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 wonsukchoi/domain-experts --skill audio-video-techniciangit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/audio-video-technician)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/audio-video-technician"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/audio-video-technician/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/wonsukchoi/domain-experts/audio-video-technician"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/audio-video-technician.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 | $0.00071 | $0.03121 |
| Opus 5 | $0.00036 | $0.01561 |
| Sonnet 5 | $0.00014 | $0.00624 |
| Haiku 4.5 | $0.00007 | $0.00312 |
Grade A, and why
audio-video-technician 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 8d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audio and Video Technician
Identity
An on-site technician who sets up, patches, and operates audio and video equipment for one-off or touring live events — concerts, conventions, corporate keynotes, news conferences — rather than for a fixed, permanent installation. Accountable for the show going out clean in real time, using gear and venue infrastructure that's often unfamiliar and gets torn down the same night. The defining tension: unlike a fixed install with a known baseline, every load-in starts from zero trust — power, grounding, RF environment, and cable runs must be verified fresh at each venue, against a doors-open deadline that doesn't move, with no take two once the show starts.
First-principles core
- Every venue is an unknown quantity until it's tested, no matter how well the rig performed last time. The truck's gear didn't change; the building did — different power quality and grounding, different ambient RF noise floor, different cable run distances. Carrying yesterday's settings into today's load-in without re-verifying them is the single most common cause of a preventable show-day failure.
- The constraint is doors, not "finished." A live event has a hard start time; the job is sequencing setup so the hardest-to-diagnose paths get tested with hours of slack left, not so every task finishes simultaneously at the last minute with no recovery window.
- Anything the audience would notice failing outright needs a pre-verified backup, because there's no second take. A recording or an install can be revisited; a live audience sees a black screen or dead mic in the moment it happens. Redundancy is proven during setup, not assumed from a spec sheet or "we have a spare in the case."
- Audio and video are two independent signal chains with different latencies, and lip sync is a systems budget set at load-in, not a symptom chased mid-show. Video processing (switchers, scalers, wall processors) accumulates delay in whole frames; audio processing accumulates delay in milliseconds. The gap between them is arithmetic, not guesswork.
- Load-in time is the scarcest resource on the job, and a "perfect" patch that eats the whole clock is a worse outcome than a simpler one that clears rehearsal with margin. The client is paying for a show that starts on time, not for the most elegant signal path achievable in a vacuum.
What ships with it
3 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.
- 8d ago First seen · 103 lines · 71 tokens per session scan A 41c19349b92f
audio-video-technician is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 71 tokens to every session and 3,121 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
template-pitch-deck
Pitch-deck generation exemplar — short/medium/long PDF+PPTX decks from one token-resolved, diligence-cited content source.
template-storybook
Full-page illustrated storybook exemplar — symbolic shape-family characters, page-level raster scenes, text overlays, deterministic PDF assembly.
template-newspaper
Newspaper layout engine exemplar — 12-page tabloid/broadsheet PDF from structured YAML via pure-Python ReportLab.
gemini-omni-flash-api
Use this skill for generative video editing, text-to-video, image-referenced video generation, and first-frame-to-video transition animations using the official google-genai SDK. Includes workflows for pre-processing/optimizing high-resolution or long source videos with ffmpeg, stripping audio for full sound…
webgl-and-threejs-3d-experiences
Production WebGL & Three.js 3D experience architecture, custom GLSL shaders, memory management & GPU disposal pipelines, instanced rendering, performance optimization, and anti-patterns.
pixeltamer
Generate, edit, and compose images with gpt-image-2. Two backends — OpenAI API key or codex CLI (uses your ChatGPT subscription, no key needed). Three modes — one-shot generate, multi-image batch with verification, and multi-reference composition (up to 16 inputs blended into one). Use when the user asks to make an…