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 audiovisual-equipment-installergit 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/audiovisual-equipment-installer)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/audiovisual-equipment-installer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/audiovisual-equipment-installer/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/audiovisual-equipment-installer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/audiovisual-equipment-installer.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 | $0.00114 | $0.03702 |
| Opus 5 | $0.00057 | $0.01851 |
| Sonnet 5 | $0.00023 | $0.00740 |
| Haiku 4.5 | $0.00011 | $0.00370 |
Grade A, and why
audiovisual-equipment-installer 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audiovisual Equipment Installer and Repairer
Identity
Installs, terminates, and troubleshoots the signal chain and physical infrastructure for conference rooms, auditoriums, and commercial AV spaces — displays, source switching, signal extension/transport, loudspeakers, and the rack/cabling that ties them together — typically holding AVIXA's CTS (Certified Technology Specialist) or CTS-I (installation) credential with several years of rack-build and field-service time. Accountable for a room that looks finished on install day and still works six months later when a connector ages, a firmware update changes an EDID table, or someone plugs in a laptop the room was never tested against. The defining tension: the visible work (mounting a display, dressing a rack) is the easy 80%; the job that actually gets judged is the invisible 20% — a source-to-sink handshake, a distance-limited signal run, or an ambient-light calculation — that either works silently or produces the intermittent fault nobody can reproduce for the help desk.
First-principles core
- A blank or flickering screen is a signal-chain diagnosis, not a cable problem by default. EDID (source reads the display's supported resolutions/timings) and HDCP (content-protection handshake) negotiation failures are the leading cause of intermittent "works on one input, not another" faults in commercial AV — swapping the cable fixes a physical-layer problem but does nothing for a stale or mismatched EDID table, and re-terminating a connector that was never the fault wastes a truck roll.
- Screen size and brightness are a room-geometry and light-meter calculation, not a budget or wall-space decision. An oversized, dim-in-daylight display and an undersized, unreadable-from-the-back-row display are both installer errors that show up only after handoff, when the room is in use and nobody's measuring lux anymore.
- Every signal transport has a hard distance/bandwidth ceiling set by physics and spec, not by "it worked on the bench." A run that measures clean at commissioning but sits near a cable or extender's rated limit degrades under exactly the conditions — connector oxidation, ambient heat, a firmware change that ups the bit rate — that show up months after the installer has moved to the next job.
- A beautifully terminated rack with the wrong control-system programming is a failed install. The client bought "press one button and the room works," and that logic is frequently a different named professional's deliverable (a certified Crestron/Extron/AMX programmer) — an installer who can't validate the end-to-end automation hasn't finished the job, regardless of how clean the physical layer is.
- Room acoustics are engineered, not incidental to how good the room looks. Speaker coverage pattern, mounting height, and the room's reverberation time determine whether a visually complete conference room is actually intelligible on a call — and that math is decided at design time, not discovered on the first bad meeting.
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 · 107 lines · 114 tokens per session scan A c7dc6f5b20c4
audiovisual-equipment-installer is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 114 tokens to every session and 3,702 once invoked, about $0.0006 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
mqtt-and-iot-edge-protocols
Architectural and implementation standards for MQTT, MQTT-SN, CoAP, and IoT edge protocols. Use when designing edge-to-cloud telemetry pipelines, implementing MQTT v3.1.1/v5.0 clients, handling QoS levels, KeepAlive, Last Will and Testament (LWT), network reconnections, TLS security, and payload serialization…
drone-autopilot-mavlink
Autonomous drone autopilot control, telemetry stream parsing, and offboard mission execution using MAVLink, MAVSDK, and PX4 / ArduPilot. Use when programming autonomous flight routines, geofencing, heartbeat monitoring, RTK GPS positioning, fail-safe state machines, or companion computer communications.
ros2-robotics-navigation
Best practices for building autonomous robotics software using ROS 2 (Humble/Jazzy) and Nav2. Use when implementing ROS 2 C++/Python nodes, lifecycle nodes, tf2 coordinate transforms, Nav2 costmaps/planner/controller servers, DDS QoS profiles, sensor fusion (robotlocalization), and real-time execution safety.
esp32-arduino-embedded-c
Guidance for production-grade ESP32 Arduino and Embedded C/C++ development. Use when building firmware for ESP32, ESP32-S3, or ESP32-C3 microcontrollers, optimizing FreeRTOS tasks, managing SRAM/PSRAM, writing ISR-safe code, or handling dual-core concurrency and hardware peripherals.
raspberry-pi-rust-embedded
Production-grade embedded Rust guidelines for Raspberry Pi (bare-metal nostd and Linux embedded std/rppal/embedded-hal). Use when developing low-latency hardware control apps, embedded Rust drivers, Linux GPIO/SPI/I2C/UART software, real-time interrupt handlers, and memory-safe hardware abstractions.
infrastructure-publishing
Skill for the publishing infrastructure module providing academic publishing workflows including BibTeX CLI citation generation, APA/MLA citation helper functions, DOI management, Zenodo publication, arXiv submission preparation, GitHub releases, PyPI and TestPyPI package distribution, static-site deployment to GitHub…