image-art-direction

image-art-direction is a skill for Claude Code, Codex from Oriolshhh/runware-image-mcp. It costs 25 tokens per session (1,198 once invoked), scanned A, original, MIT.

A planning workflow for deciding which images or other visual assets a page needs, where they should appear, and how they should share a consistent style.

In plain words
What is it for?
Use it to plan illustrations, photos, diagrams, textures, product images, and image-generation prompts for a website.
Why use it?
It prevents decorative or unrelated images from making a page harder to understand or use.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to plan illustrations, photos, diagrams, textures, product images, and image-generation prompts for a website.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oriolshhh/runware-image-mcp/image-art-direction
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.

Any agent
npx skills add Oriolshhh/runware-image-mcp --skill image-art-direction
Clone the repo
git clone --depth 1 https://github.com/Oriolshhh/runware-image-mcp

Made for: Claude Code, Codex.

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 image-art-direction

README.md
[![agentmods](https://agentmods.dev/badge/skills/oriolshhh/runware-image-mcp/image-art-direction/github.svg)](https://agentmods.dev/skills/oriolshhh/runware-image-mcp/image-art-direction)
Your own site
<a href="https://agentmods.dev/skills/oriolshhh/runware-image-mcp/image-art-direction"><img src="https://agentmods.dev/badge/skills/oriolshhh/runware-image-mcp/image-art-direction/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.

agentmods 80×15 button for image-art-direction

Your own site · 80×15
<a href="https://agentmods.dev/skills/oriolshhh/runware-image-mcp/image-art-direction"><img src="https://agentmods.dev/badge/skills/oriolshhh/runware-image-mcp/image-art-direction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,198 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00025 $0.01198
Opus 5 $0.00013 $0.00599
Sonnet 5 $0.00005 $0.00240
Haiku 4.5 $0.00003 $0.00120

Measured 8d ago against content hash 73ed9d0bc917, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

image-art-direction 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 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.

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/skills/image-art-direction/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Image Art Direction

Purpose

Create a purposeful image system rather than a collection of unrelated decorations. Every proposed asset must improve a named page outcome and every generation prompt must preserve one approved visual language.

When to use it

  • When an existing page feels visually flat, abstract, generic, or difficult to scan.
  • When illustrations, editorial images, diagrams, product imagery, textures, or contextual scenes could improve explanation, trust, identity, or pacing.
  • Before generating or integrating a family of visual assets.

Instructions

  1. Audit the rendered page and real content. Identify comprehension gaps, abstract claims, weak hierarchy, long text runs, trust gaps, empty states, onboarding moments, or transitions where an image has a clear job.
  2. Reject decorative filler. Do not add imagery where it competes with the primary action, repeats text without adding meaning, obscures product UI, increases cognitive load, or exists only to fill whitespace.
  3. Inventory existing brand assets, illustrations, photography, logos, icons, colors, typography, shape language, textures, product screenshots, and licensing constraints. Extend the local visual language before inventing one.
  4. Score each candidate slot by user value, relevance, visual leverage, implementation cost, accessibility risk, performance cost, and confidence. Record the exact route, component/landmark, surrounding content, intended viewport behavior, and why imagery is better than layout or copy alone.
  5. Define one style lock before individual prompts:
    • asset family and medium;
    • composition, perspective, depth, and geometry;
    • palette and relationship to product tokens;
    • lighting, contrast, texture, line/edge treatment, and detail level;
    • character/object continuity and representation constraints;
    • background treatment, whitespace, crop behavior, and motion potential;
    • forbidden motifs and anti-goals.
  6. Make every prompt self-contained. Repeat the exact style-lock language, then add the asset's unique subject, action, composition, mood, focal point, background, crop-safe region, and exclusions. Do not rely on “same style as above” because generation calls may run independently.
  7. Describe visual attributes instead of requesting imitation of a living artist. Do not request copyrighted characters, fabricated logos, fake product screenshots, false testimonials, or readable interface text inside generated raster images. Use real product capture workflows for actual UI.
  8. Choose aspect ratio and resolution from the slot, not from a global default. A wide hero, square card, portrait story, and inline diagram may all need different dimensions while sharing the same style. For every asset specify: rendered size by breakpoint, source resolution or responsive renditions, focal point, safe crop, and whether separate mobile art direction is required.
  9. Specify accessibility and content behavior: informative alt text, empty alt for purely decorative assets, captions when needed, contrast under overlays, no essential meaning embedded only in the image, and reduced-motion handling for any later animation.
  10. Specify delivery constraints: preferred format, compression/quality target, width and height attributes, srcset/sizes where applicable, eager versus lazy loading, LCP priority, fallback, theme variants, and a realistic page-weight budget.

Read the full file on GitHub · 103 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. 8d ago First seen · 103 lines · 25 tokens per session scan A 73ed9d0bc917

Subscribe to this mod's changes

image-art-direction is a skill published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 1,198 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 2026-09-03.

Related

Other skills, from other repositories

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

visual-ralph

Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.

Yeachan-Heo/oh-my-codex · 52 tokens

accessibility

Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.

microsoft/hve-core · 47 tokens

make-resume

A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.

Hisn00w/ASu-skills · 86 tokens