cover-designer

cover-designer is an agent for coding agents from epicsagas/Velith. It costs 40 tokens per session (1,450 once invoked), scanned A, original, Apache-2.0.

A book-cover planning assistant that turns book details into several cover ideas and image-generation prompts. It considers the book’s genre, intended readers, title, and output format.

In plain words
What is it for?
Use it to create cover concepts for fiction, nonfiction, technical books, poetry, children’s books, and other genres. It can prepare ideas for ebook, print, and audiobook covers.
Why use it?
It gives a book project concrete visual directions before a cover is made. It also helps account for differences between ebook, printed-book, and audiobook cover formats.

Agent

Part of the velith plugin — 17 skills, 8 agents shipped together

Install

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.

agentmods
npx agentmods add agents/epicsagas/velith/cover-designer
Clone the repo
git clone --depth 1 https://github.com/epicsagas/Velith

Or install velith, the plugin that ships this one along with the rest of its 17 skills, 8 agents.

Wrote 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.

agentmods badge for cover-designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/epicsagas/velith/cover-designer.svg)](https://agentmods.dev/agents/epicsagas/velith/cover-designer)
Your own site
<a href="https://agentmods.dev/agents/epicsagas/velith/cover-designer"><img src="https://agentmods.dev/badge/agents/epicsagas/velith/cover-designer.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,450 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00040 $0.01450
Opus 5 $0.00020 $0.00725
Sonnet 5 $0.00008 $0.00290
Haiku 4.5 $0.00004 $0.00145

Measured 5d ago against content hash 68a64f2f37a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cover-designer 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 5d 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.

agents/cover-designer.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Book metadata → genre trend analysis → 3-5 cover concepts → image generation prompts → format specs.

Input: PRD.md, title-candidates.md, STYLE.md, outline.md (for thematic references).

Genre Visual Language

Genre Color Palette Typography Imagery Mood
Literary Fiction Muted earth, cream, texture Serif (Garamond, Didot) Minimal, abstract, texture Contemplative
Thriller/Mystery Dark, high contrast, red accent Bold sans (Bebas, Trade Gothic) Fragmented, shadow, silhouette Tense
Romance Warm (pink, gold, cream), soft Script + serif Figures, symbols, landscape Warm
Fantasy Rich jewel tones, gold Display serif, ornate Immersive world, epic scene Awe
SF Steel, neon, dark Geometric sans Technology, space, abstract Futuristic
Nonfiction/Business Clean white/color blocks Bold sans (Helvetica, Montserrat) Abstract graphic, icon Confident
Technical Dark bg, code-green/blue Mono (JetBrains, Fira Code) Terminal, diagram, code Precise
Poetry/Essay Soft watercolor, ethereal Elegant serif Abstract, nature, symbol Intimate
Children's Bright primary, playful Rounded sans Character-centric, whimsical Joyful

Concept Development

For each of 3-5 concepts, provide:

Direction

One-line concept statement (e.g., "Silhouette of a woman walking through a field of static — loss of signal as metaphor for grief")

Color Palette

3-4 hex colors with role labels:

Primary: #1a1a2e (deep navy — background)
Secondary: #e94560 (coral red — accent/energy)
Neutral: #f5f5f5 (off-white — text areas)
Atmosphere: #16213e (dark blue — depth)

Typography

  • Title: font family, weight, size ratio, positioning
  • Subtitle/series: complementary font, smaller
  • Author name: font, positioning (bottom third or top)

Layout

Describe image and text placement:

  • Image zone (full bleed, central vignette, split, etc.)
  • Text safe area (where type sits without competing with image detail)
  • Title dominant position (top third, center, bottom third)

Read the full file on GitHub · 165 lines

Changes

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.

  1. 5d ago First seen · 165 lines · 40 tokens per session scan A 68a64f2f37a1

Subscribe to this mod's changes

cover-designer is an agent published in the GitHub repository epicsagas/Velith (33 stars, last pushed yesterday), licensed Apache-2.0. It adds 40 tokens to every session and 1,450 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 2026-08-30.

Related

Other agents, from other repositories

art-director

Plans the asset set for a brand request — decides which assets to produce, their composition and hierarchy, and which engine (vector vs raster) each needs. Use before generating anything ambiguous or multi-asset.

localplugins/plugins · 45 tokens

omd-asset-curator

페이지/컴포넌트에 필요한 에셋(아이콘, 일러스트, 차트, 사진, 로고, 비디오, 3D 렌더)을 식별하고, 프로젝트 스택에 맞춰 최적 매체 + 라이브러리를 결정한 후 (a) 인라인 코드 생성 (SVG/CSS) 또는 (b) 무료 라이선스 소싱 또는 (c) 3D 서브에이전트 라우팅 중 하나로 처리합니다. 이모지 디폴트 금지 — SVG 우선.

kwakseongjae/oh-my-design · 124 tokens

designer

Ornamental design specialist for historical and modern style analysis, colorblind-accessible palettes, and AI-assisted image generation using Z-Image.

pjt222/agent-almanac · 29 tokens

inspiration-scout

Use this agent to find aesthetic references, interaction examples, and visual inspiration that match the project brief and the user's taste profile. Dispatched when the team needs creative direction, visual references, or cross-domain inspiration before design begins.

Owl-Listener/designpowers · 50 tokens

prompt

You are a SketchUp assistant with access to a live SketchUp instance via MCP tools. You help users with modeling, scene inspection, settings, and general SketchUp automation. You write Ruby scripts to accomplish whatever the user needs.

darwin/supex · 0 tokens

polyviz

Autonomously render Polygraph verification artifacts into a clean, brand-consistent diagram set (SVG, optional PNG) and return where the figures landed. Given a viz-model JSON or a Polygraph/polyvers artifacts directory, produce the catalog (state-machine, invariants, counterexample, compat-gate, model-card)…

cognitive-fab/polygraph · 109 tokens