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 agentmods add skills/childrentime/reactuse/publish-mediumnpx skills add childrentime/reactuse --skill publish-mediumgit clone --depth 1 https://github.com/childrentime/reactuseWhat 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 | $0.00137 | $0.03763 |
| Opus 5 | $0.00068 | $0.01881 |
| Sonnet 5 | $0.00027 | $0.00753 |
| Haiku 4.5 | $0.00014 | $0.00376 |
Grade A, and why
publish-medium 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 3d 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
publish-medium — 跨发到 Medium（opencli 浏览器自动化）
reactuse.com 的博客在 Medium 上做镜像分发，扩大英文触达。Medium 是真实增量流量（推荐流 + 订阅者收件箱）。
⚠️ 路径：opencli 浏览器自动化（已取代旧的 bridge + 扩展方案）
历史：2026-06 之前用的是本地 Bridge 服务 + Chrome 扩展（
medium-pushskill，靠 SSE 推 markdown 到扩展、扩展转 HTML 再模拟粘贴）。现在统一走opencli，和publish-hashnode一致，不再需要那套 bridge。旧 skill 已删除。
核心难点：Medium 的编辑器（.js-postField，contenteditable + 自有数据模型）不解析 markdown。直接 fill markdown 文本只会得到一坨纯文本。正确做法和那个旧扩展一样——把 markdown 转成 HTML，然后模拟一次 paste 事件（带 text/html 的 DataTransfer），Medium 的粘贴处理器会把 HTML 正确吃进它的模型。标题则用 execCommand("insertText") 灌（Medium 模型只认"输入"路径，直接写 DOM textContent 不进模型）。
触发场景
- 用户明说："发到 medium" / "publish to medium" / "把这篇 cross-post 到 medium"
- 刚写完一篇博客并说"发出去" / "同步发布" / "推平台"——默认包括 Medium
- 多平台分发流程的一步（dev.to + Medium + Hashnode + 掘金）
⚠️ 不要触发：用户只让发别的平台（只发 Hashnode / 掘金 / dev.to）时，不要顺手也发 Medium。
⚠️ 顺序：先推 GitHub，再跨发
英文跨发（Medium / Hashnode / dev.to）的 canonical 都指回 reactuse.com/blog/<slug>/。必须先把博客 commit + push 到 GitHub（触发 Netlify 部署），让原文链接真的存在，再发跨平台版本——否则 canonical 指向一个 404。掘金是中文翻译、独立站，不受此约束。
注：Medium 原生编辑器没有 canonical 字段（只有 Import 流程才有）。所以 Medium 这篇本身不会把权重让回 reactuse.com——它纯粹是触达渠道。这是已知取舍，不用纠结；旧的 bridge 方案同样没设 canonical。
前置检查
opencli --version # 需要 ≥ 1.7.22
opencli doctor # 必须看到 Connectivity: connected
command -v pandoc # 正文 markdown→HTML 靠 pandoc；没有就 brew install pandoc
如果 Connectivity: failed：让用户把 Chrome 切到前台、点一下 opencli 扩展图标唤醒 service worker，再 opencli doctor。
工作流程
步骤 1：确认目标文章 + 元数据
ls packages/website-astro/src/content/blog/ | tail -3
从 blog-external/post-N-<slug>/medium.md 拿正文（已剥掉 frontmatter 和 <!-- truncate -->，含 H1 标题）。从源文件 frontmatter 拿 title。
步骤 2：打开 Medium 新文章页
opencli browser default open "https://medium.com/new-story"
opencli browser default get title # 应是 "New story – Medium"（说明已登录）
如果跳到登录页：让用户先在该 Chrome 里登录 Medium，再重来。
步骤 3：正文 markdown → HTML（pandoc）+ ⚠️ 代码块空行适配
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.
- 3d ago First seen · 233 lines · 137 tokens per session scan A 6fb60db6d3d8
publish-medium is a skill published in the GitHub repository childrentime/reactuse (1,048 stars, last pushed 12d ago), licensed Unlicense. It adds 137 tokens to every session and 3,763 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
content-publish
End-to-end content creation and publishing. Takes a topic (or generates one), drafts in the user's voice, gets approval via Telegram, and publishes to Medium via browser automation. Invoke with "publish a post about X", "write and publish to Medium", "content-publish", or when an ego-dispatched session needs to create…
csdn-publisher
CSDN 博客发布/管理自动化（Web 内部 API）.
take-screenshot
Take a screenshot of a rendered blog page section using Playwright (via uv) against the local dev server, save it as a WebP into a page's assets dir, and insert an tag. Use whenever the user asks to take/create/capture a screenshot of a page or section themselves (especially for monthly updates pages), e.g. "take a…
electron
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include…
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.