GPT Image Playground is a web application for generating and editing images through the OpenAI gpt-image-2 API and compatible image providers. Users can create images from text, edit them with reference images and masks, and manage their history and settings locally. The catalogue includes an instruction for working with the application.
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 CookSleep/gpt_image_playground --skill gpt-image-playgroundgit clone --depth 1 https://github.com/CookSleep/gpt_image_playgroundWrote 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/cooksleep/gpt_image_playground/gpt-image-playground)<a href="https://agentmods.dev/skills/cooksleep/gpt_image_playground/gpt-image-playground"><img src="https://agentmods.dev/badge/skills/cooksleep/gpt_image_playground/gpt-image-playground/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/cooksleep/gpt_image_playground/gpt-image-playground"><img src="https://agentmods.dev/badge/skills/cooksleep/gpt_image_playground/gpt-image-playground.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 | $0.00164 | $0.01159 |
| Opus 5.5 | $0.00066 | $0.00464 |
| Sonnet 5.5 | $0.00033 | $0.00232 |
| Haiku 4.5 | $0.00016 | $0.00116 |
Grade A, and why
gpt-image-playground 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 11d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
用 GPT Image Playground 生图与修改设置
GPT Image Playground 是用户电脑上的生图应用。它的 CLI gpt-image-playground 操作的就是正在运行的应用：生图用应用里启用的 API 配置和参数，结果会出现在应用的历史记录中；修改设置与在设置页里操作一样，界面会立即更新。
调用方式
- 安装时勾选了“添加到 PATH”可以直接调用，否则写完整路径，默认是
%LOCALAPPDATA%\GPT Image Playground\bin\gpt-image-playground.exe。参数与 JSON 字段见 references/cli.md。 - 应用需要保持打开。提示应用没有运行时，请用户打开后再试。
生图
gpt-image-playground generate 一只趴在键盘上的橘猫 --quality low
gpt-image-playground generate 把背景换成海边 --image D:\图片\猫.png --size 1536x1024
gpt-image-playground generate --prompt 春天的森林 --prompt 冬天的森林 -n 2
generate要等全部图片生成完才返回，常常需要几分钟，一律放到后台运行，结束后再读输出。- 提交后先输出任务 ID，结束时输出每张图片的路径，可以直接打开查看。这些是应用数据目录里的文件，只读，不要改动、移动或删除；要另存一份，加
--output <目录>。 - 多个
--prompt会按应用的批量方式一起提交。批量任务进行中时应用不接受新的生图，需要等它结束。 --image是参考图：本机图片的路径，或历史记录中的图片 ID，可以给多张。--size、--quality、-n等参数会保存为应用的参数，之后的生图都沿用；只想用一次时，生成后再改回去。- 失败时输出原因。鉴权、额度、内容审核这类错误重试也没用，直接告诉用户。
- 命令被中断时，应用里的生成会继续：用
history <任务 ID>…查看结果，不要重新生成。
历史记录
history按时间倒序列出任务，包括任务 ID、提示词、参数、图片 ID 和图片路径；history <任务 ID>…只看这几个任务。image <图片 ID 或任务 ID>输出图片的路径。- 用户可以在应用的任务详情里复制任务 ID 和图片 ID 给你。
查看与修改设置
只在用户要求时修改，改之前说明要改什么；删除不能撤销，先确认。先用 settings --json 看当前值，各项含义见 references/settings.md。
| 要做的事 | 命令 |
|---|---|
| 改偏好设置、生图参数、网络代理 | settings set <键> <值> |
| 切换启用的 API 配置 | profile use <配置 ID> |
| 新建 API 配置、修改配置或换模型、填写 API Key | profile save <JSON>（修改时加 --id <配置 ID>） |
| 删除 API 配置 | profile delete <配置 ID> |
| 接入第三方图像 API | 先 provider save <JSON>，再新建一个使用它的 API 配置，见 references/custom-provider.md |
| 删除自定义服务商 | provider delete <服务商 ID> |
- API Key 只能写入，读不到原值；不要在回复里复述用户给的 Key。
- 预置配置标有
locked时只能改 API Key 和选中的模型。 - 应用会纠正不合法的值，以输出中实际保存的值为准。
- 清空数据、导入导出备份、更改数据目录只能在应用里操作。
须知
- 要解析结果时加
--json，非 ASCII 字符会转义为\uXXXX，任何代码页下都能正确解析。 - Windows PowerShell 5.1 直接读取文本输出前，先执行
[Console]::OutputEncoding = [Text.Encoding]::UTF8，否则中文会乱码。 - 退出码：0 成功，1 出错（应用没有运行、应用返回错误），2 参数不对；原因写在 stderr。
What ships with it
3 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.
- 11d ago First seen · 60 lines · 164 tokens per session scan A e62e6acf17c3
gpt-image-playground is a skill published in the GitHub repository CookSleep/gpt_image_playground (4,035 stars, last pushed yesterday), licensed MIT. It adds 164 tokens to every session and 1,159 once invoked, about $0.0007 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 2026-10-26.
gpt-image-playground compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gpt-image-playgroundCookSleep/gpt_image_playground | Skill | 4.0k | yesterday | MIT | A | 164 | Claude Code, Codex |
| replicate-imagesericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 84 | Claude Code, Codex |
| codex-imageqwwiwi/codex-gpt-image-2-subscription | Skill | 9 | yesterday | MIT | A | 110 | Claude Code |
| logo-companyqwwiwi/codex-gpt-image-2-subscription | Skill | 9 | yesterday | MIT | A | 301 | Claude Code, Codex |
| openai-image-genJansenAnalytics/claudex | Skill | 5 | 4mo ago | MIT | A | 25 | Claude Code, Codex |
| shadcnshadcn-ui/ui | Skill | 127k | yesterday | MIT | A | 113 | Claude Code, Codex, Cursor |
| migrate-radix-to-baseshadcn-ui/ui | Skill | 127k | yesterday | MIT | A | 61 | Cursor |