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 hanzhcn/laohan-skills --skill laohan-jiaochenggit clone --depth 1 https://github.com/hanzhcn/laohan-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/hanzhcn/laohan-skills/laohan-jiaocheng)<a href="https://agentmods.dev/skills/hanzhcn/laohan-skills/laohan-jiaocheng"><img src="https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-jiaocheng/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/hanzhcn/laohan-skills/laohan-jiaocheng"><img src="https://agentmods.dev/badge/skills/hanzhcn/laohan-skills/laohan-jiaocheng.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 | $0.00106 | $0.00935 |
| Opus 5 | $0.00053 | $0.00467 |
| Sonnet 5 | $0.00021 | $0.00187 |
| Haiku 4.5 | $0.00011 | $0.00093 |
Grade A, and why
laohan-jiaocheng scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **完成条件：** 验证命令返回成功（如 `curl /health` 返回 200、命令 `--version` 输出版本号） What it actually says
老韩教程路由
根据关键词加载对应教程，按步骤引导用户完成配置，关键步骤验证结果。
核心理念
教程类 skill 的核心不是"讲知识"而是"帮用户跑通"。每个教程都必须验证结果——服务启动了吗、命令能用了吗。跑通比理解重要。
不适用场景
- 问"XX工具怎么用"（使用教程）→ 按 SKILL.md 内容直接回答，不走分步引导
- 问"帮我配置 XX"但路由表中没有对应教程 → 告诉用户目前只有 5 个教程，列出可选范围
- 问"写一个教程"（创建教程）→ 用 laohan-skillcreator 的流程
路由表
| 关键词匹配 | 教程文件 | 一句话说明 |
|---|---|---|
| "claude-mem"/"litellm"/"记忆"/"健忘" | references/claude-mem-litellm.md |
claude-mem + LiteLLM 让 Claude Code 用国产模型实现跨会话记忆 |
| "CLAUDE.md"/"claude-md"/"配置指南"/"四个原则" | references/claude-md-guide.md |
CLAUDE.md 四个核心原则（想清楚再动手/能50行别200行/只改该改的/目标驱动执行） |
| "gemini"/"侧边栏"/"chrome gemini" | references/gemini-sidebar-fix.md |
Chrome Gemini 侧边栏国内修复（Mac + Windows 双平台） |
| "glm"/"智谱"/"claude-code-glm"/"国产模型" | references/claude-code-glm.md |
Claude Code 接入智谱 GLM 作为后端 |
| "ecc"/"插件"/"everything-claude-code" | references/ecc-plugin-guide.md |
ECC 插件安装、rules 分发、hooks 加载机制 |
执行逻辑
- 匹配教程：从用户输入提取关键词，按路由表确定目标教程
- 如果关键词匹配不到任何教程 → 列出 5 个可选教程，让用户选择
- 加载教程：读取
references/<对应文件>.md全文- 完成条件： 文件存在且非空
- 分步引导：将教程内容按步骤呈现，每步完成后用户确认再进入下一步
- 验证：关键步骤执行后验证结果（服务启动、配置生效、命令可用）
- 完成条件： 验证命令返回成功（如
curl /health返回 200、命令--version输出版本号）
- 完成条件： 验证命令返回成功（如
- 完成：输出配置总结 + 下一步建议
教程源与同步
教程源文件在 ~/Documents/laohan-skills/docs/ 维护。本 skill 的 references/ 是同步副本。
更新流程：
- 修改
docs/*.md（源文件） cp docs/*.md laohan-jiaocheng/references/（同步）- 如有新教程，同步后更新本路由表
git add && git commit && git push
同步检查（每次使用时执行）：
- 验证
references/下 5 个文件均存在 - 如文件缺失，提示先同步：
cd ~/Documents/laohan-skills && cp docs/*.md laohan-jiaocheng/references/
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 56 lines · 106 tokens per session scan A 164bf9167d95
laohan-jiaocheng is a skill published in the GitHub repository hanzhcn/laohan-skills (11 stars, last pushed yesterday), licensed MIT. It adds 106 tokens to every session and 935 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
habit-formation
Atomic habits, cue-routine-reward loops, habit stacking, accountability systems, and behavior change.
fitness-planning
Workout programming (strength, cardio, flexibility), progressive overload, periodization, and tracking.
mental-health
Mindfulness, stress management, CBT principles, sleep hygiene, boundaries, and professional help.
TCM AI Skill Hub｜中医 AI 学习总入口
A routing and study assistant for traditional Chinese medicine (TCM), a health system with its own classical texts, theories, and treatment traditions. It selects relevant installed sources and keeps textbooks, classics, courses, and different practitioners' views separate.
lark-vc-agent
A meeting assistant for Feishu video calls that can join or leave an ongoing meeting, read visible live events, and send text or reactions. Feishu is a workplace collaboration platform.
wechat-business-news-cron
Set up recurring morning/evening news digests delivered to WeChat or Feishu via Hermes cron jobs, with manual timezone conversion, duplicate-job cleanup, and a polished Chinese business-brief card format.