A set of instructions for generating new images with OpenAI's Images API, including illustrations, logos, artwork, and other visual designs. It lists supported command options such as model, size, quality, and style.

Use it to create a new visual from a text prompt, such as a logo, illustration, banner, or scene. It can also guide selection of image model, dimensions, quality, and style.

It explains when image generation is appropriate and when another tool should be used, such as for editing an existing image or converting formats. It also describes the required API-key setup.

image_gen — Skill for Claude Code and Codex by ericwang915/PythonClaw

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/ericwang915/PythonClaw

agentmods

npx agentmods add skills/ericwang915/pythonclaw/image_gen

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ericwang915/pythonclaw/image_gen/github.svg)](https://agentmods.dev/skills/ericwang915/pythonclaw/image_gen)

Your own site

<a href="https://agentmods.dev/skills/ericwang915/pythonclaw/image_gen"><img src="https://agentmods.dev/badge/skills/ericwang915/pythonclaw/image_gen/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ericwang915/pythonclaw/image_gen"><img src="https://agentmods.dev/badge/skills/ericwang915/pythonclaw/image_gen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 624 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00058	$0.00624
Opus 5.5	$0.00023	$0.00250
Sonnet 5.5	$0.00012	$0.00125
Haiku 4.5	$0.00006	$0.00062

Measured 1mo ago against content hash 265b08abe575, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (generate.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.

pythonclaw/templates/skills/media/image_gen/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Image Generation

Generate images via the OpenAI Images API.

When to Use

✅ USE this skill when:

"Generate an image of a sunset over mountains"
"Create a logo for my project"
"Draw a cartoon cat wearing a hat"
"Design a banner for my blog"
"Make me an illustration of X"

When NOT to Use

❌ DON'T use this skill when:

Editing or modifying existing images → use image editing tools
Screenshot capture → use system screenshot tools
Image format conversion → use run_command with ImageMagick/Pillow
Web image search → use web_search tool

Setup

Requires an OpenAI API key with Images API access.

Configure in pythonclaw.json:

"skills": {
  "image_gen": {
    "apiKey": "sk-your-openai-key"
  }
}

Or set OPENAI_API_KEY environment variable.

Commands

Generate an image

python {skill_path}/generate.py "a serene mountain lake at sunset, watercolor style"

Options

# Specific model
python {skill_path}/generate.py "prompt" --model dall-e-3

# Size options
python {skill_path}/generate.py "prompt" --size 1792x1024

# Quality
python {skill_path}/generate.py "prompt" --quality hd

# Style (dall-e-3 only)
python {skill_path}/generate.py "prompt" --style vivid

# Output directory
python {skill_path}/generate.py "prompt" --output ./images/

Model-Specific Parameters

DALL-E 3:

Sizes: 1024x1024, 1792x1024, 1024x1792
Quality: standard, hd
Style: vivid, natural
Generates 1 image at a time

DALL-E 2:

Sizes: 256x256, 512x512, 1024x1024
Quality: standard only
Can generate multiple images

Notes

Output is saved as PNG files in the specified directory (default: current dir)
Each generation costs API credits (DALL-E 3 HD ~$0.08/image)
Prompts are sometimes rewritten by the API for safety
Use --style natural for more photographic results

Resources

File	Description
`generate.py`	OpenAI Images API wrapper

Read the full file on GitHub · 100 lines

Files

What ships with it

1 file 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.

generate.py 3.2 KB runs code

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.

1mo ago First seen · 100 lines · 58 tokens per session scan A 265b08abe575

Subscribe to this mod's changes

image_gen is a skill published in the GitHub repository ericwang915/PythonClaw (45 stars, last pushed 10d ago), licensed MIT. It adds 58 tokens to every session and 624 once invoked, about $0.0002 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 2026-08-30.

Creative and media ai ai-agent autonomous-agent chatbot deepseek framework

image_gen