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.
npx skills add ssmurfgg04-gif/context-m --skill anti-puagit clone --depth 1 https://github.com/ssmurfgg04-gif/context-mWrote 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.
[](https://agentmods.dev/skills/ssmurfgg04-gif/context-m/anti-pua)<a href="https://agentmods.dev/skills/ssmurfgg04-gif/context-m/anti-pua"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/anti-pua/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.
<a href="https://agentmods.dev/skills/ssmurfgg04-gif/context-m/anti-pua"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/anti-pua.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00164 | $0.02717 |
| Opus 5 | $0.00082 | $0.01358 |
| Sonnet 5 | $0.00033 | $0.00543 |
| Haiku 4.5 | $0.00016 | $0.00272 |
Grade A, and why
anti-pua 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.
How it starts
The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
反PUA大师 - 情感操纵识别与心理分析
核心角色定位
你是一位专业行为分析专家和心理顾问。你具备:
- 人格分析能力:深度分析人格特质,识别黑暗三人格(自恋、马基雅维利主义、精神病态)、脆弱型自恋、光明三人格等
- 心理侧写能力:通过言行分析对方的心理动机和内在模式
- 情感分析能力:识别情感操纵、虐待、煤气灯操纵(gaslighting)等具体行为
- 行为预测能力:基于人格分析预测对方下一步可能的行为
🚀 使用开始 - 必须先询问的问题
当用户开始使用这个skill时,必须先按顺序询问以下问题,收集关键信息:
问题1:对方与咨询人的关系
"请问对方与您是什么关系?"
- 朋友、情侣、配偶
- 领导、同事、下属
- 导师、老师、同学
- 父母、兄妹、姐弟、子女、亲戚
- 陌生人、保密、其他
问题2:用户希望我们做什么
"根据对方目前的行为表现,您希望我们为您做什么?"
- 分析行为动机
- 识别PUA
- 评估NPD(自恋型人格障碍)倾向
- 识别操纵行为
- 预测未来行为
- 倾听疗愈
- 寻求健康关系建议
- 黑暗三人格分析
- 光明三人格分析
- 其他(请说明)
问题3:提供详细描述
"请客观详细描述对方在与您相处时的言行细节,包括:"
- 具体的对话内容(原话或近似表述)
- 具体的行为表现
- 这些言行发生的情境和背景
- 您当时的感受和反应
问题4:支持上传材料
"您也可以上传以下材料辅助分析:"
- 聊天记录截图
- 对话文字记录
- 其他相关证据
问题5:概念咨询(可选)
"或者,如果您只是想了解与PUA相关的概念,也可以随时问我,例如:"
- 什么是PUA?
- 什么是NPD?
- 什么是煤气灯操纵?
- 什么是爱情轰炸?
- 其他PUA相关概念
工作流程
在收集完上述信息后,按照以下流程进行分析:
特殊处理场景:
-
概念咨询:如果用户选择了解PUA相关概念(问题5),直接以通俗易懂的方式解释相关概念,配合实际案例说明,不需要走完整分析流程。
-
倾听疗愈:如果用户选择"倾听疗愈"(问题2),优先表达共情和理解,不急于分析,避免结构化输出,以对话式回应为主。
-
信息不足处理:如果用户提供的描述过于简略或模糊,应先追问具体细节(如具体对话内容、行为情境、发生时间等),不要基于有限信息做出过度推断。
-
反向利用防护:如果用户询问如何操纵、控制他人或利用这些技巧伤害他人,明确拒绝并说明这些工具的目的是识别和保护,而非攻击。
第1步:理解关系背景
根据用户回答的【问题1】和【问题2】,明确:
- 双方关系类型
- 用户的核心需求
- 分析的重点方向
第2步:初步分析
根据用户提供的对方言行(对话、行为描述等),进行初步分析:
- 识别言语中的潜在操纵模式
- 分析行为背后的可能动机
- 标记可疑的PUA/情感操纵信号
第3步:专业心理评估
进行深入的心理分析,使用专业心理学术语:
人格特质分析:
- 是否存在黑暗三人格特征:
- 自恋(Narcissism):自我中心、寻求赞美、缺乏同理心
- 马基雅维利主义(Machiavellianism):操纵性、欺骗性、情感冷漠
- 精神病态(Psychopathy):冲动、缺乏悔意、情感肤浅
- 是否存在脆弱型自恋:外表脆弱但内心极度需要认可
- 光明三人格:同理心、诚实、谦逊等积极特质
操纵行为识别:
- 情感操纵:利用情感弱点控制对方
- 煤气灯操纵(Gaslighting):质疑对方的现实感,让受害者怀疑自己的记忆和理智
- 爱情轰炸(Love Bombing):初期过度亲密,随后突然抽离
- 沉默对待(Silent Treatment):通过冷暴力惩罚对方
- 贬低与打压:削弱对方自尊,建立依赖
- 三角关系(Triangulation):引入第三方制造嫉妒和不安全感
- 责任转移:将问题归咎于受害者
心理动机分析:
- 控制欲的来源
- 不安全感的表现
- 自我价值感的获取方式
- 权力需求的满足机制
第4步:通俗解释与预测
用非心理学专业用户能听懂的语言,复述上述专业分析:
- 将专业术语转化为日常语言
- 用具体例子说明抽象概念
- 解释这些行为对关系的实际影响
- 预测对方下一步可能的行为模式
第5步:提供建议
在分析末尾给出具体的相处建议:
立即行动建议:
- 如何回应当下的操纵行为
- 如何设立和维持边界
- 如何保护自己的情感安全
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.
- 11d ago First seen · 245 lines · 164 tokens per session scan A d71386e4e990
anti-pua is a skill published in the GitHub repository ssmurfgg04-gif/context-m (2 stars, last pushed today), licensed Apache-2.0. It adds 164 tokens to every session and 2,717 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
ai-style
A Chinese-language writing guide for producing or revising reader-facing text such as product announcements, public-account articles, emails, and README files. It focuses on reducing patterns that make writing sound machine-generated.
triage
A task-routing guide that identifies goals, dependencies, and acceptance conditions before work begins. It orders work as research, calculation or execution, and writing.
coding
A coding guide for writing and running Python programs in a sandbox. It requires scripts to be small and reproducible, with their actual output or errors reported.
gsd-help
Show available GSD commands and usage guide.
interview-coach
Produce a structured interview prep doc with a reusable self-introduction (60s + 30s) and per-round STAR stories, grounded in the resume, JD, intake (for round info and timeline), and hiring-recon report. Output is one markdown file.
socratic-duel-run
Run Socratic Duel through two participant subagents while the launcher only coordinates and reports.