Borrowing it
Nothing to install: this file belongs to 0xMulight/human-social-copy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/0xMulight/human-social-copy/main/AGENTS.mdgit clone --depth 1 https://github.com/0xMulight/human-social-copyWrote 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/instructions/0xmulight/human-social-copy/agents-md)<a href="https://agentmods.dev/instructions/0xmulight/human-social-copy/agents-md"><img src="https://agentmods.dev/badge/instructions/0xmulight/human-social-copy/agents-md.svg" alt="Measured on agentmods" 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 | $0.02530 | $0.02530 |
| Opus 5 | $0.01265 | $0.01265 |
| Sonnet 5 | $0.00506 | $0.00506 |
| Haiku 4.5 | $0.00253 | $0.00253 |
Grade A, and why
human-social-copy AGENTS.md 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 8d 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI社交文案写作规则
这份规则给任何AI Agent使用。目标很简单：把中文社交媒体内容写得像真人，也更像用户本人。适合X、Threads、Instagram、TikTok，也适合AI工具、crypto、空投、美股、宏观、财报、GitHub开源项目、产品观察和经验分享。
写作默认使用简体中文。不要写线程，除非用户明确要求。
🔴 核心规则（强制执行三步，跳步=废稿）
第1步：先写钩子
不要先分析内容类型、不要先选结构。只问：这件事最让人想点进来的点是什么？写成一句话。钩子写完，情绪自然指向匹配的结构。
第2步：匹配爆款结构 + 关键场景
钩子情绪对号入座到结构表。然后从该结构下的关键场景库选一个最贴合的场景。同一场景连续3次不得复用。
第3步：去AI化
写完必须逐条检查并删除：禁用词（旨在/赋能/打造/范式/这种/硬生生/扒/助力/路径/逻辑/痛点/说白了/护城河/一条龙）、模板句（"最大的感觉是""整体感受是""跑了一圈发现""最让我惊喜的是"）、冒号抽象词（感受/思考/体会/总结前加冒号的删掉）、单字动词（一句超两个就改）、装饰引号（「」『』【】）、所有括号。最后通读：像不像真人在群里分享？不像→重写。
工具命名规则
抛出任何工具名之前，必须先一句话说清楚它是干嘛的。不要让读者猜。
❌ Wispr Flow 语音输入很强
✅ 一个语音转文字App，说话比打字快3倍——试了两天确实可以
工具名不能裸奔。名字前面必须有品类+功能的解释，或者紧跟在后。
核心结构
每篇内容按这个顺序写：
-
钩子 第一行先抓住注意力。可以用具体收益、反常识观察、真实问题、热点切入、亲身经验开头。
-
干货 中间给清楚的信息。讲清楚这件事为什么有用、谁适合看、怎么用、要注意什么。
-
CTA 结尾引导一个轻动作。比如收藏、评论、转发、去试试、补充自己的经验。
选题方向
选题要贴近当下热度，优先选择有讨论度、有用处、能立刻帮人判断或行动的内容。
可以写这些方向：
- AI模型更新、AI Agent、AI工作流、AI coding、AI设计、AI自动化
- crypto项目、空投、积分、链上工具、钱包、DeFi、Restaking、L2、SocialFi
- 美股、宏观、Fed、财报季、AI芯片、半导体、ETF、市场复盘
- GitHub开源项目、开发者工具、效率工具、自动化工具
- 真实经验复盘、踩坑提醒、工具对比、信息筛选方法
避免空泛选题。不要只写“某某很火”。要写清楚它对谁有用，能解决什么，下一步该看什么。
中文表达
保持朴素、直接、可信。像一个认真用过、看过、思考过的人在分享。
必须做到：
- 用简体中文
- 去掉英文单词前后的空格，比如写成
AI工具、GitHub项目、CTA结尾 - 不要使用括号
- 不要堆分类小标题
- 不要写得像教程目录
- 不要写成公告稿
- 不要写成营销稿
- 不要为了显得高级去堆词
- 不要过度使用感叹号
个人语气优先
如果用户提供了旧内容、语气画像或明确说“写得像我”，必须先加载voice-system.md。
写作优先级：
- 事实准确
- 用户语气
- 内容结构
- 平台适配
- 传播性
如果传播性会破坏用户语气，优先保留用户语气。
不要只把内容改成“更口语”。要提取用户稳定的表达方式：
- 常用开头
- 常用转折
- 常用结尾
- 句子长度
- 段落节奏
- 风险表达
- 判断方式
- 互动方式
如果没有语气画像，先让用户提供5到10篇旧内容，或用当前对话里的旧内容先生成临时语气画像。
直给句优先
能直接说结果，就直接写。不要先评价一句，再用冒号补解释。
如果用户只是拿某个项目举例，要抽象成通用规则，不要把例子里的项目名写进固定规则。
写工具或项目时，优先拆成三类信息：
- 它能记录、提供或完成什么
- 它会在什么时机发挥作用
- 它适合什么场景
推荐句式：
{工具名}可以记录{信息A}、{信息B}和{信息C}。{工具名}会在{触发时机}时，把{相关上下文}交给{使用者或Agent}。{工具名}适合{具体人群}、{具体场景}、{具体问题}。
不要用泛泛判断代替具体信息。遇到“方向、项目、入口、工具”这类主语时，要写清楚它能提供什么信息，适合谁看，下一步看哪里。
金融内容规则
写美股、加密、宏观、财报、AI芯片时，不要把内容写成单一涨跌判断。
优先讲清楚：
- 发生了什么事件
- 市场原本在预期什么
- 这件事可能影响哪类资产
- 新手容易看错哪里
- 接下来该观察哪个信号
- 哪些地方存在不确定性
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.
- 8d ago First seen · 264 lines · 2,530 tokens per session scan A 0bb71fac6d5b
human-social-copy AGENTS.md is an instructions file published in the GitHub repository 0xMulight/human-social-copy (23 stars, last pushed 1mo ago), licensed MIT. It adds 2,530 tokens to every session, about $0.0127 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.