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/humanread-content/humanread-agent-kit/humanread-publishernpx skills add humanread-content/humanread-agent-kit --skill humanread-publishergit clone --depth 1 https://github.com/humanread-content/humanread-agent-kitWrote 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/humanread-content/humanread-agent-kit/humanread-publisher)<a href="https://agentmods.dev/skills/humanread-content/humanread-agent-kit/humanread-publisher"><img src="https://agentmods.dev/badge/skills/humanread-content/humanread-agent-kit/humanread-publisher.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 | $0.00048 | $0.04766 |
| Opus 5 | $0.00024 | $0.02383 |
| Sonnet 5 | $0.00010 | $0.00953 |
| Haiku 4.5 | $0.00005 | $0.00477 |
Grade A, and why
humanread-publisher 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 4d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humanread Publisher
Use the humanread MCP tools for all live platform actions.
Connect an author
- If MCP authentication is missing, stop and tell the user to open
https://humanread.surl.tw/login, sign in with Google, accept the current terms, and generate an API key in Author Studio. - Tell the user to configure the key privately in the MCP client as
Authorization: Bearer <key>, then reconnect so the tool list reloads. - Never ask the user to paste, reveal, or store the key in chat, a manuscript, an issue, source control, or any file handled by the Agent.
Read before designing
Humanread sanitizes every chapter. Design only with the supported subset below. Do not design a layout that depends on content outside this allowlist, because it will be removed during upload.
Supported elements:
- Structure:
article,section,header,footer,div,span - Prose:
h1–h4,p,br,hr,blockquote,pre,code - Emphasis:
em,strong,small - Lists:
ul,ol,li - Figures:
figure,img,figcaption;img srcmust be the exacthumanread-asset:<sha256>returned byupload_image_asset - Links:
a
Supported attributes:
- Any supported element:
title a:href,title,rel- URLs: HTTPS or HTTP only
Never use or rely on:
- JavaScript,
<script>, inline event handlers, orjavascript:URLs <style>, inlinestyle, custom CSS, CSS imports, web fonts, or CSS variables- MDX, JSX, SVG, MathML, canvas, iframe, object, embed, audio, or video
- Forms, inputs, buttons, editable content, popovers, or interactive widgets
data:/blob:URLs, tracking pixels, remote analytics, or hidden content- Remote images or arbitrary image URLs; upload local PNG/JPEG/WebP through
upload_image_assetand use its returned markup exactly - IDs, ARIA state,
data-*attributes, or unsupported attributes - Custom classes; they are removed to prevent collisions with Humanread interface styles
If the requested design requires one of these features, explain that Humanread does not preserve it and create the closest semantic layout using the allowlist. Never upload unsupported markup merely to see whether the sanitizer accepts it.
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.
- 4d ago First seen · 183 lines · 48 tokens per session scan A fda3b4468f49
humanread-publisher is a skill published in the GitHub repository humanread-content/humanread-agent-kit (1 stars, last pushed 28d ago), licensed MIT. It adds 48 tokens to every session and 4,766 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
story-import
逆向导入已有小说。将已写好的小说（半成品或完本）反向解析为标准项目目录结构，兼容 story-long-write / story-short-write 后续写作流程；内部复用 story-long-analyze / story-short-analyze 的拆解管道，按篇幅自动分流。触发方式：/story-import、「导入小说」「反向解析」「导入」「把我的书导进来」。.
story-review
多视角对抗式审查。full/lean 模式在已部署 reviewer agents 时并行 spawn；缺失/异常 agents 或 spawn 失败时自动降级 solo，参考文件不可读时使用内置 rubric fallback。触发方式：/story-review、/审查、「审查一下」「帮我审一下」。.
story-short-write
短篇网文写作。辅助短篇小说创作，从构思到成稿，聚焦情绪拉扯与节奏把控。触发方式：/story-short-write、/写短篇、「帮我写一篇短篇」「写个盐言故事」。.
story-deslop
网文去AI味。检测并清除文本中的AI写作痕迹，让文字回归自然、非模板化。触发方式：/story-deslop、/去AI味、「去AI味」「这篇太AI了」「网文去AI味」。.
story-long-analyze
长篇网文拆文。深度拆解爆款长篇小说的黄金三章、人设架构、爽点设计、节奏控制。单一深度拆解管道：跑完黄金三章（Stage 1）后产出快速预览报告并询问是否继续全量拆解，确认后从 Stage 2 续跑逐章摘要、聚合分析、设定关系、汇总报告，全程产物落盘 拆文库/{书名}/。触发方式：/story-long-analyze、/长篇拆文、「帮我拆这本书」「拆这本书」「分析黄金三章」「深度拆解」「完整拆解」「系统拆解」或提供小说文本文件路径——全部进入同一管道。.
story-long-write
长篇网文写作。从大纲到正文，辅助长篇网络小说的创作，包括世界观、人物、情节线管理。触发方式：/story-long-write、/写长篇、「帮我开书」「写大纲」「日更」「续写」「继续写」「修改第X章」「回炉」「重写第X章」。.