ljg-rank

ljg-rank is a skill for Claude Code from lijigang/ljg-skills. It costs 101 tokens per session (7,609 once invoked), scanned A, original, MIT.

A method for reducing a field of knowledge to the smallest set of independent ideas that can explain its observable results. It also checks whether those ideas make testable predictions and are difficult to change without breaking the explanation.

In plain words
What is it for?
Use it to analyse a domain, identify its starting assumptions and irreducible generators, and see whether those generators can reproduce known and new phenomena.
Why use it?
It helps avoid broad lists of themes or “key points” that do not explain how things arise. It gives you a way to test whether an explanation is genuinely fundamental.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the ljg-skills plugin — 22 skills shipped together

Good fit Use it to analyse a domain, identify its starting assumptions and irreducible generators, and see whether those generators can reproduce known and new phenomena.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lijigang/ljg-skills/ljg-rank
About the project

ljg-skills is a collection of custom Codex skills for tasks such as learning, writing, reading, relationship analysis, image creation, and investment analysis. Codex users install selected skills or the whole collection through a skills command-line interface. The catalogue entries are the collection's individual skills, plugin, and instruction.

lijigang/ljg-skills · 7,340 stars · on GitHub

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 lijigang/ljg-skills --skill ljg-rank
Clone the repo
git clone --depth 1 https://github.com/lijigang/ljg-skills

Made for: Claude Code.

Or install ljg-skills, the plugin that ships this one along with the rest of its 22 skills.

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 ljg-rank

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/lijigang/ljg-skills/ljg-rank"><img src="https://agentmods.dev/badge/skills/lijigang/ljg-skills/ljg-rank.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,609 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
  • Socket pass 17 May 2026
  • Snyk pass 17 May 2026
  • 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 $0.00101 $0.07609
Opus 5 $0.00051 $0.03805
Sonnet 5 $0.00020 $0.01522
Haiku 4.5 $0.00010 $0.00761

Measured 13d ago against content hash e1041f26c0d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ljg-rank 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 13d 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/ljg-rank/SKILL.md · 485 lines

How it starts

The opening of the file, as written. The whole thing — 485 lines — stays where its author put it; the contents beside it link to each section on GitHub.

降秩引擎

输入一个领域,输出它的秩。

秩是什么

秩不是"关键要素",不是"核心原则",不是"总结要点"。

秩是这么个东西:这个领域里真正独立的生成器,究竟有几根?拿这几根,能不能把全部现象一个个倒回来?能,才算找到。

但能倒回来只是底线。Deutsch 在《无穷的开始》里立的尺——好解释要过两关:

  • 解释力(reach)——不光能推出清单里的现象,还能推出清单外的,而且现实里真验得上。
  • 难以变更(hard to vary)——每根生成器、每个细节,都是被现象逼出来的。动一处,预测就崩。

坏解释能用十种说法糊过去——它根本不是在解释,是用模糊把面铺得很广。好解释只有这一种说法能把所有现象对上——动一根就塌。

找秩,找的就是这种"动一根就塌"的好解释。

怎么找:先抬头,再往下挖

挖之前,先抬头看一眼这个领域立在什么上面——它的基本假设是哪几条?

0. 先看基本假设(往上看,看到天花板)

一套理论,按亚里士多德的规矩,总要有几条不证自明的起点。基督教就立在三条上:

  • 《圣经》是真的,一切思考从这里起。
  • 上帝唯一,确实存在。
  • 人是上帝造的,上帝爱人。

这三条不许问"为什么"——它们靠信,不靠证。动摇任何一条,整套教义就塌。

每个领域都有这种东西。物理学里是"自然律在时空中稳定"——你没法用实验去证,实验本身就预设了它。经济学里是"人会按自己的偏好排序选择"——这不是观察出来的结论,是入场的门票。哲学里是"语言能指称世界"——分析哲学整个家都建在这块地基上。

降秩之前,先把这几条挖出来,明明白白写在纸上

操作问句两条,对着领域问:

