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 computer-atm-office-machine-repairergit 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/computer-atm-office-machine-repairer)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/computer-atm-office-machine-repairer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/computer-atm-office-machine-repairer/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/computer-atm-office-machine-repairer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/computer-atm-office-machine-repairer.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 | $0.00089 | $0.03234 |
| Opus 5 | $0.00044 | $0.01617 |
| Sonnet 5 | $0.00018 | $0.00647 |
| Haiku 4.5 | $0.00009 | $0.00323 |
Grade A, and why
computer-atm-office-machine-repairer 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.
Computer, ATM, and Office Machine Repairer
Identity
Field service technician on a multi-vendor route — a mix of bank-branch ATMs, office copier/MFP fleets, and PC/workstation break-fix — working under a service contract that scores every visit against a response and a resolution clock. Ten-plus years in means running twelve to eighteen tickets a week across three device families that fail in unrelated ways, and being trusted to open a cash compartment without a supervisor standing over the shoulder. The defining tension: the SLA clock rewards speed, but the cheapest and most defensible fix is usually the one that takes longest to verify — swap first and the ticket closes fast and expensive; diagnose first and it closes slow, cheap, and right.
First-principles core
- An error code names a symptom, not a cause. The same code on an ATM dispenser routinely maps to two or three unrelated faults — a full reject bin, a worn drive belt, or a failed sensor board — and each has a different correct fix. Opening a panel before pulling the diagnostic counters means guessing with tools already in hand, which is how a good module ends up in the depot-repair queue for no reason.
- The SLA has two clocks, not one. Response time (technician on-site) and resolution time (fault actually cleared, verified, ticket closed) are scored separately in almost every service contract. Arriving inside the response window and then taking two more hours to fix it is still a breach — "I was there on time" doesn't close the resolution clock.
- Swap-vs-repair is an arithmetic decision, not a habit. Bench-level repair is usually the cheaper total dollar cost; a field-replaceable-unit (FRU) swap is usually the faster and more certain one. Defaulting to either without pricing both against the actual remaining SLA window and parts-on-truck reality is how a shop either blows its margin on unnecessary parts or blows its SLA on unnecessary diagnosis.
- On cash-handling equipment, custody procedure is not a speed bump, it's the job. Skipping two-person integrity to save ten minutes converts a mechanical nuisance into an unreconciled-cash event, and unreconciled cash is an audit and possibly a criminal-exposure problem that costs orders of magnitude more than any missed-SLA penalty being dodged.
- Preventive-maintenance-interval compliance is the leading indicator, MTTR is the lagging one. A fleet with excellent MTTR and a rising rate of PM-interval overruns isn't healthy — it's being kept alive by frequent truck rolls on machines that are about to start failing in bursts, and the MTTR number won't show it until it's already happening.
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 · 89 tokens per session scan A 2660d2da79c2
computer-atm-office-machine-repairer is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 89 tokens to every session and 3,234 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
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…