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.
npx skills add mupengi-bot/mupengism --skill openai-image-cligit clone --depth 1 https://github.com/mupengi-bot/mupengismWrote 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.
[](https://agentmods.dev/skills/mupengi-bot/mupengism/openai-image-cli)<a href="https://agentmods.dev/skills/mupengi-bot/mupengism/openai-image-cli"><img src="https://agentmods.dev/badge/skills/mupengi-bot/mupengism/openai-image-cli/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.
<a href="https://agentmods.dev/skills/mupengi-bot/mupengism/openai-image-cli"><img src="https://agentmods.dev/badge/skills/mupengi-bot/mupengism/openai-image-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00024 | $0.01651 |
| Opus 5 | $0.00012 | $0.00826 |
| Sonnet 5 | $0.00005 | $0.00330 |
| Haiku 4.5 | $0.00002 | $0.00165 |
Grade A, and why
openai-image-cli 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.
How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenAI Image CLI 🐧
Generate, edit, and create variations of images using OpenAI's latest models.
Installation
npm install -g @versatly/openai-image-cli
Authentication
# Via environment variable
export OPENAI_API_KEY=sk-...
# Or via config
openai-image config set api-key sk-...
Quick Start
# Generate an image
openai-image generate "A futuristic city at sunset"
# High quality landscape
openai-image generate "Mountain panorama" -s 1536x1024 -q high
# Multiple images with transparency
openai-image generate "Logo design" -n 4 -b transparent
# Edit an existing image
openai-image edit photo.png "Add sunglasses to the person"
# Create variations (DALL-E 2)
openai-image vary original.png -n 3
Available Models
| Model | Description | Notes |
|---|---|---|
gpt-image-1.5 |
Latest GPT Image (default) | Best quality, recommended |
gpt-image-1 |
GPT Image | Good balance |
gpt-image-1-mini |
GPT Image Mini | Cost-effective |
dall-e-3 |
DALL-E 3 | Deprecated May 2026 |
dall-e-2 |
DALL-E 2 | Deprecated May 2026, supports variations |
Commands
generate
Create images from text prompts.
openai-image generate "prompt" [options]
Options:
-m, --model <model> Model (default: gpt-image-1.5)
-s, --size <size> Size: 1024x1024, 1536x1024, 1024x1536, auto
-q, --quality <quality> Quality: auto, high, medium, low
-n, --count <n> Number of images (1-10)
-f, --format <format> Format: png, jpeg, webp
-o, --output <path> Output file/directory
-b, --background <bg> Background: auto, transparent, opaque
--compression <0-100> Compression level for jpeg/webp
--moderation <level> Content moderation: auto, low
--stream Enable streaming with partial images
--partial-images <0-3> Partial images during streaming
--json Output JSON response
--dry-run Show request without executing
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.
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.
- 8d ago First seen · 229 lines · 24 tokens per session scan A 0d0ae90ae6ff
openai-image-cli is a skill published in the GitHub repository mupengi-bot/mupengism (10 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 1,651 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 2026-08-31.
Other skills, from other repositories
hive.image-generation
Required before calling imagegenerate. Create and edit images from a prompt — generate an image, make a picture / logo / illustration / icon / banner / poster / thumbnail / hero image / mockup / product shot / social graphic, or edit / restyle / combine existing images from reference images. Uses OpenAI gpt-image-2…
image-posting
Skill for embedding images in chat replies: URL detection from tool results, Markdown image syntax, and assets paths. Use when: surfacing images from search or generation tools, pasting Markdown images, or showing attachments.
image-gen-tool
Image and 3D model generation tool using NovelAI, Flux, and Meshy for illustrations and 3D output. Use when: generating character art, bust or chibi images, avatars, or running image pipelines.
transcribe-tool
Audio transcription tool. Converts audio files to text with Whisper and optional LLM post-processing. Use when: transcribing meetings, podcasts, or extracting text from recorded audio files.
prompt-craft
Translate natural language image descriptions into detailed, structured DALL-E prompts with subject, style, composition, lighting, and mood specifications.
presentation-template-designer
Plan reusable presentation templates from a creative brief, optional brand assets, or an existing deck. Use when Codex needs to define a slide inventory, choose an editable presentation toolchain, author or validate a template manifest, adapt a visual system for PowerPoint or Google Slides, or prepare a reviewed…