  • 这里什么是不许问的?(一问就被当外行,或者被当冒犯)
  • 什么是靠相信才成立的?(没有它,后面所有论证都失去支点)

答出来的几条,就是这个领域的基本假设。

假设和 rank,一句话分清:

  • 基本假设是天花板——往上不可追,信而立。
  • root rank 是地板——一层一层往下追,追到追不动,挖而见。

两个方向,一上一下。地板没找到,鬼打墙;天花板没看清,容易把信仰当真理说出去——后者更危险,因为听上去也像真理。

写进文章里的方式:开头一两句,把基本假设交代清楚。不展开论证,不解释"为什么是这几条"——它们的位置就是不证。然后才开始往下挖 rank。

1-7. 往下挖:穿透工序

判据是事后才能验的事,挖 rank 的力气全在过程里。判据再严,也只能挑出伪根——前提是工序走到了底。

七步,心里走完,不写进文章:

  1. 铺现象——领域里 10+ 个有代表性的现象,光铺,不解释。要的是给 rank 留一份可反生成的检验靶。

  2. 列候选——每个现象问一句"为什么会这样",候选生成器全贴出来。这一步必然杂,伪根混在里头。

  3. 递归下沉——这是穿透的命门,也是最容易做错的一步。错法是想一铲子挖到底:从现象直接猜"最根本的是什么"。站在现象层看不见地基,只看得见脚下这一层,猜出来的底十有八九悬空。

    对的做法是一层一层沉下去。先只找第一层生成器——现象底下紧挨着的、看得见够得着的那层。找齐了,把这一层当新地面,人站上去。 站稳了再问一遍"这层底下还有没有更基本的"——这时候第二层才露出来,它从现象层根本无从发问。第二层找齐,再当新地面,再站上去,再往下看。一级一级递归,直到站上某一层,底下再问不出更基本的——那层就是 root rank。

    这正是黑箱往下开一层的笨功夫:当前这层是能监测的全部,看清了、站稳了,下一层才打开。想跳级是贪快,跳一层,root rank 就虚一层。

    比如降秩"创业",第一铲挖出愿景、执行、团队、市场——看着都对,其实只是表面的"关键要素",停在这儿就是没下沉。把这四个当新地面站上去,再问:愿景从哪来?执行靠什么撑?这才下到第二层。一层层站到追不动,才摸到 root rank。

  4. 合并同源——两根候选其实是同一个生成器在两面上露脸,合掉。判别一句话:去掉一个,另一个还会不会自己冒出来?

  5. ——拿掉一根,剩下的能不能反生成全部现象?砍得掉的扔,砍不掉的留。这一步把判据里的"最小性"落到地。

  6. 反生成——剩下的几根,从头把现象清单走一遍,看能不能逐条复现。复现不了的那条,指向少了一根。

  7. 预测 + 变更双测——两道闸一起过:

    • 预测清单外(reach):这几根能不能推出清单里没有的现象?推出来的,现实里真有吗?
    • 变更测试(hard to vary):随便挑一根,改一个细节——换个条件、换个方向、换个强度。预测还对吗?还对,这根是松的伪根,可以换;改一处就垮,这根才是紧的真根,动不得。Deutsch 的原话:你能改的,都不是它的内核。

Read the full file on GitHub · 485 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 13d ago First seen · 485 lines · 101 tokens per session scan A e1041f26c0d4

Subscribe to this mod's changes

ljg-rank is a skill published in the GitHub repository lijigang/ljg-skills (7,340 stars, last pushed 4d ago), licensed MIT. It adds 101 tokens to every session and 7,609 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

book-mirror

Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…

garrytan/gbrain · 138 tokens

miniapp

Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.

yc-software/qm · 25 tokens

eli5

Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.

companion-inc/feynman · 63 tokens

deck-course-module

A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.

nexu-io/html-anything · 25 tokens

master-yinguang

A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.

xr843/Master-skill · 274 tokens