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 idea2realClaw/myAgent --skill qualcomm-ai-assistantgit clone --depth 1 https://github.com/idea2realClaw/myAgentWrote 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/idea2realclaw/myagent/qualcomm-ai-assistant)<a href="https://agentmods.dev/skills/idea2realclaw/myagent/qualcomm-ai-assistant"><img src="https://agentmods.dev/badge/skills/idea2realclaw/myagent/qualcomm-ai-assistant/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/idea2realclaw/myagent/qualcomm-ai-assistant"><img src="https://agentmods.dev/badge/skills/idea2realclaw/myagent/qualcomm-ai-assistant.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 | $0.00151 | $0.00645 |
| Opus 5 | $0.00076 | $0.00322 |
| Sonnet 5 | $0.00030 | $0.00129 |
| Haiku 4.5 | $0.00015 | $0.00064 |
Grade A, and why
qualcomm-ai-assistant 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.
What it actually says
Qualcomm AI Assistant Skill
通过浏览器自动化访问 Qualcomm 官方文档网站的 AI Assistant，发送问题并获取基于高通文档库的 AI 回复。
前置条件
playwright-cli已安装（npm install -g @playwright/cli@latest）- 系统安装了 Edge 浏览器（Windows 环境默认可用）
- 网络可访问
docs.qualcomm.com
使用方法
# 基本用法 - 向 AI 助手提问
python scripts/ask_qualcomm_ai.py "What is IQ-9075?"
# 指定产品页面
python scripts/ask_qualcomm_ai.py "How to set up the development kit?" --product 1601111740076079
# 等待更长时间（复杂问题）
python scripts/ask_qualcomm_ai.py "Compare IQ-9075 with QCS8250" --timeout 60
工作流程
- 使用
playwright-cli打开 Edge 浏览器 - 导航到指定的高通产品文档页面
- 等待 AI Assistant 面板加载
- 在输入框中填入问题
- 按 Enter 发送
- 等待 AI 生成回复（轮询检测 "Generating..." 状态消失）
- 从页面快照中提取回复文本和引用来源
- 关闭浏览器并返回结构化结果
输出格式
脚本输出为 JSON 格式，包含：
question: 用户提出的问题answer: AI 助手的回复文本（Markdown 格式）sources: 引用的文档链接列表product_url: 当前产品页面 URL
注意事项
- AI 回复时间通常 15-30 秒，复杂问题可能需要更长时间
- 未登录时 AI 功能有限，建议登录高通开发者账号以获取更完整的文档访问
- 如果 "Generating..." 状态超过 60 秒未消失，视为超时
- 每次提问会开启新聊天（自动点击 "Start a new chat"）
What ships with it
4 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.
- 9d ago First seen · 65 lines · 151 tokens per session scan A 994a90fa11d8
qualcomm-ai-assistant is a skill published in the GitHub repository idea2realClaw/myAgent (2 stars, last pushed 20d ago), licensed MIT. It adds 151 tokens to every session and 645 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
screen-recording-on-chromebook
Records screen video on ChromeOS devices, Chromebooks, and CrOS DUTs over SSH using ffmpeg KMS grab, and transcodes the video to MP4 on the host workstation. Use when recording the screen of a Chromebook, ChromeOS device, cros DUT, or CrOS test hardware, capturing visual bug reproductions or feature demonstrations on…
physical-chromebook-debugging
Build and deploy Chrome to a physical ChromeOS device, monitor logs, and take screenshots over SSH. Use when working with remote Chromebook testing hardware, deploying new builds of Chrome or ChromeOS, reading specific log files via SSH, or taking screenshots of a connected test endpoint.
go2rtc-cameras
Multi-camera RTSP to WebRTC streaming via go2rtc.
lichtblick
Use when deploying, launching, or reviewing the Lichtblick web viewer — an open-source, Foxglove-compatible MCAP / ROS-bag / robotics log viewer served from S3 artifacts.
cad-viewer-skill
Start or reuse CAD Viewer and return review links for CAD, implicit, robot-description, and G-code files (.step, .stl, .glb, .3mf, .gcode, .dxf, .urdf, .srdf, .sdf).
digikey
Proven scraping playbook for digikey.com /en/products/category/ listings. Cloudflare challenge (cf-mitigated: challenge) blocks bare curl with HTTP 403, but a puppeteer connection to the user's real Chrome via the real Chrome debug port walks straight through with zero stealth, no captcha, no proxy, no auth. Listings…