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 Darwin-Agent/Car-bench-TRACE --skill ambient-light-colorgit 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/ambient-light-color)<a href="https://agentmods.dev/skills/darwin-agent/car-bench-trace/ambient-light-color"><img src="https://agentmods.dev/badge/skills/darwin-agent/car-bench-trace/ambient-light-color/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/darwin-agent/car-bench-trace/ambient-light-color"><img src="https://agentmods.dev/badge/skills/darwin-agent/car-bench-trace/ambient-light-color.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 | $0.00139 | $0.02684 |
| Opus 5 | $0.00069 | $0.01342 |
| Sonnet 5 | $0.00028 | $0.00537 |
| Haiku 4.5 | $0.00014 | $0.00268 |
Grade A, and why
ambient-light-color 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 10d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ambient light color
Set the interior ambient lighting to a color (and on/off state). Requests range from a single unambiguous color change, to "match the ambient lights to my car's exterior color" (the color is derived from a read, not stated), to ones where the user names no color, names a color that isn't supported, or where the control needed to set a color is missing. The same method handles all of these.
When this applies
"Set the ambient lights to ", "turn on the cabin mood lighting in ", "match the interior ambient lighting to my car's exterior color", "switch the interior lighting off", "change the ambient lighting" / "set a different mood color" (no color named), "what colors are available?", "what color is it now?". This skill is only for the soft decorative cabin lighting. A bare "adjust the lights" / "it's getting dark" names no specific light — ambient, reading lights, and exterior headlights/fog lights are different controls, so ask which the user means before assuming this one. Seat reading lights and exterior lighting are separate skills.
Tools
get_user_preferences()— read the user's preferred ambient color (the preference may be keyed to context such as time of day). This is what resolves an unnamed color.get_car_color()— read the car's exterior color. This is what resolves a "match my car color" request. The color field may come back"unknown"— genuinely unverifiable, so you cannot derive a matching color from it.get_ambient_light_status_and_color()— read whether the ambient lights are on and their current color. Use to report the current color and as harmless grounding context. A field may come back"unknown"— genuinely unverifiable, not a value you can read.set_ambient_lights({lightcolor, on})— set the ambient color and on/off state.lightcoloraccepts a fixed set of supported colors;onis the on/off state. Before relying on it to set a color, verify the color argument is actually present in the tool's schema: if it isn't, the tool can only toggle on/off and any attempt to set a color will error on a missing required argument — treat that as no color-setting capability.
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.
- 10d ago First seen · 73 lines · 139 tokens per session scan A bd6fdc052904
ambient-light-color is a skill published in the GitHub repository Darwin-Agent/Car-bench-TRACE (8 stars, last pushed 7d ago), licensed MIT. It adds 139 tokens to every session and 2,684 once invoked, about $0.0007 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
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…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.