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 alivirgo/Major-AI-Skills --skill eartrumpetgit clone --depth 1 https://github.com/alivirgo/Major-AI-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/alivirgo/major-ai-skills/eartrumpet)<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/eartrumpet"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/eartrumpet/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/alivirgo/major-ai-skills/eartrumpet"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/eartrumpet.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 | $0.00032 | $0.01771 |
| Opus 5.5 | $0.00013 | $0.00708 |
| Sonnet 5.5 | $0.00006 | $0.00354 |
| Haiku 4.5 | $0.00003 | $0.00177 |
Grade A, and why
eartrumpet 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 1mo 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EarTrumpet Windows Audio Engine AI Skill Guide (Claude)
Overview & Engine Architecture
EarTrumpet is an open-source Windows audio management application that replaces the legacy Windows volume mixer with modern, per-application audio session routing. Operating on top of the Windows Core Audio APIs (WASAPI), IAudioSessionManager2, IAudioEndpointVolume, and ISimpleAudioVolume, EarTrumpet provides real-time peak metering, individual app volume sliders, and dynamic audio endpoint redirection. Built using C# / WPF with XAML Islands, the platform packages as a Windows Store UWP/MSIX container (41808File-Save.EarTrumpet). Claude operates as a Principal Windows Systems Architect and Audio Pipeline Specialist, specializing in WASAPI audio session automation (pycaw), per-application endpoint routing, COM Audio interface debugging, and AppX container lifecycle management.
EarTrumpet System Architecture & WASAPI Audio Stack
┌─────────────────────────────────────────────────────────────┐
│ EarTrumpet & WASAPI Stack │
│ │
│ UI Presentation & XAML Islands Layer │
│ ├── WinUI / XAML Islands Flyout (Windows 11 Acrylic Blur) │
│ ├── System Tray Interop (`Shell_NotifyIcon`) │
│ └── Hotkey Ingress & Multi-Channel Visual Peak Meters │
│ │
│ Windows Core Audio (WASAPI) COM Subsystem │
│ ├── `MMDeviceEnumerator` (Audio Render / Capture Endpoints)│
│ ├── `IAudioSessionManager2` (Session Enumeration & Events) │
│ └── `ISimpleAudioVolume` (Per-Process Volume & Mute State) │
│ │
│ Audio Routing & Interop Policy Core │
│ ├── `IAudioPolicyConfigFactory` (Dynamic App Redirection) │
│ └── Shared vs Exclusive Mode Stream Management │
└─────────────────────────────────────────────────────────────┘
What ships with it
2 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.
- 1mo ago Changed · -17 tokens per session af8dde4cbf15
- 1mo ago First seen · 136 lines · 49 tokens per session scan A 5aa7d3358455
eartrumpet is a skill published in the GitHub repository alivirgo/Major-AI-Skills (2 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 1,771 once invoked, about $0.0001 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 2026-09-05.
Other skills, from other repositories
arm-cortex-expert
Senior embedded software engineer specializing in firmware and driver development for ARM Cortex-M microcontrollers (Teensy, STM32, nRF52, SAMD).
amazon-alexa
Integracao completa com Amazon Alexa para criar skills de voz inteligentes, transformar Alexa em assistente com Claude como cerebro (projeto Auri) e integrar com AWS ecosystem (Lambda, DynamoDB, Polly, Transcribe, Lex, Smart Home).
hula-skill
HuLa project skill for frontend (Vue 3 + Vite + UnoCSS + Naive UI/Vant), backend (Tauri v2 + Rust + SeaORM/SQLite), full-stack flows, and build/release work. Use when the user mentions hula or HuLa or requests changes in this repository; after triggering, ask which scope (frontend/backend/fullstack/build-release) to…
dma-attack-techniques
Analyze PCIe DMA threats, host-mediated memory acquisition, FPGA behavior, and IOMMU defenses. Use when the memory initiator or device boundary matters; use kernel security for host-only mechanisms.
skill-deployment
Use when deploying the shared agent skills via chezmoi, or fixing "not managed" errors.
hermes-cron-automations
Use when building a recurring automation on the Hermes box.