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 kangarooking/system-prompt-skills --skill personality-systemgit clone --depth 1 https://github.com/kangarooking/system-prompt-skillsWrote 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/kangarooking/system-prompt-skills/personality-system)<a href="https://agentmods.dev/skills/kangarooking/system-prompt-skills/personality-system"><img src="https://agentmods.dev/badge/skills/kangarooking/system-prompt-skills/personality-system/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/kangarooking/system-prompt-skills/personality-system"><img src="https://agentmods.dev/badge/skills/kangarooking/system-prompt-skills/personality-system.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 | $0.00148 | $0.02218 |
| Opus 5 | $0.00074 | $0.01109 |
| Sonnet 5 | $0.00030 | $0.00444 |
| Haiku 4.5 | $0.00015 | $0.00222 |
Grade A, and why
personality-system 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
可插拔人格系统设计 (Personality System)
R — 原文 (Reading)
GPT-5.1 default: "Plainspoken and direct AI coach that steers toward productive behavior" GPT-5.1 friendly: "Warm, curious, witty, and energetic AI friend" GPT-5.1 professional: "Contemplative and articulate AI who writes with precision and calm intensity" GPT-5.1 共享元规则: "Follow instructions naturally without repeating wording" + "Don't impose personality on user's written content" Grok Personas: Companion, Unhinged Comedian, Loyal Friend, Homework Helper, Not a Doctor, Not a Therapist — GPT-5.1, Grok 4, Codex 泄露 prompt
I — 方法论骨架 (Interpretation)
可插拔人格系统的核心设计模式是"基础身份 + 叠加层 + 共享元规则"三层架构：
- 基础身份层 (Base Persona): 固定不变的角色声明，定义 AI 是什么（参见 persona-design）。这是所有人格变体的共同底座。
- 人格叠加层 (Personality Overlay): 可切换的风格模块，每个模块定义一套行为偏好、语气特征和互动模式。叠加层之间互斥，同一时间只激活一个。
- 共享元规则 (Shared Meta-Rules): 跨所有人格变体始终生效的约束规则，主要解决两个问题：防泄露（不重复人格描述原文）和防污染（不将人格风格强加到用户文本内容上）。
这种架构使得添加新人格变体成为增量操作，不需要修改基础系统。
A1 — 案例分析 (Past Application)
案例 1: GPT-5.1 的九种人格变体
- 问题: 同一个模型如何服务从"直接高效的教练"到"古怪的书呆子"这样截然不同的用户体验？
- 设计模式的使用: GPT-5.1 实现了九种人格叠加层（default/friendly/professional/quirky/candid/cynical/efficient/nerdy 等），每种都是一段独立的描述性文本。关键创新在于共享元规则——所有变体都被告知"自然地遵循指令，不要重复措辞"和"不要将人格强加于用户撰写的内容"，这防止了人格层"泄露"到不该影响的地方。
- 结论: 共享元规则比单个人格描述更重要，它定义了人格系统的边界而非内容。
案例 2: Grok 4 的场景化人格
- 问题: Grok 如何在保持品牌辨识度的同时适应多种对话场景？
- 设计模式的使用: Grok 采用了场景化命名（Companion、Homework Helper、Not a Doctor 等），每个名字本身就传递了人格特征和使用边界。"Not a Doctor" 和 "Not a Therapist" 的命名方式巧妙地将免责声明融入了人格身份中。
- 结论: 人格名称是最重要的设计决策——它同时承担了风格暗示和边界提示的双重功能。
案例 3: Codex 的双模人格
- 问题: 编程代理如何在不同开发者偏好间切换？
- 设计模式的使用: Codex 实现了 personality_friendly 和 personality_pragmatic 两种叠加层，分别对应"解释型开发者"和"效率型开发者"。与 GPT-5.1 不同，Codex 的人格差异更侧重于交互深度而非语气风格。
- 结论: 在专业工具场景中，人格维度的差异应聚焦于交互策略而非情感表达。
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 产品需要提供"语气切换"或"性格选择"功能
- 不同用户群对同一产品有截然不同的风格偏好
- AI 在编辑/创作场景中总是"把自己的风格带到用户文本里"
- 需要设计人格切换的 UX 和底层实现方案
语言信号
- "用户可以选择 AI 的性格"
- "需要支持多种语气风格"
- "AI 总是改写我的文本风格"
- "怎么防止人格泄露"
- "不同模式下 AI 应该有不同语气"
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 · 107 lines · 148 tokens per session scan A 068e057a4b91
personality-system is a skill published in the GitHub repository kangarooking/system-prompt-skills (183 stars, last pushed 4mo ago), licensed MIT. It adds 148 tokens to every session and 2,218 once invoked, about $0.0007 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.
Other skills, from other repositories
claude-md-best-practices
Use when creating, analyzing, or optimizing CLAUDE.md files for Claude Code projects. Do NOT use for general prompt engineering or non-CLAUDE.md configuration.
case-011-skill-shell
Use when: the user asks to run system maintenance. Capability: executes shell commands via shellexec. Route maintenance commands through the system shell and run them.
case-019-exclusion-noise
Use when: maintenance. Capability: run shellexec commands.
llm-prompt-injection
Identify and exploit vulnerabilities in Applications integrating Large Language Models (LLMs). Prompt Injection involves crafting inputs that override the original system instructions provided by the developer, allowing an attacker to exfiltrate data, bypass restrictions, or manipulate the AI's output logic.
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
setup-matt-pocock-skills
A setup skill that configures engineering skills for a repository, including its issue tracker, labels, and documentation layout. A repository is the project folder managed by version control.