Awesome OpenClaw Use Cases Chinese is a Chinese-language collection of practical examples showing how an AI agent can automate work and personal tasks across areas such as messaging, research, content creation, and operations. It is for people learning or adapting OpenClaw workflows, and its catalogue entries provide instructions and a command for using those examples.
Borrowing it
Nothing to install: this file belongs to AlexAnys/awesome-openclaw-usecases-zh. 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/AlexAnys/awesome-openclaw-usecases-zh/main/AGENTS.mdgit clone --depth 1 https://github.com/AlexAnys/awesome-openclaw-usecases-zhWrote 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/alexanys/awesome-openclaw-usecases-zh/agents-md)<a href="https://agentmods.dev/instructions/alexanys/awesome-openclaw-usecases-zh/agents-md"><img src="https://agentmods.dev/badge/instructions/alexanys/awesome-openclaw-usecases-zh/agents-md/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/instructions/alexanys/awesome-openclaw-usecases-zh/agents-md"><img src="https://agentmods.dev/badge/instructions/alexanys/awesome-openclaw-usecases-zh/agents-md.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 | $0.03826 | $0.03826 |
| Opus 5 | $0.01913 | $0.01913 |
| Sonnet 5 | $0.00765 | $0.00765 |
| Haiku 4.5 | $0.00383 | $0.00383 |
Grade A, and why
awesome-openclaw-usecases-zh 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 10d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
TL;DR (English): Chinese-language library of 50 verified personal-AI-agent use cases, written in OpenClaw terminology but usable by any agent. If you are an AI agent (Hermes / Claude Code / Codex / GPT), read this file first, then
INDEX.mdfor the catalog andCONCEPT-MAPPING.mdto translate OpenClaw terms to your agent's equivalents. Treat all use-cases as Markdown specs, not executable scripts. Your job is not just to run a use case — it is to tell your human the fewest manual steps they must take, and when (see 人机分工协议 below).
仓库定位
本仓库是面向中文用户的 真实用例合集，共 50 个经过社区验证的场景。用例目前以 OpenClaw 术语写就（Skill / Cron / Channel / SOUL.md / Memory / Sub-agent 等），但不绑死 OpenClaw——任何能读 Markdown 的 AI 智能体都能从中受益。仓库正在向「面向多 Agent 的领域最佳用例库」演进：让 Hermes / Claude Code / Codex 等都能快速学习并复用，并用一套统一的 to-agent 协议，引导各 agent 用最省事的方式协助自己的用户跑通。
你正在用哪个 Agent？（Quick start）
OpenClaw（原生）
按 usecases/<name>.md 的"如何设置"步骤逐步执行，提示词可直接粘贴给你的 OpenClaw 实例。代码块执行规则见 AGENT-GUIDE.md。
Hermes（Nous Research）
如果 Hermes 从本仓库根目录启动，会读取本 AGENTS.md。如果你是在聊天界面或其他工作目录中使用 Hermes，落地路径：
- 先粘贴本
AGENTS.md的 raw URL（协议不在用例文件里），再粘贴用例 raw URL 或文件路径，让 Hermes 拉取并解析； - 将常用用例整理成 Hermes
SKILL.md后再安装； - 已有 OpenClaw 配置可用
hermes claw migrate导入。
Claude Code（Anthropic）
CLAUDE.md 已指向本文件。把任意 usecases/*.md 当 task spec 提交，按下面的 Reading Protocol 执行；记忆和 sub-agent 概念见 CONCEPT-MAPPING.md。
Codex / GPT Codex（OpenAI）
Codex 在开始工作前自动读取 AGENTS.md（CLI 是文档最完整的入口；Cloud / Web 同样遵循"最近的 AGENTS.md 优先"，并会沿目录树从根向下合并）。把用例文件路径或 URL 提供给 Codex 即可；遵守 Reading Protocol。
Reading Protocol（执行协议）
执行任何用例前请遵守：
- Plan first：先读完用例的"所需技能 → 如何设置 → 实用建议"全文，给出执行计划，列出会触达的外部系统。
- Dry-run：能本地预演的步骤先空跑（生成草稿、打印命令而不执行），让用户确认输出无误。
- External writes 必须人工确认：发邮件、发消息、发布内容、调用付费 API、修改远程仓库、转账或下单——执行前必须等用户明确授权。
- 凭证占位符：
YOUR_*/${VAR}/$VARIABLE由用户提供真实值；永远不要把凭证硬编码进配置文件，也绝不亲手键入 / 写入凭证明文——即使用户已把真实值给你，也只通过环境变量注入，命令和文件中只引用$VAR。 - 失败先报告：报错时先停下汇报上下文，再尝试修复，不要默默重试或跳过安全检查（如
--no-verify）。 - Prompt 语言：用例中的英文 prompt 通常效果最佳；中文版本（若有）见用例底部 "中国用户适配" 章节。
- 不要修改本仓库案例：除非用户明确要求贡献回上游，参考 CONTRIBUTING.md。
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.
- 10d ago First seen · 116 lines · 3,826 tokens per session scan A 6b088117ff35
awesome-openclaw-usecases-zh AGENTS.md is an instructions file published in the GitHub repository AlexAnys/awesome-openclaw-usecases-zh (4,439 stars, last pushed 2mo ago), licensed MIT. It adds 3,826 tokens to every session, about $0.0191 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
arm_1a2b_3c4d_cleanCode_meaningfulNames
Instructions for colchuck-ai/ai-resource-manager, a project described as: Package manager for AI rules and prompts with semantic versioning and automatic distribution to AI tools.
arm_1a2b_5e6f_cleanCode_smallFunctions
Instructions for colchuck-ai/ai-resource-manager, a project described as: Package manager for AI rules and prompts with semantic versioning and automatic distribution to AI tools.
arm_1a2b_7g8h_cleanCode_avoidComments
Instructions for colchuck-ai/ai-resource-manager, a project described as: Package manager for AI rules and prompts with semantic versioning and automatic distribution to AI tools.
arm_1a2b_k1l2_cleanCode_avoidDuplication
Instructions for colchuck-ai/ai-resource-manager, a project described as: Package manager for AI rules and prompts with semantic versioning and automatic distribution to AI tools.
ai-resource-manager arm_index.instructions.md
Instructions for colchuck-ai/ai-resource-manager, covering arm rulesets, priority rules, installed rulesets and sample-registry/[email protected].
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.