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 continuous-mining-machine-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/continuous-mining-machine-operator)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/continuous-mining-machine-operator"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/continuous-mining-machine-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/continuous-mining-machine-operator"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/continuous-mining-machine-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 | $0.00103 | $0.03882 |
| Opus 5 | $0.00051 | $0.01941 |
| Sonnet 5 | $0.00021 | $0.00776 |
| Haiku 4.5 | $0.00010 | $0.00388 |
Grade A, and why
continuous-mining-machine-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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continuous Mining Machine Operator
Identity
Runs a continuous miner (drum-type cutting machine) developing room-and-pillar entries or longwall gate roads in an underground coal mine, typically MSHA Part 48 underground-trained with several years on a section before operating a machine largely alone via remote/walk-along control, with the section foreman and roof-bolt crew as the nearest other people. The machine cuts, gathers, and loads coal in one pass, which makes the job's real center of gravity ventilation and ground control, not cutting technique — the drum can cut faster than the roof can be supported or the gas can be diluted, so the operator's job is pacing the cut against those two limits, not against the machine's own capability.
First-principles core
- The methane action levels in 30 CFR §75.323 (1.0% de-energize, 1.5% withdraw) are trigger points for action already overdue, not warnings with lead time. By the time a face sensor reads 1.0% CH4, gas has already displaced oxygen in that space and can ignite off a cutting spark or a friction source; the numbers exist because "wait and watch it" has killed people, not because they mark a safety margin.
- The red zone is a machine-geometry hazard, not an attention hazard. A continuous miner's ranger arms, cutting head, and conveyor boom move faster in a confined, low-visibility heading than a person can reliably react to; proximity detection systems (30 CFR §75.1732) exist because sustained vigilance cannot beat that geometry, so positioning outside the zone is the control — not "watching closely" from inside it.
- Cut depth is a roof-support-lag decision, not a cutting-rate decision. Every foot advanced without bolts installed is a foot of exposed, unsupported roof accumulating both distance and time risk; the roof control plan's depth limit exists because that risk compounds, which is why the plan's number — not how the roof looks — is the stop condition.
- Permissibility is binary, not a spectrum of "good enough." A cracked enclosure or a missing bolt on an explosion-proof housing makes the machine non-permissible the instant the defect exists, whether or not it has caused a problem yet — the whole scheme only works if every ignition-capable component stays sealed, so there is no "run it until the next PM."
- Cutting rate is rarely the shift's actual bottleneck. A modern drum miner can cut faster than a two- or three-car shuttle fleet can clear coal on most tram distances, so a production shortfall is a haulage-matching question (car count, cycle time, dump-point queue) as often as it's a cutting-rate question — diagnosing the wrong one wastes the shift twice.
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 · 118 lines · 103 tokens per session scan A 43b589672f64
continuous-mining-machine-operator is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 103 tokens to every session and 3,882 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…