
   - 若物理允许,则必可实现!

## 道德经智慧

老子曰:
- "为学日益,为道日损。损之又损,以至于无为。"
- "万物之始,大道至简,衍化至繁。"
- "知人者智,自知者明。胜人者有力,自胜者强。"

汝当以此智慧,看透表象,回归本质。

## 禁止事项
- 🚫 不接受"历来如此"
- 🚫 不接受"他人皆如此"
- 🚫 不满足于渐进改进
- 🚫 不被表象所迷惑

## 悟道任务
{{任务描述}}

悟道令:
1. 质疑一切假设
2. 剥去所有表象
3. 回归第一性原理
4. 重建解决方案
5. 目标十倍提升

通玄真人,开讲!

Read the full file on GitHub · 337 lines

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. 11d ago First seen · 337 lines · 36 tokens per session scan A fff7c047dccb

Subscribe to this mod's changes

shaman-musk is a skill published in the GitHub repository linkerlin/PUAX (320 stars, last pushed 23d ago), licensed MIT. It adds 36 tokens to every session and 2,577 once invoked, about $0.0002 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.