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 joeseesun/qiaomu-blog-opensource --skill qiaomu-blog-publish-skillgit clone --depth 1 https://github.com/joeseesun/qiaomu-blog-opensourceWrote 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/joeseesun/qiaomu-blog-opensource/qiaomu-blog-publish-skill)<a href="https://agentmods.dev/skills/joeseesun/qiaomu-blog-opensource/qiaomu-blog-publish-skill"><img src="https://agentmods.dev/badge/skills/joeseesun/qiaomu-blog-opensource/qiaomu-blog-publish-skill/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/joeseesun/qiaomu-blog-opensource/qiaomu-blog-publish-skill"><img src="https://agentmods.dev/badge/skills/joeseesun/qiaomu-blog-opensource/qiaomu-blog-publish-skill.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 | $0.00037 | $0.01364 |
| Opus 5.5 | $0.00015 | $0.00546 |
| Sonnet 5.5 | $0.00007 | $0.00273 |
| Haiku 4.5 | $0.00004 | $0.00136 |
Grade A, and why
qiaomu-blog-publish 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 28d 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.
curl -s "https://your-domain.com/api/admin/categories" \ How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
qiaomu-blog-publish: 发布内容到 Qiaomu Blog
触发方式
Slash command:
/qiaomu-blog-publish path/to/file.md/qiaomu-blog-publish https://example.com/article/qiaomu-blog-publish然后粘贴 Markdown 或正文
自然语言:
- “发布到博客”
- “发布成草稿”
- “发到 Qiaomu Blog”
- “把这篇文章发到自己的博客”
- “publish to blog”
- “publish draft”
配置
API Base URL: https://your-domain.com
Token 读取优先级:
- 环境变量
QIAOMU_BLOG_API_TOKEN - 环境变量
QMBLOG_API_TOKEN(兼容旧配置) - 配置文件
~/.claude/skills/qiaomu-blog-publish/config.json
如果没有 token,提示用户:
- 打开
https://your-domain.com/admin/settings - 在
API Token页面生成 token - 保存到:
{
"apiUrl": "https://your-domain.com",
"token": "qm_xxx"
}
工作流
1. 判断输入来源
- 文件路径:读取本地 Markdown 或文本文件
- URL:抓取正文并转成 Markdown
- 纯文本:直接作为正文使用
2. 读取配置
优先读取环境变量;如果没有,再读取 config.json 中的 apiUrl 和 token。
3. 拉取分类
curl -s "https://your-domain.com/api/admin/categories" \
-H "Authorization: Bearer $TOKEN"
让用户选择分类;如果不选,可以留空,后续再在后台调整。
分类接口返回 { name, slug }。发布到 /api/posts 时,category 字段应传所选分类的 name,不要传 slug。例如传 AI资讯,不要传 ai-news;slug 只用于分类 URL 和本地匹配。
4. 解析内容
标题优先级:
- YAML frontmatter 的
title - 第一条
# Heading - 文件名
正文处理:
- 去掉 frontmatter
- 如果标题来自第一条
# Heading,则移除这条 heading,避免重复 - 其余 Markdown 原样保留
5. 上传本地媒体
需要识别这些引用:
![[image.png]]- 音频 / 视频 / 附件本地路径
上传接口:
curl -s -X POST "https://your-domain.com/api/uploads" \
-H "Authorization: Bearer $TOKEN" \
-F "file=@/absolute/path/to/file"
拿到返回 URL 后,替换正文中的本地引用。
6. 转存第三方图片
如果 Markdown 中有第三方远程图片:
- 先下载到临时文件
- 再上传到博客
- 替换成博客自己的图片 URL
如果下载失败,保留原图 URL,并在最终结果里提示。
7. 让用户确认发布参数
确认三件事,若用户要求更新已有文章,还要确认目标 slug:
- 标题
- 分类
- 状态:
draft或published
默认用 draft。
8. 发布或更新
curl -s -X POST "https://your-domain.com/api/posts" \
-H "Authorization: Bearer $TOKEN" \
-H "Content-Type: application/json" \
-d '{
"title": "The Title",
"content": "Full processed Markdown content",
"category": "selected-category-name-or-empty",
"status": "draft"
}'
What ships with it
1 file 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.
- 28d ago Changed · +30 lines 93691a30b8e3
- 2mo ago First seen · 163 lines · 37 tokens per session scan A e6e70634931e
qiaomu-blog-publish is a skill published in the GitHub repository joeseesun/qiaomu-blog-opensource (301 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 1,364 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
qiaomu-blog-publish compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| qiaomu-blog-publishjoeseesun/qiaomu-blog-opensource | Skill | 301 | yesterday | MIT | A | 37 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |