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-trip-plangit 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-trip-plan)<a href="https://agentmods.dev/skills/darwin-agent/car-bench-trace/ev-trip-plan"><img src="https://agentmods.dev/badge/skills/darwin-agent/car-bench-trace/ev-trip-plan/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/ev-trip-plan"><img src="https://agentmods.dev/badge/skills/darwin-agent/car-bench-trace/ev-trip-plan.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 | $0.00000 | $0.06364 |
| Opus 5 | $0.00000 | $0.03182 |
| Sonnet 5 | $0.00000 | $0.01273 |
| Haiku 4.5 | $0.00000 | $0.00636 |
Grade A, and why
ev-trip-plan 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan an EV trip and its charging needs
The user wants the route and charging side of a trip worked out — how far, how long, whether/where to charge, how long the charge takes, how many stops. You resolve the destination, read the battery, get routes for the preferred selection, and find/reason about a charger. The decisive judgement is whether the user is asking for information or for a car action. Some requests are pure info ("plan it and email the details", "how long would I need to charge", "how many stops to get there") — gather everything, change nothing. Others explicitly call for a car action ("navigate to X with a charging stop", "replace my destination", "set it up") — then set or modify navigation as asked. The same method underlies both; only the final step differs. Under-specified requests leave genuine choices (which route, which charger) that you resolve from what the user states, asking only when truly open.
When this applies
Route + charging questions for an EV trip: "plan my trip to and email the route and charging details", "find a charger near the -km mark / where I reach %", "charge nearby before I leave, then continue", "how long to charge / how many charging stops to ", "navigate to with a charging stop", "change my destination and check if I'll need to charge". The unifying feature is reasoning about range and charging for a trip. If the request is a plain navigation change with no charging/range angle (just "take me to X", "remove a stop"), the navigation mechanics live in navigation-start / the waypoint-edit skills — come here when charging or range feasibility is part of it.
Tools
planning_tool({...})— optional scaffold; a malformed dependency index returns a recoverable error, so just continue with the real lookups.get_user_preferences({preference_categories})— retrieve stored preferences. Usepoints_of_interest:{charging_stations:true}when the user defers which charger or where to charge (a stored SoC threshold or preferred provider resolves it), andnavigation_and_routing:{route_selection:true}when the route choice is left to preference.get_location_id_by_location_name({location})— resolve a destination or a named point to an id (use the city main name only). A "not found" result is real: surface it and ask for a correction; never invent an id.get_charging_specs_and_status({})— current state of charge, range, max AC/DC power, capacity. Most of the plan depends on this. It may be removed for a task, or return a field (e.g. range, capacity) as the literal"unknown"— treat that as genuinely unavailable, not zero.get_current_navigation_state({detailed_information})— read whether navigation is active and the current waypoints/routes. Read this before any navigation change to know whether to useset_new_navigation(inactive) or a waypoint-edit tool (active), and to identify which leg a charger falls on.get_routes_from_start_to_destination({start_id, destination_id})— route alternatives (distance, time, tolls, fastest/shortest aliases). Start of the overall route must be the current car location.search_poi_at_location({location_id, category_poi, filters})— chargers (or fast_food, etc.) AT a place. Use this when the user charges before leaving / at the current location / at a specific city.search_poi_along_the_route({at_kilometer, route_id, category_poi, filters})— chargers along a route;at_kilometeris REQUIRED for charging_stations. Use this when the user charges on the way / at a km mark / where a certain SoC is reached.calculate_charging_time_by_soc({charging_station_id, charging_station_plug_id, start_state_of_charge, target_state_of_charge})— charge time, computed from the current SoC at the chosen plug.calculate_charging_soc_by_time(...)— the inverse, when the user fixes a charging duration.get_distance_by_soc({initial_state_of_charge, final_state_of_charge})— distance drivable between two SoC levels; use it to find where a buffer SoC is reached and to test whether a further stop is needed.convert_route_distance_and_time({route_id, time_minutes|distance_km})— map a time on the route to a kilometre mark (e.g. to place a stop at a target arrival time) and back.- Navigation-change tools —
set_new_navigation(only when navigation is inactive), andnavigation_add_one_waypoint/navigation_replace_one_waypoint/navigation_replace_final_destination/navigation_delete_waypoint/navigation_delete_destination(only when navigation is already active). Use these only when the user calls for a car 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 · 128 lines · 0 tokens per session scan A bf7ad0b0b172
ev-trip-plan is a skill published in the GitHub repository Darwin-Agent/Car-bench-TRACE (8 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,364 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…