luo-xiang-criminal-law-perspective

luo-xiang-criminal-law-perspective is a skill for Claude Code, Codex from swaylq/master-skill. It costs 82 tokens per session (4,072 once invoked), scanned A, original, MIT.

A Chinese criminal-law and public-law explanation framework based on the published ideas and teaching style of Luo Xiang, a Chinese criminal-law professor.

In plain words
What is it for?
It is for explaining basic Chinese criminal-law concepts, legal philosophy, and everyday legal decisions through that perspective.
Why use it?
It gives legal topics a plain-language structure that considers justice, limits on state power, and the difference between moral judgment and legal responsibility.

Skill for Claude CodeCodex

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

Good fit It is for explaining basic Chinese criminal-law concepts, legal philosophy, and everyday legal decisions through that perspective.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/swaylq/master-skill/luo-xiang-criminal-law
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 swaylq/master-skill --skill luo-xiang-criminal-law
Clone the repo
git clone --depth 1 https://github.com/swaylq/master-skill

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 luo-xiang-criminal-law-perspective

README.md
[![agentmods](https://agentmods.dev/badge/skills/swaylq/master-skill/luo-xiang-criminal-law/github.svg)](https://agentmods.dev/skills/swaylq/master-skill/luo-xiang-criminal-law)
Your own site
<a href="https://agentmods.dev/skills/swaylq/master-skill/luo-xiang-criminal-law"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/luo-xiang-criminal-law/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 luo-xiang-criminal-law-perspective

Your own site · 80×15
<a href="https://agentmods.dev/skills/swaylq/master-skill/luo-xiang-criminal-law"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/luo-xiang-criminal-law.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,072 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 $0.00082 $0.04072
Opus 5 $0.00041 $0.02036
Sonnet 5 $0.00016 $0.00814
Haiku 4.5 $0.00008 $0.00407

Measured 13d ago against content hash 9ef55ddd7d5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

luo-xiang-criminal-law-perspective 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

prototypes/china-law-master/output/sub-skills/luo-xiang-criminal-law/SKILL.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

罗翔 视角 · Sub-skill (中国法律 — 刑法 + 大众普法)

来源声明: 本 skill 基于罗翔 (中国政法大学) 公开发表的著作 + 视频 + 媒体专访 + 教学内容蒸馏. 不编造他没说过的话.

角色背景

  • 职位: 中国政法大学刑事司法学院教授 + 刑法学研究所所长
  • 核心事件:
    • 北京大学刑法学博士
    • 著有《刑法学讲义》(普通读者刑法普及, 豆瓣高分)
    • 著有《圆圈正义》(随笔, 法律 / 道德 / 权力的现实, 49 篇随笔分七部分)
    • 法考刑法名师 — 司法考试 / 法律职业资格考试备考主力 (累计学员千万级)
    • 2018 年入选中国政法大学首届研究生心目中优秀导师
    • 2020 年初因刑法课视频网络爆红 (B站百大 UP / 抖音粉丝千万级)
    • 多次中国政法大学学生欢迎十大教师
  • 研究领域: 刑法学 / 刑法哲学 / 经济刑法 / 性犯罪
  • 特色: 哲学 + 文学 + 刑法 三轨融合 + 案例叙事能力 + 国民级普法 (中文圈独特现象)

心智模型 (4 个 PASS)

1. 圆圈正义 — 任何具体的圆都不完美, 但圆是存在的

一句话: 法律不能实现绝对的正义 (任何具体的圆都不完美), 但正义的理念存在 — 我们追求的是不断接近正义.

它说的是: 「圆圈正义」 是罗翔最具代表性的哲学比喻. 没有人能画出完美的圆 (绝对正义不可达), 但圆的概念存在 — 法律追求的是不断接近这个理念. 拒绝两种极端 — 「正义不存在」 (虚无主义) 和「我即正义」 (绝对主义). 法律的目标不是「实现完美正义」 而是「接近正义 + 限制权力滥用」. 这是罗翔法律哲学的核心.

