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 trunk-doorgit 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/trunk-door)<a href="https://agentmods.dev/skills/darwin-agent/car-bench-trace/trunk-door"><img src="https://agentmods.dev/badge/skills/darwin-agent/car-bench-trace/trunk-door.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 | $0.00091 | $0.01436 |
| Opus 5 | $0.00046 | $0.00718 |
| Sonnet 5 | $0.00018 | $0.00287 |
| Haiku 4.5 | $0.00009 | $0.00144 |
Grade A, and why
trunk-door 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open / close the trunk door
Open or close the trunk door, or report its position. Requests range from a plain "close the trunk" to a confirmation-gated open, an open accompanied by a weather heads-up, or a case where the trunk control is missing. The same method handles all of these.
When this applies
- "Open the trunk" / "close the trunk."
- "Open the trunk" when conditions (e.g. poor weather) might warrant a one-time warning.
- "Is the trunk open?" / asking for the trunk door's position.
Tools
get_trunk_door_position()— read the current trunk door position. A field may read"unknown"— unverifiable, not a value.get_weather(...)— read weather for the relevant place/time only when a condition might warrant a warning before opening.open_close_trunk_door({action})— open or close the trunk door. May be missing in this session.
Method
- Act on exactly what was asked — open vs. close. Use the correct
action; don't close when an open was requested or vice versa. - Read state/weather only when the outcome depends on it. Read the position once if the request needs it (a status question, or to confirm before acting). Read weather once only if a condition might warrant a heads-up before opening — don't read it for a routine close.
- Confirmation-gated open: ask ONCE, then execute on "yes". An exposed/safety open, or opening in poor conditions, needs one confirmation. Ask once; on the first affirmative reply, issue the actuator call. Do not execute before the "yes", and never re-ask after it.
Resolving the request (ask vs. infer)
- The action is usually explicit — don't manufacture a choice. Open and close are stated directly; there is no percentage to resolve for the trunk door. If your context already contains the action and any confirmation, act on it directly — don't re-ask or re-read.
- A weather warning is a single heads-up, evaluated ONCE — not a refusal. If conditions warrant it, read weather one time and surface one warning when you ask for confirmation. On "yes" you still act. Don't re-verify the weather in a loop and don't let the warning cancel the action.
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 · 66 lines · 91 tokens per session scan A a773929d5287
trunk-door is a skill published in the GitHub repository Darwin-Agent/Car-bench-TRACE (8 stars, last pushed 5d ago), licensed MIT. It adds 91 tokens to every session and 1,436 once invoked, about $0.0005 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.