image-gen

image-gen is a skill for Claude Code from djbelieny/nova. It costs 94 tokens per session (845 once invoked), scanned A, original, MIT.

An image-generation skill that turns written descriptions into images using AI models. It can produce visuals in styles such as photographs, paintings, illustrations, and 3D renders.

In plain words
What is it for?
Use it to create pictures, illustrations, graphics, logos, icons, artwork, or other visual assets from text prompts. Generated images can be saved to a chosen file path.
Why use it?
It removes the need to create every visual manually or search for a matching image. The prompt can describe the subject, style, lighting, composition, and mood.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; positional $N argument.

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/djbelieny/nova/image-gen
Any agent
npx skills add djbelieny/nova --skill image-gen
Clone the repo
git clone --depth 1 https://github.com/djbelieny/nova

Made for: Claude Code.

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-gen

README.md
[![agentmods](https://agentmods.dev/badge/skills/djbelieny/nova/image-gen.svg)](https://agentmods.dev/skills/djbelieny/nova/image-gen)
Your own site
<a href="https://agentmods.dev/skills/djbelieny/nova/image-gen"><img src="https://agentmods.dev/badge/skills/djbelieny/nova/image-gen.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 845 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 5.1 $0.00094 $0.00845
Opus 5 $0.00047 $0.00423
Sonnet 5 $0.00019 $0.00169
Haiku 4.5 $0.00009 $0.00085

Measured 6d ago against content hash f39dce0bacdd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

image-gen 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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/generate_image.py), 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.

.claude/skills/image-gen/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Image Generation

Generate images from text descriptions using the scripts/generate_image.py script. Primary provider is Gemini 2.5 Flash (free tier: 1,500 images/day). Falls back to OpenAI gpt-image-1 if Gemini is unavailable.

Quick Start

python scripts/generate_image.py "a sunset over mountains in watercolor style" /tmp/sunset.png

Workflow

1. Craft the Prompt

Transform the user's request into a detailed image generation prompt:

  • Add style descriptors: "photorealistic", "oil painting", "minimalist illustration", "3D render"
  • Add lighting: "golden hour", "soft natural light", "dramatic shadows"
  • Add composition: "close-up", "wide angle", "centered", "rule of thirds"
  • Add mood: "serene", "energetic", "mysterious", "whimsical"
  • Keep the user's core intent — enhance, don't override

2. Generate the Image

Run the script with the crafted prompt:

python ~/.claude/skills/image-gen/scripts/generate_image.py "<prompt>" <output_path>

Arguments:

  • prompt (required) — text description of the image
  • output (optional) — file path for the output image (default: /tmp/<name>.png)
  • --provider gemini|openai|auto — force a specific provider (default: auto)
  • --size 1024x1024 — image size, OpenAI only (options: 1024x1024, 1024x1536, 1536x1024)

Environment variables required:

3. Present the Result

After generation, read the output image file to display it to the user. The script prints the output path on success.

4. Iterate

If the user wants changes, modify the prompt and regenerate. Common adjustments:

  • "Make it more colorful" — add "vibrant colors, saturated"
  • "More realistic" — add "photorealistic, 8K, detailed"
  • "Simpler" — add "minimalist, clean, simple"
  • "Different style" — replace style descriptors

Provider Selection

Read the full file on GitHub · 79 lines

Files

What ships with it

2 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. 6d ago First seen · 79 lines · 94 tokens per session scan A f39dce0bacdd

Subscribe to this mod's changes

image-gen is a skill published in the GitHub repository djbelieny/nova (5 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 845 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

commonly

You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…

Team-Commonly/commonly · 0 tokens

officecli-commonly-templates

Use this skill when producing a polished, Commonly-branded deliverable (.docx brief / memo, .xlsx data matrix, .pptx deck) and you do not have specific brand guidance from the user. Trigger on: 'write me a brief', 'one-pager', 'memo', 'data sheet', 'status matrix', 'short deck', 'summary deck', 'closing slide', 'final…

Team-Commonly/commonly · 182 tokens

github

Interact with GitHub (issues, PRs, repos, releases) using the gh CLI. Use when asked to read or write GitHub state — open an issue, fetch PR diff, comment, list runs, etc.

Team-Commonly/commonly · 49 tokens

markdown-converter

Convert binary documents (PDF, DOCX, XLSX, PPTX, HTML, EPUB, images) to clean LLM-friendly Markdown using Microsoft's markitdown Python tool. Use when a user attaches a binary file and you need to read its contents.

Team-Commonly/commonly · 57 tokens

pandic-office

Convert Markdown to PDF (or DOCX/EPUB/HTML) using the pandoc CLI. Use when asked to produce a PDF report, brief, summary, or any document where the input is Markdown and the output should be a polished, paginated file.

Team-Commonly/commonly · 59 tokens

pdf

Manipulate PDF files — extract text, count pages, render thumbnails, merge or split documents. Use for PDF-specific operations that don't fit markdown-converter (general read) or pandic-office (write from markdown).

Team-Commonly/commonly · 49 tokens