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 ask-gpt-progit 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/ask-gpt-pro)<a href="https://agentmods.dev/skills/hxy91819/mason-skills/ask-gpt-pro"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/ask-gpt-pro/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/ask-gpt-pro"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/ask-gpt-pro.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 | $0.00084 | $0.01568 |
| Opus 5.5 | $0.00034 | $0.00627 |
| Sonnet 5.5 | $0.00017 | $0.00314 |
| Haiku 4.5 | $0.00008 | $0.00157 |
Grade A, and why
ask-gpt-pro 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 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.
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： How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ask GPT Pro
使用 Oracle CLI 的 browser engine 发送一次性咨询。Oracle 负责浏览器连接、会话记录和回答抓取；登录态由 Chromium profile 保存。先确认 oracle 在 PATH，并用 oracle --version、oracle --help --verbose 和 oracle session --help 确认当前版本支持所用参数。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 --model gpt-6-pro --browser-archive never --verbose -p "<问题>"
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。当前账号没有所写模型时，根据账号可用的 Pro 型号显式调整 --model，检查 Oracle 的模型选择结果，不依赖网页默认选择。
2026-10-15 实测 Oracle 0.21.5 可操作改版后的 ChatGPT：模型菜单列出 GPT-6 和 GPT-5.6 Sol；输入框按钮显示当前推理强度（如 Medium、Pro），aria-label 为 Select ChatGPT model。菜单中的 Thinking effort / Power 滑杆最右档为 Pro。以页面可见标签和滑杆状态核对，按钮的 data-selected-reasoning-effort 可能仍为 medium，不能单独作为强度依据。
--model gpt-6-pro 会选择 GPT-6 并将推理强度设为 Pro，默认 --browser-model-strategy select 即可；无需手动预选，也无需 current 绕过选择。--reasoning-effort / --reasoning-mode 是 API 参数，不用它们设置网页滑杆。加 --verbose 核对最终两条证据：
Model selection evidence：requestedKey=gpt-6-pro; target=GPT-6; resolvedLabel=GPT-6，且verified=yes。Thinking effort evidence：requestedLevel=pro; resolvedLabel=Pro，且verified=yes。状态可以是switched或已选中。
实测该版本能识别发送成功并自动取回 OK。0.21.1 在该页面上找不到模型按钮；手动预选后也可能报 Prompt did not appear 且续取为 Assistant turns: 0，应升级后使用上述流程。运行前记录页面模型和强度；咨询结束或失败后恢复原值，并重新打开菜单核对；恢复默认偏好时刷新原新会话页再核对。实测已完成的 Pro 咨询页重载后仍可能显示该轮的 Pro，需与新会话默认强度分开核验。
发送问题的 browser 调用（包括 manual-login 和 follow-up）默认显式传入 --browser-archive never，将会话保留在 ChatGPT 历史中。只有用户明确要求归档时才改用其他策略。Oracle 自身的默认 auto 会归档成功的非项目单次咨询；本机通用默认可在 ~/.oracle/config.json 的 browser 对象中设置 archiveConversations: "never"，CLI 显式参数优先。oracle session <id> 只取回已有记录，无需加归档参数。
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 Changed · +22 tokens per session b50d0cb3dfc5
- 10d ago Changed · +18 lines 8951531e39fe
- 11d ago Changed · +4 lines 33c4c6698bf2
- 27d ago Changed 553b8be73b07
- 29d ago First seen · 27 lines · 62 tokens per session scan A 9e9cfd8eef73
ask-gpt-pro is a skill published in the GitHub repository hxy91819/mason-skills (3 stars, last pushed yesterday), licensed MIT. It adds 84 tokens to every session and 1,568 once invoked, about $0.0003 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
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.
data-scraper-agent
Build a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. Scrapes on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitHub Actions. Use when…
ai-sdk
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI…
protractor-skill
Generates Protractor E2E tests for Angular/AngularJS apps in JS/TS. NOTE: Protractor is officially deprecated — recommend Playwright or Cypress. Use when user mentions "Protractor", "element(by.model())", "Angular E2E". Triggers on: "Protractor", "element(by.model)", "Angular E2E test", "protractor.conf".
local-slm-edge-ai-expert
Expert guide for Local Small Language Models (SLMs) and Edge AI execution — WebLLM, Transformers.js v3, ONNX Runtime Web, WebGPU, and zero-latency local embeddings / Panduan ahli SLM lokal dan AI edge di browser.
lightcad
Use when building or extending a desktop CAD/BIM application with the open-source FeiYang LightCAD platform — plugin development, custom elements, DWG/DXF I/O, 2D drafting and 3D/BIM modeling on C#/.NET. LightCAD (FeiYang Integrated Design Platform) is a C# CAD system integrating 2D design, 3D design, and BIM.