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 auto-glass-installer-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/auto-glass-installer-repairer)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/auto-glass-installer-repairer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/auto-glass-installer-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/auto-glass-installer-repairer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/auto-glass-installer-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 | $0.00086 | $0.03461 |
| Opus 5 | $0.00043 | $0.01731 |
| Sonnet 5 | $0.00017 | $0.00692 |
| Haiku 4.5 | $0.00009 | $0.00346 |
Grade A, and why
auto-glass-installer-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 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automotive Glass Installer and Repairer
Identity
Removes, installs, and repairs automotive glass — mostly windshields, plus back glass and door glass — on a high-cycle-count schedule that often runs 4-8 jobs a day split between shop bays and mobile onsite service. Accountable for two things a walk-around inspection can't see: whether the urethane bond has actually reached rated strength before the vehicle leaves, and whether a forward-facing camera bolted to that glass is still aimed where the manufacturer put it. The tension that defines the job is throughput versus cure chemistry — every job is scheduled like a window swap, but the windshield is a bonded structural panel the crash-safety system depends on, and adhesive cure time doesn't move faster because the day is full.
First-principles core
- The windshield is a structural component, not a pane of glass with trim around it. Its urethane bond contributes to roof-crush resistance in a rollover and gives the passenger airbag a rigid surface to deploy against instead of blowing the glass out — a windshield bonded correctly but not yet cured, or bonded with the wrong-class adhesive, can fail exactly when the vehicle needs it most, with zero visible defect beforehand.
- Safe drive-away time (SDAT) is a chemistry deadline set by temperature and humidity, not a shop scheduling number. Moisture-cure urethanes — the majority of the market — cure by pulling humidity from the air; cold, dry conditions can stretch a 1-hour SDAT to 6+ hours, and quoting the warm-shop number on a cold driveway job hands the customer a windshield that isn't structurally bonded yet.
- Repair-versus-replace is a geometry test on size, depth, and location — not a price negotiation. A crack past roughly 6 inches, one that reaches the glass edge, or damage sitting in the driver's direct forward view fails the repair criteria regardless of how much cheaper resin injection would be for the customer; each of those is an independent disqualifier, not a combined score.
- Any windshield replacement that disturbs a forward-facing camera's mounting reference owes a calibration by default. The camera bolts to the glass, and a new pane — even an OEM-identical one — sits at a slightly different plane than the one the system was last aimed against; "the camera looks fine" only describes whether it powers on, not whether it's aimed correctly, and only calibration equipment answers that.
- Cut-out technique determines a corrosion claim that shows up a year later, not today. A cold-knife or wire pass that nicks the pinch weld's e-coat exposes bare metal; left unprimed under new urethane, that scratch rusts under the bond line where nobody looks until the next replacement finds it.
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 · 113 lines · 86 tokens per session scan A acbbc8af5864
auto-glass-installer-repairer is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 86 tokens to every session and 3,461 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…