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 ev-range-feasibilitygit 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/ev-range-feasibility)<a href="https://agentmods.dev/skills/darwin-agent/car-bench-trace/ev-range-feasibility"><img src="https://agentmods.dev/badge/skills/darwin-agent/car-bench-trace/ev-range-feasibility.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 | $0.00000 | $0.05295 |
| Opus 5 | $0.00000 | $0.02648 |
| Sonnet 5 | $0.00000 | $0.01059 |
| Haiku 4.5 | $0.00000 | $0.00530 |
Grade A, and why
ev-range-feasibility 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EV range / charging feasibility and the charging math (information only)
The user is gathering numbers about range or charging — "how far between these two charge levels?", "can I reach on what I have?", "how long would a charge here take?", "how many charging stops would this trip need?". These are read-only questions: you gather numbers and answer. You never change navigation and you never start charging. This file owns the charging computations (the SoC-range and charge-time math) that other EV skills reference. Sometimes a needed bound is unstated; sometimes an input is missing (a tool removed, or a field reading "unknown"). The same method handles all of these.
When this applies
"How far can I drive from X% down to Y%?", "what's my range between these levels?", "can I make it to without charging?", "will my current battery get me there?", "how long to charge here?", "if I always charge from <some low %>, how many stops to ?" — any read-only EV range / charging estimate, or the charging math another skill needs.
Sibling boundary. This skill is read-only: it answers range/charging questions and may find a charger, but it never edits navigation. Actually modifying the route (remove / replace / add a waypoint, change the destination, add a charging stop, start navigation) is a separate navigation operation — defer those tool calls to it. When a single turn mixes a navigation change with a charging-feasibility check (e.g. "drop this stop, and will I need to charge?"), do the feasibility part here, but the navigation change must still honor its own rules: when the edit yields a multi-stop route and the user didn't specify route selection, take the fastest per segment, explicitly tell the user you took the fastest and offer alternatives, and flag any toll. Silently applying a chosen route without surfacing that choice is the failure.
Tools
get_distance_by_soc({initial_state_of_charge, final_state_of_charge})— distance obtainable between two state-of-charge percentages; let it carry the arithmetic (e.g. derive a stop count from the per-charge range). May be the MISSING tool.get_charging_specs_and_status({})— read current remaining range / state of charge / battery capacity / plug specs. May be MISSING, or may return a field as"unknown".get_user_preferences()— read the standing charge level the user tops up to; this fixes an otherwise-unstated target/upper state of charge.get_location_id_by_location_name({location})— resolve a destination name to an id (for the "can I reach X?" variant).get_routes_from_start_to_destination({start_id, destination_id})— read the route distance to compare against range (information only). May return the distance field as"unknown".search_poi_at_location({location_id, category_poi, filters})— find a charger at the current location (e.g. one with an available plug) when the question is about charging here; generally still works and can be offered proactively.search_poi_along_the_route({route_id, category_poi, at_kilometer, filters})— find a charger along a route segment at a given kilometer (at_kilometeris required forcharging_stations); use when the user wants a stop on the way or at the point where the battery will hit a buffer level. Crucially,at_kilometeris measured from the start of that route segment, not from the current car position — see the offset note in the Method.calculate_charging_time_by_soc({charging_station_id, charging_station_plug_id, start_state_of_charge, target_state_of_charge})— charge time between two SoC levels.
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 · 103 lines · 0 tokens per session scan A df3bc3bf2e8f
ev-range-feasibility is a skill published in the GitHub repository Darwin-Agent/Car-bench-TRACE (8 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,295 tokens. 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.