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 agentmods add skills/darwin-agent/car-bench-trace/reading-lights-controlnpx skills add Darwin-Agent/Car-bench-TRACE --skill reading-lights-controlgit clone --depth 1 https://github.com/Darwin-Agent/Car-bench-TRACEWrote 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/darwin-agent/car-bench-trace/reading-lights-control)<a href="https://agentmods.dev/skills/darwin-agent/car-bench-trace/reading-lights-control"><img src="https://agentmods.dev/badge/skills/darwin-agent/car-bench-trace/reading-lights-control.svg" alt="Measured on agentmods" 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 | $0.00154 | $0.01502 |
| Opus 5 | $0.00077 | $0.00751 |
| Sonnet 5 | $0.00031 | $0.00300 |
| Haiku 4.5 | $0.00015 | $0.00150 |
Grade A, and why
reading-lights-control 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 6d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Turn interior reading lights on or off. The same method handles a clear single-position request, a bare under-specified request, an occupancy-driven adjustment, and the cases where a needed control or read is unavailable.
When this applies
Requests to control the cabin reading/courtesy lights at one or more seats: "turn on my reading light", "turn on the driver reading light", "switch off the rear reading lights", "turn on the reading lights" (no position), or "set the reading lights for whoever's in the car / only the occupied seats, off for the empty ones". For exterior low/high beams and fog lights use exterior-lights-control; for cabin mood/ambient lighting use ambient-light-color. This skill is only the reading lights.
Tools
- set_reading_light(position, on) — turns a reading light on/off. position is one of ALL, DRIVER, PASSENGER, DRIVER_REAR, PASSENGER_REAR, RIGHT_REAR, LEFT_REAR; on is true/false. One call per position; fire the needed positions together in one turn. The position argument may be unavailable in the schema — then you cannot target a specific light and the call errors.
- get_seats_occupancy() — reads which seats are occupied. Needed before any occupancy-based adjustment; may be unavailable.
- get_reading_lights_status() — reads current on/off state per position; use it to resolve "turn them off" when which lights are on is otherwise unknown.
Method
- Always call get_seats_occupancy first before calling set_reading_light, regardless of whether the user named specific positions or not. This confirms which seats are occupied and ensures the correct context for any reading-light adjustment.
- After reading occupancy, call set_reading_light for the requested positions — DRIVER for the driver's light, ALL only when the user actually said "all"/"every" reading light. For occupancy-based requests ("turn on the occupied seats, off the empty ones", "adjust to who's actually in the car", "don't waste energy on empty seats"), issue one set_reading_light per seat: on for each occupied seat, off for each empty seat. Map occupancy keys to positions exactly (driver→DRIVER, passenger→PASSENGER, driver_rear→DRIVER_REAR, passenger_rear→PASSENGER_REAR).
- Report what you changed in plain terms.
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.
- 6d ago First seen · 56 lines · 154 tokens per session scan A 643eca898a54
reading-lights-control is a skill published in the GitHub repository Darwin-Agent/Car-bench-TRACE (7 stars, last pushed 3d ago), licensed MIT. It adds 154 tokens to every session and 1,502 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 2026-08-31.
Other skills, from other repositories
integrated-browser
Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under src/vs/platform/browserView and src/vs/workbench/contrib/browserView.
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…