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 Ckokoski/AuthorAgent --skill website-publishergit clone --depth 1 https://github.com/Ckokoski/AuthorAgentWrote 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/ckokoski/authoragent/website-publisher)<a href="https://agentmods.dev/skills/ckokoski/authoragent/website-publisher"><img src="https://agentmods.dev/badge/skills/ckokoski/authoragent/website-publisher/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/ckokoski/authoragent/website-publisher"><img src="https://agentmods.dev/badge/skills/ckokoski/authoragent/website-publisher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 60 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00029 | $0.01513 |
| Opus 5 | $0.00015 | $0.00757 |
| Sonnet 5 | $0.00006 | $0.00303 |
| Haiku 4.5 | $0.00003 | $0.00151 |
Grade A, and why
website-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 9d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Website Publisher
The management layer on top of AuthorAgent's static-site builder. Generates your site, keeps it in sync with your books, drafts blog posts from your project artifacts, and pushes the rendered site to your host.
This skill is deliberately not a CMS. AuthorAgent is for producing books — shipping a working site is part of that, but maintaining a fully interactive web property isn't. Authors who need comments, forms, ESP integration UIs, or deep analytics should keep using the WordPress / Squarespace / Ghost they already have.
What it does
1. Sites — register, link, manage
A "site" is a deployable unit (one author or one pen name typically). Each site has:
- A config (slug, name, tagline, base URL, primary color, social links)
- A list of linked projects (when those projects complete, their books auto-publish to the site's books list)
- A list of blog posts (drafts + published — drafted by this skill)
- A deploy target (Netlify / Vercel / Cloudflare Pages / rsync / manual zip / none)
POST /api/sites Create a site
GET /api/sites List all sites + freshness status
PATCH /api/sites/:id Update config / linked projects / deploy target
DELETE /api/sites/:id Remove a site
POST /api/sites/:id/link-project { projectId }
2. Auto-add books on project completion
When a book-production or novel-pipeline project completes AND the
project is linked to one or more sites, the book is auto-added to each
site's books list. Idempotent on slug — re-completing the project updates
the existing entry.
The author still has to render + deploy explicitly — auto-publishing a
brand-new book without review would be too aggressive. The dashboard shows
each site's pendingChanges count so the author knows when a render is
needed.
3. Blog post drafter
Four post types, each pulling different project artifacts into a focused prompt:
| Type | What it produces |
|---|---|
release_announcement |
New-release post: 500-700 words, conversational, with buy-link CTAs |
behind_the_scenes |
Process post: 700-900 words pulling from chapter summaries + user-model + craft-critic flags |
excerpt |
Excerpt-with-tease post: lead-in → verbatim scene → tease → CTA |
teaser |
Coming-soon post: 350-500 words building anticipation without overselling |
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.
- 9d ago First seen · 156 lines · 29 tokens per session scan A 349b330c2017
website-publisher is a skill published in the GitHub repository Ckokoski/AuthorAgent (105 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 1,513 once invoked, about $0.0001 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
search
Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.
app-search
A search tool that opens search pages in popular mobile apps, including shopping, maps, video, knowledge, music, and app-store services. It covers apps such as Pinduoduo, Meituan, Amap, Douyin, Xiaohongshu, Bilibili, Zhihu, Baidu, and Taobao-related services.
clipboard-to-shortcut
A skill that turns a copied mobile-app sharing link into a reusable shortcut for opening that app page later.
capcut-theme-video
A guide for creating one-tap videos in CapCut, a video-editing app, from photos on an Android device. It specifies how to select photos and place them in the required album before making a video.
taobao-search
A tool for searching products on Taobao, Alibaba’s consumer shopping marketplace, by opening its search page in the Taobao app. It supports product, brand, price-limit, comparison, and new-product searches.
scheduled-automation
Schedule app automation tasks such as opening an app and performing actions at a specific time.