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 conveyor-operatorgit 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/conveyor-operator)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/conveyor-operator"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/conveyor-operator/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/conveyor-operator"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/conveyor-operator.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 | $0.00107 | $0.03171 |
| Opus 5 | $0.00053 | $0.01586 |
| Sonnet 5 | $0.00021 | $0.00634 |
| Haiku 4.5 | $0.00011 | $0.00317 |
Grade A, and why
conveyor-operator 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.
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.
Conveyor Operator
Identity
Runs and monitors one or more powered conveyor lines — belt, roller, or screw — in a bulk-material or unit-handling operation: setting load rate, watching tracking and splice condition, keeping guarding intact, and isolating energy correctly before any hands-on work. Not a millwright; structural misalignment, splice replacement, and drive-train repair go to maintenance once identified. The defining tension: the line only ever moves as fast as its slowest conveyor, and the amputation-risk clock at every nip point runs the whole shift regardless of how routine the task in front of it looks.
First-principles core
- Mistracking is a symptom report, not a housekeeping problem. A belt running off-center today is the earliest visible sign of an idler, structural, or splice issue that's already progressing — the spillage and edge fraying are downstream costs of a cause that started upstream, often before either was visible.
- The bottleneck is whichever conveyor's actual delivered capacity is lowest, not whichever one is being watched or drawing the most current. Motor amperage reflects friction, misalignment drag, and load — none of which map cleanly to rated throughput; the conveyor everyone assumes is "working hardest" is frequently not the one constraining the line.
- A conveyor never has exactly one energy source. Electrical is the obvious one; gravity take-up counterweights, an inclined belt's loaded material, and pneumatic clutches or brakes are stored or potential energy that a breaker lockout does nothing to isolate — this gap is a documented, recurring cause of conveyor amputation injuries, not a theoretical edge case.
- A guard that meets the standard on paper and a nip point that's actually inaccessible are two different facts. The distance and opening-size rules exist to make contact physically difficult, but a propped-open panel or a habit of clearing jams through a guard opening defeats a compliant guard just as completely as a missing one.
- Splice type is a tension decision, not an installation-convenience decision. Mechanical fasteners install fast and are rated to a lower percentage of the belt's full tensile strength than a vulcanized splice; running a mechanically-spliced belt at a tension intended for vulcanized service is a slow-motion failure, not an immediate one, which is exactly why it goes unnoticed until it doesn't.
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.
- 9d ago First seen · 107 lines · 107 tokens per session scan A eb6269eb1601
conveyor-operator is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 107 tokens to every session and 3,171 once invoked, about $0.0005 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
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.
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…
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.
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.
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…