agentmods.dev

image-generation

image-generation is a skill for Claude Code from shaharsha/claude-skills. It costs 173 tokens per session (3,403 once invoked), scanned A, original, MIT.

A skill for creating visual assets such as logos, icons, interface mockups, hero images, and product images with OpenAI or Google image models.

In plain words
What is it for?
Use it to create, design, mock up, render, or illustrate images, and to improve prompts for image generation.
Why use it?
It helps choose a suitable image model and turn a design brief into an image-generation prompt.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

Part of the brand-and-visuals plugin — 4 skills shipped together , and of shaharsha-skills

not rated 6repo +1 changed 1mo ago A scan 173 tokens original MIT

Good fit Use it to create, design, mock up, render, or illustrate images, and to improve prompts for image generation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shaharsha/claude-skills/image-generation
View source ↗ shaharsha/claude-skills
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 shaharsha/claude-skills --skill image-generation
Clone the repo
git clone --depth 1 https://github.com/shaharsha/claude-skills

Made for: Claude Code.

Or install brand-and-visuals, the plugin that ships this one along with the rest of its 4 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 image-generation

README.md
[![agentmods](https://agentmods.dev/badge/skills/shaharsha/claude-skills/image-generation/github.svg)](https://agentmods.dev/skills/shaharsha/claude-skills/image-generation)
Your own site
<a href="https://agentmods.dev/skills/shaharsha/claude-skills/image-generation"><img src="https://agentmods.dev/badge/skills/shaharsha/claude-skills/image-generation/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-generation

Your own site · 80×15
<a href="https://agentmods.dev/skills/shaharsha/claude-skills/image-generation"><img src="https://agentmods.dev/badge/skills/shaharsha/claude-skills/image-generation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 173 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,403 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 $0.00173 $0.03403
Opus 5.5 $0.00069 $0.01361
Sonnet 5.5 $0.00035 $0.00681
Haiku 4.5 $0.00017 $0.00340

Measured 1mo ago against content hash 3912c87b963d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

image-generation 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 1mo ago.

The scan reads SKILL.md. This mod also ships 6 executable files (scripts/crop_faces.py, scripts/gemini-image.sh, scripts/openai-image.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/image-generation/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Image Generation

Two model families, three jobs.

Models covered

Model ID Family Use for Cost (1024×1536, measured 2026-10-02)
gpt-image-2.5-sunburst OpenAI (Images 2.5, 2026-09-08) Default. Anything that may ship. #1 on every major leaderboard (generation, editing, text rendering, portraits) max ≈ $0.165, ~90 s · high ≈ $0.041, ~35 s
gpt-image-2.5-flare OpenAI (Images 2.5) Quick drafts — exploring directions, testing a prompt. Same prompts as Sunburst, ~2× faster medium ≈ $0.01, ~15 s
gemini-3-pro-image Google (Nano Banana Pro) Close-up natural skin/hair when votes and reviewers disagree; up to 14 references $0.134 (1K/2K) · $0.24 (4K)
gemini-3.1-flash-image Google (Nano Banana 2) Extreme aspect ratios (1:4…8:1), image-search grounding $0.067 (1K)
gemini-3.1-flash-lite-image Google (Nano Banana 2 Lite) Cheapest Gemini exploration; 1K only, returns JPEG $0.034

gpt-image-2 still works (not deprecated) but is a step below both 2.5 models. The Gemini *-preview IDs and all Imagen models are shut down — the scripts refuse them.

The three jobs of this skill

  1. Pick the model and the quality for the asset. See reference/model-selection.md.
  2. Write the prompt following the model's house rules. The two providers want opposite things:
    • OpenAI GPT Image 2.5 wants labeled sections (scene / subject / details / constraints), exact text in quotes, and accepts inline exclusions ("no extra text, no watermarks"). Read reference/openai-gpt-image.md.
    • Gemini wants narrative paragraphs, negative phrasing backfires (rewrite "no people" as "empty street"), aspect ratio goes in imageConfig. Read reference/gemini-image.md.
  3. Run the API via the bundled scripts. See scripts/README.md.

Quality on 2.5 — the trap

The 2.5 quality ladder was re-cut. At the same size, 2.5 high buys about the output tokens of gpt-image-2 medium; 2.5 max buys what gpt-image-2 high did (measured: Sunburst 1024×1536 high = 1,372 output tokens, max = 5,488). Copying "quality=high" from old habits silently ships a medium-detail image.

Read the full file on GitHub · 177 lines

Files

What ships with it

24 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.

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. 1mo ago Changed · +20 lines · +46 tokens per session 3912c87b963d
  2. 1mo ago Changed · -9 lines · +20 tokens per session 862415361304
  3. 2mo ago First seen · 166 lines · 107 tokens per session scan A c6cb445af402

Subscribe to this mod's changes

image-generation is a skill published in the GitHub repository shaharsha/claude-skills (6 stars, last pushed today), licensed MIT. It adds 173 tokens to every session and 3,403 once invoked, about $0.0007 per session on Opus 5.5. 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.

Creative and mediaDesign and UX
Related

image-generation compared with skills from other repositories

image-generation next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
image-generationshaharsha/claude-skillsSkill6todayMITA173Claude Code
webgl-holographic-foilnexu-io/open-designSkill106kyesterdayApache-2.0A41Claude Code, Codex
html-ppt-hermes-cyber-terminalnexu-io/open-designSkill106kyesterdayApache-2.0A53Claude Code, Codex
html-ppt-taste-brutalistnexu-io/open-designSkill106kyesterdayApache-2.0A78Claude Code, Codex
visual-ralphYeachan-Heo/oh-my-codexSkill34k4d agoMITA52Codex
glance-canonical-layoutsandroid/skillsSkill10kyesterdayApache-2.0A56Claude Code
accessibilitymicrosoft/hve-coreSkill1.6kyesterdayMITA47Claude Code