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 calesthio/generative-media-skills --skill openai-gpt-imagegit clone --depth 1 https://github.com/calesthio/generative-media-skillsWrote 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/calesthio/generative-media-skills/openai-gpt-image)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/openai-gpt-image"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/openai-gpt-image/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/calesthio/generative-media-skills/openai-gpt-image"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/openai-gpt-image.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- medium Excessive Agency · line 447 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00124 | $0.07598 |
| Opus 5 | $0.00062 | $0.03799 |
| Sonnet 5 | $0.00025 | $0.01520 |
| Haiku 4.5 | $0.00012 | $0.00760 |
Grade A, and why
openai-gpt-image 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.
How it starts
The opening of the file, as written. The whole thing — 511 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Produce still images with OpenAI GPT Image
Use this skill for OpenAI still-image generation and editing. Do not route video, animation, speech, transcription, or music work through it.
Read claims by evidence label
- Documented fact means OpenAI currently documents the behavior.
- Production heuristic means a practical workflow recommendation derived from documented behavior and production risk, not an API guarantee.
- Inference means a reasoned conclusion that must be validated on the actual workload.
Treat model names, prices, limits, supported parameters, regional availability, policy, and lifecycle dates as volatile. Recheck the linked official source immediately before building or quoting them to a user. The volatile facts below were verified 2026-07-09.
Start with the current lifecycle, not remembered model names
Documented facts, verified 2026-07-09:
| Model | Current role | Lifecycle / migration action |
|---|---|---|
gpt-image-2 |
Current production default for generation and editing; alias plus snapshot gpt-image-2-2026-04-21 |
Use the alias for automatic updates or the snapshot when regression stability is required. |
gpt-image-1.5 |
Previous model | Deprecated; scheduled API removal 2026-12-01. Migrate to gpt-image-2. |
gpt-image-1 |
Previous model | Deprecated; scheduled API removal 2026-10-23. Migrate to gpt-image-2. |
gpt-image-1-mini |
Cost-efficient GPT Image 1 variant | Deprecated; scheduled API removal 2026-12-01. Do not begin a new dependency on it; test gpt-image-2 with quality="low". |
dall-e-3, dall-e-2 |
Legacy migration knowledge only | Deprecated and removed from the API 2026-05-12. Replace, do not select. |
Sources: GPT Image 2 model page, all-model catalog, deprecations.
Production heuristic: Default new work to gpt-image-2. Keep a deprecated GPT Image model only long enough to run a measured migration comparison against existing prompts. Do not choose a deprecated model merely because its per-image table appears cheaper.
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 · 511 lines · 124 tokens per session scan A eb20db5862de
openai-gpt-image is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 124 tokens to every session and 7,598 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
cliptalk-cover-director
Produces evidence-backed cover candidates and reviewable cover variants for a ClipTalk video. Use when the user asks for a cover, poster frame, thumbnail, or multiple cover directions; do not use for timeline editing or social-video reframing.
cliptalk-smart-reframe
Creates a subject-aware, time-varying crop track and a review-only social-format preview from an accepted ClipTalk cut. Use for automatic vertical, square, or portrait reframing; do not use for a fixed manual crop or before content editing is accepted.
cliptalk-content-extractor
Locates and assembles source passages matching a semantic request. Use for extracting explanations, topics, quotes, demonstrations, or other specifically described content.
cliptalk-interview-editor
Produces a coherent interview edit by combining speaker discovery, topic selection, dialogue context, cleanup, subtitles, and preview. Use for interviews, podcasts, testimonials, or question-and-answer recordings.
cliptalk-shortform-hook-director
Finds and assembles a reviewable short-form cut with a strong opening hook. Use for Shorts, Reels, social clips, talking-head cutdowns, or requests for a punchier opening.
cliptalk-social-reframe-exporter
Creates a review-only 9:16, 4:5, 1:1, or 16:9 version from an existing accepted ClipTalk cut, then checks the rendered preview. Use only when a cut already exists and the user asks to adapt it for Shorts, Reels, Douyin, Xiaohongshu, WeChat Channels, or square feeds; do not use when the user still needs content found…