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.
git clone --depth 1 https://github.com/casatwy/deyo-skillWrote 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/plugins/casatwy/deyo-skill/gemini-extension)<a href="https://agentmods.dev/plugins/casatwy/deyo-skill/gemini-extension"><img src="https://agentmods.dev/badge/plugins/casatwy/deyo-skill/gemini-extension/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/plugins/casatwy/deyo-skill/gemini-extension"><img src="https://agentmods.dev/badge/plugins/casatwy/deyo-skill/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
deyo 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 today.
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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
6 files beside gemini-extension.json 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.
- today Changed fd0d60edd59b
- 22d ago First seen · 6 lines scan A 375b80e172f1
deyo is a plugin published in the GitHub repository casatwy/deyo-skill (2 stars, last pushed yesterday), with no licence file. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-24.
Other plugins, from other repositories
omnireach
Search and read the login-walled Chinese internet, parse media, and download bounded Douyin videos for AI agents.
last30days-cn
A research plugin for finding and analysing recent content from eight Chinese platforms, including Weibo, Xiaohongshu, Bilibili, Zhihu, Douyin, WeChat, Baidu, and Toutiao.
openshorts
Turn long videos (podcasts, webinars, streams) into vertical 9:16 clips with subtitles, re-cut them, and publish them to TikTok, Instagram Reels and YouTube Shorts via the OpenShorts API or MCP server.
noisy-coding
Voice coding for Claude Code, Jarvis-style — talk to your agent while it works. Ships the voice hooks and connects to the noisy-coding daemon (Docker or native).
voice-to-claude
High-quality voice dictation for Claude Code using whisper.cpp with Metal GPU acceleration.
social-vision
Paste an Instagram, TikTok, YouTube (Shorts), or X/Twitter link and Claude watches it for you — transcribes the audio, reads the on-screen text and visuals, and explains what it's actually about. Runs locally and cross-platform.