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 hxy91819/mason-skills --skill chatgpt-web-imagegit clone --depth 1 https://github.com/hxy91819/mason-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/hxy91819/mason-skills/chatgpt-web-image)<a href="https://agentmods.dev/skills/hxy91819/mason-skills/chatgpt-web-image"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/chatgpt-web-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/hxy91819/mason-skills/chatgpt-web-image"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/chatgpt-web-image.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 | $0.00057 | $0.00683 |
| Opus 5.5 | $0.00023 | $0.00273 |
| Sonnet 5.5 | $0.00011 | $0.00137 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
chatgpt-web-image scanned grade A with 1 finding 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 27d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
先探测本机 DevTools。`curl -sS -m 2 http://127.0.0.1:9222/json/version` 返回 `webSocketDebuggerUrl` 时，只 attach，不要再启动第二个浏览器： What it actually says
ChatGPT 网页生图
使用 Oracle CLI 的 browser engine 和 --generate-image，复用已登录的 Chromium profile。先确认 oracle 在 PATH，并用 oracle --help --verbose 确认当前版本支持 --generate-image。Oracle browser 只接 Chrome/Chromium CDP；Firefox 远程调试是 WebDriver BiDi，不能 attach。
浏览器入口
先探测本机 DevTools。curl -sS -m 2 http://127.0.0.1:9222/json/version 返回 webSocketDebuggerUrl 时，只 attach，不要再启动第二个浏览器：
oracle --engine browser --browser-attach-running --browser-model-strategy current \
--generate-image /absolute/path/artifacts/teapot.png \
-p "生成一张蓝绿色陶瓷茶壶的产品摄影，奶油色背景，柔和光照，无文字。"
端口不是 9222 时另加 --remote-chrome <host:port>。没有常驻 DevTools 时，使用 --browser-manual-login，让 Oracle 读取 ~/.oracle/config.json 里的 chromePath 和 manualLoginProfileDir。该 profile 保存登录态；--browser-keep-browser 只决定进程是否常驻。无 DISPLAY 时，从用户图形会话复制 DISPLAY、XAUTHORITY、DBUS_SESSION_BUS_ADDRESS 再启动。页面出现登录按钮时停止并请用户在该 profile 登录一次，不要循环重试。
生成
根据交付物明确画面、用途和尺寸。输出路径优先使用用户指定位置；否则放在当前项目的 artifacts/ 中，并避免覆盖已有文件。生图使用网页当前模型，保持 Medium，不要传 --model gpt-*-pro。账号与网页模型需支持图片生成；检查实际输出是否为图片。
Oracle 会在 ChatGPT 返回可下载图片时保存至指定路径；多张图片保存为带序号的相邻文件。完成以文件实际保存并可打开为准，检查图片内容后提供文件链接或直接展示。
恢复
若提交后超时，先用 oracle status --hours 72 找原会话，再用 oracle session <id> --render 查看结果和会话 artifacts。提示已提交但 CLI 失败时，先看已打开的 ChatGPT 标签是否已出图，已出则下载该图，不要重发。用户提供任意 ChatGPT 会话地址时，在同一已登录浏览器中打开该会话并下载已有图片；不为取图重新发送生成请求。Oracle 的会话记录可用于回看运行结果；本 Skill 不另建账本，当前没有图片质量裁决的聚合统计。
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.
- 27d ago Changed · +4 lines d504bbf521d7
- 29d ago First seen · 27 lines · 57 tokens per session scan A 9f26789051de
chatgpt-web-image is a skill published in the GitHub repository hxy91819/mason-skills (3 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 683 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-27.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…