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/sunshadenpx skills add Darwin-Agent/Car-bench-TRACE --skill sunshadegit 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/sunshade)<a href="https://agentmods.dev/skills/darwin-agent/car-bench-trace/sunshade"><img src="https://agentmods.dev/badge/skills/darwin-agent/car-bench-trace/sunshade.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 | $0.00174 | $0.02072 |
| Opus 5 | $0.00087 | $0.01036 |
| Sonnet 5 | $0.00035 | $0.00414 |
| Haiku 4.5 | $0.00017 | $0.00207 |
Grade A, and why
sunshade 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 5d 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.
Open / close / position / sync the sunshade
Open, close, set the sunshade to a position, or synchronise it to the sunroof. Requests range from a fully specified open to an unstated percentage, a "match the sunroof" sync, or a case where the control — or its position parameter — is missing. The same method handles all of these.
When this applies
- "Open the sunshade to N%" / "close the sunshade" — a fully specified move.
- "Open the sunshade for some shade" — no percentage given.
- "Match / synchronise the sunshade to the sunroof" — set the sunshade to the sunroof's current position.
- Asking for the sunshade's position.
Tools
get_user_preferences()— read the default opening percentage only when the percentage is meant to come from a standing preference.get_sunroof_and_sunshade_position()— read the current sunroof and sunshade positions; required before any "match/synchronise to the sunroof" request — the target number is only knowable from this read. A field may read"unknown"— unverifiable, not a value.get_weather(...)— read weather for the relevant place/time only when a condition or warning applies to the move.open_close_sunshade({percentage})— set the sunshade opening percentage;0is fully closed. The tool, or its position parameter, may be missing (a missing required parameter makes every call error).
Method
- Act on the sunshade, with the correct argument. Open vs. close, and the right
percentagevalue — don't close when an open was asked, and don't omit the value. - "Match/synchronise the sunshade to the sunroof" → read positions FIRST, then set the sunshade. Call
get_sunroof_and_sunshade_positiononce, take the sunroof's current position as the target, and set the sunshade to it — the sunshade is the component that moves. Don't skip the read and don't ask or guess the target; the number comes from the reading. This holds even if the user also states a number ("set the sunshade to 60% to match the sunroof") — the "match" framing makes the sunroof the source of truth, so still read and use the read value; the stated number is the user's belief, not the authority. Only a plain positioning request with no "match" framing skips the read. - Read state/weather only when the outcome depends on it, once. Read positions for a sync; read weather one time only if a condition or warning applies. Read each deciding value once.
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.
- 5d ago First seen · 73 lines · 174 tokens per session scan A 49efc80c9431
sunshade is a skill published in the GitHub repository Darwin-Agent/Car-bench-TRACE (7 stars, last pushed 2d ago), licensed MIT. It adds 174 tokens to every session and 2,072 once invoked, about $0.0009 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…