imagery

imagery is a skill for Claude Code, Codex from lenxism/ives. It costs 94 tokens per session (707 once invoked), scanned A, original, MIT.

Guidance for choosing and using photos, icons, illustrations, and app icons in an interface. It covers both fixed images and unpredictable user-uploaded images.

In plain words
What is it for?
Use it when selecting photos, handling uploaded images, choosing an icon set, creating simple illustrations, or designing an app icon.
Why use it?
It helps avoid mismatched visuals, poor-quality photos, inconsistent icons, broken image states, and layouts that fail when user content varies.

Skill for Claude CodeCodex

Part of the ives plugin — 13 skills 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 skills/lenxism/ives/imagery
Any agent
npx skills add lenxism/ives --skill imagery
Clone the repo
git clone --depth 1 https://github.com/lenxism/ives

Made for: Claude Code, Codex.

Or install ives, the plugin that ships this one along with the rest of its 13 skills.

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 imagery

README.md
[![agentmods](https://agentmods.dev/badge/skills/lenxism/ives/imagery.svg)](https://agentmods.dev/skills/lenxism/ives/imagery)
Your own site
<a href="https://agentmods.dev/skills/lenxism/ives/imagery"><img src="https://agentmods.dev/badge/skills/lenxism/ives/imagery.svg" alt="Measured on agentmods" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 707 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 $0.00094 $0.00707
Opus 5 $0.00047 $0.00353
Sonnet 5 $0.00019 $0.00141
Haiku 4.5 $0.00009 $0.00071

Measured 4d ago against content hash 4c39bc390d8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

imagery 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 4d 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.

skills/imagery/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Imagery

Imagery has a massive impact on aesthetics, mood, and perceived quality. Whatever kind you use — photos, icons, illustrations — they must match the overall direction.

Static Photos

Photos you control (stock, curated, photo shoots):

  • Avoid cliché stock — Happy salad-eating people, businessmen jumping with briefcases. These trigger negative emotions. Search for authentic, candid, moody imagery.
  • Consistency — All photos in a set should have similar treatment (color temperature, exposure, style).
  • Quality — A mediocre photo undermines an otherwise excellent interface. Better to use no photo than a bad one.

Dynamic Images

User-generated content (avatars, posts, uploads) that you can't predict:

  • Design for the worst case — screenshots, dark photos, text-heavy images
  • Use consistent aspect ratios and cropping
  • Avatar fallbacks: initials or generic icon, never a broken image
  • Consider how a grid of random images looks together, not just individually

Icons

Using existing icons

  • Choose ONE icon set and stick with it (Feather, Lucide, SF Symbols, Phosphor)
  • Never mix icon sets — inconsistent stroke widths and styles are immediately noticeable
  • All outline OR all filled, not mixed
  • Consistent size: common sizes are 20px, 24px, or 28px. Pick one for each context.
  • Icon color should come from your gray system, not arbitrary values

Creating icons

  • Start with a consistent grid (24×24 or 32×32)
  • Uniform stroke width (typically 1.5-2px)
  • Consistent corner radius on line caps and joins
  • Optical alignment — visually center within the grid, not mathematically
  • Test at actual size, not just zoomed in

When icons become illustrations

Icons are small, symbolic, single-purpose. Illustrations are larger, environmental, mood-setting. The transition is about complexity and context size. If it needs a scene or environment, it's an illustration.

Simple Illustrations

You can create effective illustrations with basic shapes in any design tool:

  • Rounded rectangles with gradients for objects
  • Circles with linear gradients for lighting
  • Drop shadows for grounding
  • Layer opacity for depth
  • Noise texture overlay (3-5% opacity) for character

Read the full file on GitHub · 67 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. 4d ago First seen · 67 lines · 94 tokens per session scan A 4c39bc390d8b

Subscribe to this mod's changes

imagery is a skill published in the GitHub repository lenxism/ives (5 stars, last pushed 6mo ago), licensed MIT. It adds 94 tokens to every session and 707 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 2026-08-31.

Related

Other skills, from other repositories

motion-graphics

A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…

heygen-com/hyperframes · 139 tokens

infographic-creator

基于给定文字内容创建精美信息图。当用户请求创建信息图时使用。.

antvis/Infographic · 25 tokens

liquid-glass

Apple Liquid Glass design system. Use when building UI with translucent, depth-aware glass morphism following Apple's design language. Provides CSS tokens, component patterns, dark/light mode, and animation specs.

fengshao1227/ccg-workflow · 43 tokens

better-ui

Design engineering principles for making interfaces feel polished. Use when building UI components, reviewing frontend code, implementing animations, hover states, shadows, borders, micro-interactions, enter/exit animations, choosing or reviewing icons, or any visual detail work. Triggers on UI polish, design details…

talebook/talebook · 99 tokens

cli-anything-photoshop

通过 COM 自动化操控 Adobe Photoshop 的 CLI harness。支持项目管理、图层操作、选区控制、文字编辑、图像调整和多格式导出。.

yb2460/harness-anything · 43 tokens

nano-banana

Generate professional presentation slides and high-quality illustrations using Gemini image generation API (Nano Banana 2), with interactive browser-based review and iterative editing. Full workflow: content planning conversation → slidesplan.json → batch image generation → review with feedback → targeted slide…

EvoScientist/EvoSkills · 128 tokens