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 Varnan-Tech/opendirectory --skill graphic-ebookgit clone --depth 1 https://github.com/Varnan-Tech/opendirectoryWrote 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/varnan-tech/opendirectory/graphic-ebook)<a href="https://agentmods.dev/skills/varnan-tech/opendirectory/graphic-ebook"><img src="https://agentmods.dev/badge/skills/varnan-tech/opendirectory/graphic-ebook/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/varnan-tech/opendirectory/graphic-ebook"><img src="https://agentmods.dev/badge/skills/varnan-tech/opendirectory/graphic-ebook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Rogue Agent · line 149 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00097 | $0.05304 |
| Opus 5 | $0.00048 | $0.02652 |
| Sonnet 5 | $0.00019 | $0.01061 |
| Haiku 4.5 | $0.00010 | $0.00530 |
Grade A, and why
graphic-ebook 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 — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.
graphic-ebook
Creates professionally designed B2B SaaS e-books — lead magnets, gated guides, nurture assets, white papers. HTML + CSS → print-ready PDF. 3–10 pages.
Critical Rules
Before any step, these rules are absolute:
- Every page MUST fit within A4 canvas (1200×1697px). No content overflow.
- All scalable font sizes use
clamp(). Fixed px only for borders/structural elements. - Single self-contained HTML. All CSS inline. Font CDN
<link>only external dependency. - Never dump HTML in chat. Save to file, show summary only.
- Body copy is primary. Line-height ≥ 1.75 on all text-column and text-sidebar pages. Max-width ≤ 65ch for single-column body.
- No generic AI slop: no Inter as display font, no purple-to-blue gradient on white, no "Thank You" closing.
- Visual rhythm: never place 2+ text-column pages back-to-back. Break with chapter-intro, quote-callout, or stat-grid.
- Before generating HTML, commit to a design direction: one tone, one signature element, one background system. Generic = failure. Each ebook must be distinctly designed for its audience and subject — not a template.
* { -webkit-print-color-adjust: exact !important; print-color-adjust: exact !important; }— mandatory global CSS. Chromium strips all background colors in PDF without this.- Every page except cover must have a page footer: page number + brand name. Absolute position at bottom of each
.slide.
Step 1: Brief Intake
Four required fields. If all four are present in the user's prompt: skip to Step 2.
If any are missing, ask exactly:
"To create your ebook, I need four things:
- Topic — what is the ebook about? (be specific: "5 ways to reduce CAC" not "marketing tips")
- Audience — who reads it? (role, company size, pain point: "Customer Success Managers at 50–500 person SaaS companies struggling with churn")
- Desired action — what should the reader do after? (book a demo, download a template, share with team)
- Content — do you have existing content, or should I draft from the topic?"
What ships with it
7 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.
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 · 397 lines · 97 tokens per session scan A 7db9938afeaf
graphic-ebook is a skill published in the GitHub repository Varnan-Tech/opendirectory (635 stars, last pushed 23d ago), licensed MIT. It adds 97 tokens to every session and 5,304 once invoked, about $0.0005 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
marp-slides
Author MARP markdown slide decks exportable to PDF, PPTX, and HTML via marp-cli. Covers Marpit directives, custom CSS themes, SVG chart recipes, and dashboard components. Triggers on: "marp", "marp deck", "markdown slides", "slides from markdown", "marp-cli", "pdf from markdown", "pptx from markdown".
paper2xhs
A process for turning an academic paper PDF into an illustrated multi-image post for Xiaohongshu, a Chinese social-media platform. It combines a plain-language explanation with a cover, paper figures, and tags.
laohan-notebooklm
A workflow that turns a Chinese spoken script into slide images through NotebookLM, Google’s AI notebook service, and saves them for use in video editing. It also converts the resulting PDF into images.
glmv-pdf-to-ppt
Convert a PDF (research paper, report, or any document) into a polished multi-slide HTML presentation with a structured outline JSON and summary markdown. Trigger this skill when the user mentions making slides or a PPT from a PDF — in Chinese or English.
document-exports
Generate and TEST downloadable document exports (PDF/CSV) from a Node/Express backend — pdfkit streaming, CSV BOM, cents formatting, and the supertest/pdfkit pitfalls that silently break tests.
financas-app
Corrigir, estender e validar o app de finanças pessoais (Node/Express + EJS + MongoDB + Docker). Cobre a arquitetura de porta única 4460 com demo via /demo, o fluxo de correção de UI (rebuild de AMBOS os containers + ASSETVERSION), validação por browser headless no IP docker, verificação ad-hoc e o padrão…