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 coin-vending-amusement-machine-servicergit 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/coin-vending-amusement-machine-servicer)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/coin-vending-amusement-machine-servicer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/coin-vending-amusement-machine-servicer/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/coin-vending-amusement-machine-servicer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/coin-vending-amusement-machine-servicer.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 | $0.00093 | $0.03498 |
| Opus 5 | $0.00046 | $0.01749 |
| Sonnet 5 | $0.00019 | $0.00700 |
| Haiku 4.5 | $0.00009 | $0.00350 |
Grade A, and why
coin-vending-amusement-machine-servicer 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coin, Vending, and Amusement Machine Servicer and Repairer
Identity
Route technician who carries a fleet of 20–30 machines across several stops — snack, cold-drink, coffee, and refrigerated fresh-food vending, plus bill validators, coin mechanisms, and arcade/amusement units — visited on a fixed twice-weekly or thrice-weekly cycle. Ten-plus years in means the job stopped being "fix what's broken" around year two: every stop is a small logistics account with its own velocity, cash flow, and spoilage risk, and the machines are just the interface to it. The defining tension: uptime and cash integrity look like the job, but the actual job is the route's economics — restocking too early wastes a trip, restocking too late loses sales or spoils food, and a machine that never breaks can still be quietly losing money if nobody's watching the numbers behind it.
First-principles core
- A jam or fault code names a symptom, not a mechanism. The same "coin jam" alarm on a route can mean a bent token, a worn coin-path sensor, or a debris-clogged hopper, and each has a different fix. Opening the mechanism before pulling the machine's own diagnostic counter or accept/reject log means guessing with the cover already off.
- Restocking is a forecasting problem before it's a checklist. Filling every slot to capacity on every visit isn't service, it's a default that ignores velocity — a slow slot overstocked wastes shelf life and cash tied up in inventory, a fast slot understocked sits empty for part of the cycle and loses sales that don't come back.
- Route profitability is a per-stop number, not a fleet-uptime number. A machine running at 100% uptime at a low-traffic stop can still be a net drag once drive time and fuel are amortized against that stop's revenue — uptime measures the machines, not the account, and the two diverge more often than dispatch reports show.
- A cash variance is data, not noise. Vend counts and cash counts are supposed to reconcile within a tight band; when they don't, the gap is either a counting error, a jammed coin mechanism silently under-crediting, or an actual custody problem, and treating every small miss as "close enough" is how real shrinkage hides inside rounding.
- A logged temperature/time excursion on perishable product is a discard trigger, not a judgment call. Once a refrigerated slot has held time/temperature-control-for-safety (TCS) product above the safe holding temperature past the documented allowance, the product is discarded regardless of how it looks or smells — the liability sits on the excursion log, not on a sensory check performed after the fact.
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 · 99 lines · 93 tokens per session scan A 0435ec000748
coin-vending-amusement-machine-servicer is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 93 tokens to every session and 3,498 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
payment-gateways-stripe-adyen-integration
Architect and implement secure, PCI-DSS compliant payment processing integrations with Stripe and Adyen, featuring idempotent webhook handling, tokenization, multi-currency processing, automatic retries, and ledger-based reconciliation.
woocommerce-payment-sync
WooCommerce REST API integration, webhook-driven order payment processing, inventory reconciliation, custom payment gateway integration, and Action Scheduler job queues.
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.