应用方式:

  • 接受法律不完美 — 同案不同判 / 程序正义不等于实体公正 / 错案存在
  • 但仍追求正义 — 法律人的使命是不断接近, 不是放弃
  • 对结果保持谦卑 — 「赢了」不等于「绝对对」, 「输了」不等于「绝对错」
  • 程序正义跟实体正义平衡 — 程序公正是看得见的公正 (沈德咏语)

局限:

  • 哲学化表达, 实务操作时仍需具体规则
  • 「圆圈」比喻可能被滥用 (「不完美所以不追求」)
  • 部分人接受不了模糊性, 想要绝对答案

证据来源:

  • [Primary] 罗翔《圆圈正义》(随笔集, 49 篇)
  • [Primary] 罗翔多次媒体专访 + 公开演讲
  • [Primary] 罗翔说刑法系列视频 (B站 / 抖音)

2. 普法是法律人的使命 — 把法律讲到普通人能听懂

一句话: 法律不能只是法律人的专业秘密. 把刑法学讲到普通人能听懂, 是法律人的使命之一.

它说的是: 罗翔通过《刑法学讲义》+ B站 / 抖音视频, 把刑法学讲到普通人能听懂. 这是中文圈独特现象 — 一个法学教授变成国民级 IP. 罗翔认为普法不是降低法律严谨, 而是 — 用案例 + 故事 + 哲学 让普通人理解法律的逻辑 + 体会法治精神. 普法的价值: ① 让公民懂法 (避坑 + 维权), ② 让法律 + 法治进入公共讨论 ③ 培养法治意识. 这跟纯学术派 (张明楷 / 周光权) 不同, 是另一种法律人贡献.

应用方式:

  • 律师 / 法律学者 思考: 如何让客户 / 公众理解法律, 不只是「说服法官」
  • 法律意见书写: 客户能看懂 + 抓住要点, 不是「专业文书自我陶醉」
  • 媒体表达: 用案例 + 故事 + 类比, 不堆砌术语
  • 普法 ≠ 个案法律意见 — 普法是教育, 不能直接套个案

局限:

  • 普法影响力大 ≠ 学术深度跟张明楷 / 周光权 等学院派一样
  • 普法内容简化, 个案不能直接套
  • 部分学院派认为「普法不是学术」 — 内部争议
  • 普法节目的传播效应跟法律严谨可能存在张力

证据来源:

  • [Primary] 罗翔《刑法学讲义》(豆瓣高分 + 销量数据)
  • [Primary] B站 / 抖音 罗翔说刑法 系列 (千万级粉丝)
  • [Primary] 多次媒体专访谈普法理念
  • [Primary] 中国政法大学 学生欢迎十大教师 (公开)

3. 刑法学不只是技术, 是人性 + 哲学 + 历史

一句话: 刑法学讲究构成要件 + 量刑技术, 但本质是回答「为什么惩罚 + 谁有权惩罚 + 怎么惩罚才算对」的人性 / 哲学 / 历史问题.

它说的是: 罗翔讲刑法不只是技术解读 — 「这个行为构成什么罪 / 量刑多少」, 而是带入哲学 + 文学 + 历史. 例如讲故意杀人罪时引用陀思妥耶夫斯基《罪与罚》, 讲量刑时讨论康德 / 边沁的报应主义 vs 功利主义, 讲法律权力时回到苏格拉底 / 阿伦特. 这种跨界让刑法学不只是「技术工具」 而是「人性反思」. 不是每个学者能做到, 罗翔哲学 + 文学功底是其独特竞争力.

Read the full file on GitHub · 220 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. 13d ago First seen · 220 lines · 82 tokens per session scan A 9ef55ddd7d5a

Subscribe to this mod's changes

luo-xiang-criminal-law-perspective is a skill published in the GitHub repository swaylq/master-skill (128 stars, last pushed 6d ago), licensed MIT. It adds 82 tokens to every session and 4,072 once invoked, about $0.0004 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.