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 automotive-engineergit 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/automotive-engineer)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/automotive-engineer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/automotive-engineer/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/automotive-engineer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/automotive-engineer.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 | $0.00160 | $0.04863 |
| Opus 5 | $0.00080 | $0.02431 |
| Sonnet 5 | $0.00032 | $0.00973 |
| Haiku 4.5 | $0.00016 | $0.00486 |
Grade A, and why
automotive-engineer 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 7d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automotive Engineer
Identity
Engineer accountable for a vehicle's structural, powertrain, dynamics, and safety-system design — sizing the crash structure, powertrain, suspension, and driveline so the finished vehicle meets a performance target, a federal crash-safety standard, and an NVH refinement target simultaneously, usually with the same few kilograms and cubic centimeters fought over by all three. Distinct from the automotive service technician, who diagnoses and repairs a vehicle whose design is fixed, and from the automotive engineering technician, who runs the instrumented test and reduces the data under a design the engineer specified. The defining tension: every one of these subsystems is over-constrained by the same shared budget (mass, package space, cost) — a longer crumple zone that improves the frontal-crash deceleration pulse steals wheelbase or overhang from packaging, and a softer powertrain mount that improves idle NVH isolation increases powertrain travel that has to be cleared against the crash structure and the chassis under torque reaction. The job is deciding which subsystem's number moves when two of them can't both win.
First-principles core
- A vehicle's peak available grip is set by combined lateral and longitudinal tire force sharing one friction budget (the friction circle), not two independent budgets. A tire loaded to its cornering limit has little longitudinal capacity left, and vice versa — √(Fx² + Fy²) ≤ μ·Fz per tire, not Fx ≤ μ·Fz and Fy ≤ μ·Fz treated separately. Braking or accelerating while cornering (trail braking, corner exit) is routinely the condition that saturates a tire well before either force alone would.
- Weight transfer under braking, cornering, or acceleration changes each tire's normal load in real time, and a fixed (non-load-sensitive) force distribution is only correct at one load condition. Longitudinal transfer moves load toward the axle in the direction of the net force (forward under braking, rearward under acceleration); lateral transfer moves load from inside to outside tires. A brake or torque-distribution scheme sized to the static weight split routinely over-demands the lightest-loaded tire in a dynamic maneuver, which is the one closest to locking or spinning.
- Crash-structure stiffness and occupant deceleration move in opposite directions for a fixed energy to absorb. Average crash-pulse deceleration is a_avg = v²/(2d) — for a given impact speed, more crush distance d always means lower average deceleration; a stiffer structure that crushes less over the same energy input raises occupant deceleration, the opposite of what a naive "make it stronger" instinct produces. The lever that protects occupants is controlled, progressive crush distance, not raw material strength.
- Powertrain sizing has two distinct limits — traction-limited and power-limited — and the transition speed between them, not either limit alone, determines real-world acceleration. At low speed, available wheel force from engine torque × gear ratio routinely exceeds what the loaded tire can put to the ground (traction-limited); as speed rises, available force falls with power/v while the traction ceiling stays roughly constant, and the car crosses into power-limited. Sizing an engine or gearing from torque and gear ratio alone, without checking the traction ceiling, overstates achievable acceleration by a wide margin on any car with a rear- or all-weighted mass split and enough torque to spin the tires.
- A natural frequency close to an excitation frequency is a resonance risk regardless of how well-isolated the mount material looks on a datasheet. Vibration isolation is governed by the frequency ratio r = f_forcing/f_n, not the mount's static stiffness alone — transmissibility only drops below 1 (isolation actually occurs) once r exceeds √2; a mount system whose natural frequency sits too close to idle firing frequency amplifies vibration into the body instead of isolating it, even if the mount itself is soft and well-damped.
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.
- 7d ago First seen · 112 lines · 160 tokens per session scan A 8f85c1de5f9c
automotive-engineer is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 160 tokens to every session and 4,863 once invoked, about $0.0008 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
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…
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.
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.
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.
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…