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.
git clone --depth 1 https://github.com/metaspartan/cybaranpx agentmods add skills/metaspartan/cybara/openai-image-genWrote 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/metaspartan/cybara/openai-image-gen)<a href="https://agentmods.dev/skills/metaspartan/cybara/openai-image-gen"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/openai-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.
<a href="https://agentmods.dev/skills/metaspartan/cybara/openai-image-gen"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/openai-image-gen.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 | $0.00025 | $0.00865 |
| Opus 5 | $0.00013 | $0.00432 |
| Sonnet 5 | $0.00005 | $0.00173 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade A, and why
openai-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 9d 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.
This is a copy
97% identical to openai-image-gen — 22 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenAI Image Gen
Generate a handful of “random but structured” prompts and render them via the OpenAI Images API.
Run
python3 {baseDir}/scripts/gen.py
open ~/Projects/tmp/openai-image-gen-*/index.html # if ~/Projects/tmp exists; else ./tmp/...
Useful flags:
# GPT image models with various options
python3 {baseDir}/scripts/gen.py --count 16 --model gpt-image-1
python3 {baseDir}/scripts/gen.py --prompt "ultra-detailed studio photo of a lobster astronaut" --count 4
python3 {baseDir}/scripts/gen.py --size 1536x1024 --quality high --out-dir ./out/images
python3 {baseDir}/scripts/gen.py --model gpt-image-1.5 --background transparent --output-format webp
# DALL-E 3 (note: count is automatically limited to 1)
python3 {baseDir}/scripts/gen.py --model dall-e-3 --quality hd --size 1792x1024 --style vivid
python3 {baseDir}/scripts/gen.py --model dall-e-3 --style natural --prompt "serene mountain landscape"
# DALL-E 2
python3 {baseDir}/scripts/gen.py --model dall-e-2 --size 512x512 --count 4
Model-Specific Parameters
Different models support different parameter values. The script automatically selects appropriate defaults based on the model.
Size
- GPT image models (
gpt-image-1,gpt-image-1-mini,gpt-image-1.5):1024x1024,1536x1024(landscape),1024x1536(portrait), orauto- Default:
1024x1024
- Default:
- dall-e-3:
1024x1024,1792x1024, or1024x1792- Default:
1024x1024
- Default:
- dall-e-2:
256x256,512x512, or1024x1024- Default:
1024x1024
- Default:
Quality
- GPT image models:
auto,high,medium, orlow- Default:
high
- Default:
- dall-e-3:
hdorstandard- Default:
standard
- Default:
- dall-e-2:
standardonly- Default:
standard
- Default:
Other Notable Differences
- dall-e-3 only supports generating 1 image at a time (
n=1). The script automatically limits count to 1 when using this model. - GPT image models support additional parameters:
--background:transparent,opaque, orauto(default)--output-format:png(default),jpeg, orwebp- Note:
streamandmoderationare available via API but not yet implemented in this script
- dall-e-3 has a
--styleparameter:vivid(hyper-real, dramatic) ornatural(more natural looking)
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.
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.
- 9d ago First seen · 72 lines · 25 tokens per session scan A a88b77326827
openai-image-gen is a skill published in the GitHub repository metaspartan/cybara (30 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 865 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to openai-image-gen, differing in 22 lines, and is treated as a copy.
Other skills, from other repositories
kodama-verification
Define measurable success criteria and collect targeted test, build, lint, type-check, or smoke-test evidence before claiming work is complete.
kodama-behavior
Classify requests, assess unfamiliar codebases, delegate work safely, and recover from failed attempts. Use for multi-step, ambiguous, or parallelizable work.
kodama-constraints
Enforce non-negotiable safety, scope, security, and quality constraints for implementation and review work.
project-release-check
Validate this example project's release readiness. Use before publishing a release candidate.
slop-taste
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
slop-hallmark
Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots. Use when the user asks to build a new app or landing page, wants to redesign something, invokes Hallmark by name, or uses audit/redesign/study.