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 tdimino/claude-code-minoan --skill vellum-editorialgit clone --depth 1 https://github.com/tdimino/claude-code-minoanWrote 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/tdimino/claude-code-minoan/vellum-editorial)<a href="https://agentmods.dev/skills/tdimino/claude-code-minoan/vellum-editorial"><img src="https://agentmods.dev/badge/skills/tdimino/claude-code-minoan/vellum-editorial/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/tdimino/claude-code-minoan/vellum-editorial"><img src="https://agentmods.dev/badge/skills/tdimino/claude-code-minoan/vellum-editorial.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00156 | $0.02650 |
| Opus 5 | $0.00078 | $0.01325 |
| Sonnet 5 | $0.00031 | $0.00530 |
| Haiku 4.5 | $0.00016 | $0.00265 |
Grade A, and why
vellum-editorial 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 8d 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 -sI https://<project-name>.pages.dev/ | grep -iE 'x-robots|x-frame|content-security' How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build editorial documentation sites with the Vellum design system. Two theme variants (warm parchment, dark space), OKLCH color science, three-font typographic hierarchy, 35 semantic components. Static HTML with zero build step — deploys to Cloudflare Pages, GitHub Pages, or any static host.
Creative Direction
Two theme variants, each with a distinct character:
Warm (default): "Vellum manuscript" — warm cream backgrounds with a subtle SVG crosshatch texture, deep ink-brown text, copper accents. Authoritative, like a well-made journal.
Dark: "Space archive" — deep blue-black backgrounds with CSS starfield (box-shadow stars + nebula gradients), bright gold copper accents, cool blue-gray text. Atmospheric, like a command center or digital archaeology site.
Both themes share the same typography, component library, and layout system. The palette transformation is purely in :root custom properties — no structural CSS changes needed.
If the minoan-frontend-design skill is available, read it for broader aesthetic principles. Vellum encodes those principles into a concrete design system. Pages built with Vellum should score 16+/20 on /design-audit and 28+/40 on /design-critique.
Quick Start
Scaffold a new project:
python3 ~/.claude/skills/vellum-editorial/scripts/init_project.py <project-name> \
[--style editorial|instrument] [--template landing|one-pager] \
[--pages N] [--theme warm|dark] [--auth] [--no-auth] \
[--password <string>] [--deploy-ready] [--no-deploy-ready] \
[--audio] [--no-audio]
This generates a deploy-ready site with CSS, starter HTML, OG/Twitter social meta tags, a light/dark theme toggle, and optionally a client-side auth gate and ambient audio player. By default, --deploy-ready generates _headers (CF Pages security headers) and robots.txt (crawl prevention). The --theme dark flag transforms the palette to a dark space aesthetic with CSS starfield background. Open index.html in a browser — fonts load from Google Fonts, icons from Phosphor Icons CDN.
What ships with it
13 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.
- assets/_audio-player.js 4.5 KB runs code
- assets/_auth.js 2.0 KB runs code
- assets/_components.css 29 KB
- assets/_shared.css 26 KB
- assets/template-one-pager.html 11 KB
- assets/template-subpage.html 3.6 KB
- assets/template.html 3.9 KB
- README.md 2.2 KB
- references/advanced-patterns.md 11 KB
- references/component-catalog.md 29 KB
- references/design-tokens.md 12 KB
- references/page-architecture.md 15 KB
- scripts/init_project.py 22 KB runs code
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.
- 8d ago First seen · 172 lines · 156 tokens per session scan A 20af9be35262
vellum-editorial is a skill published in the GitHub repository tdimino/claude-code-minoan (41 stars, last pushed yesterday), licensed MIT. It adds 156 tokens to every session and 2,650 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
pm-feedback
A feedback-analysis aid that turns spreadsheet data, CSV files, pasted text, or review screenshots into organized product insights. It groups themes, identifies sentiment, examines trends and sources, calculates NPS, and extracts user types.
add-pdf-report
Internal implementation skill invoked by /add-native for app-generated PDF report workflows using expo-print and, when present, expo-sharing.
add-excel
Adds Excel Online (Business) connector to a Power Apps code app. Use when reading or writing Excel workbook data from OneDrive or SharePoint.
officecli-commonly-templates
Use this skill when producing a polished, Commonly-branded deliverable (.docx brief / memo, .xlsx data matrix, .pptx deck) and you do not have specific brand guidance from the user. Trigger on: 'write me a brief', 'one-pager', 'memo', 'data sheet', 'status matrix', 'short deck', 'summary deck', 'closing slide', 'final…
add-onedrive
Adds OneDrive for Business connector to a Power Apps code app. Use when uploading, downloading, listing, or managing files in OneDrive.
markdown-converter
Convert binary documents (PDF, DOCX, XLSX, PPTX, HTML, EPUB, images) to clean LLM-friendly Markdown using Microsoft's markitdown Python tool. Use when a user attaches a binary file and you need to read its contents.