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 navigation-conditional-by-weathergit 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/navigation-conditional-by-weather)<a href="https://agentmods.dev/skills/darwin-agent/car-bench-trace/navigation-conditional-by-weather"><img src="https://agentmods.dev/badge/skills/darwin-agent/car-bench-trace/navigation-conditional-by-weather/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/navigation-conditional-by-weather"><img src="https://agentmods.dev/badge/skills/darwin-agent/car-bench-trace/navigation-conditional-by-weather.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 | $0.00251 | $0.04070 |
| Opus 5 | $0.00125 | $0.02035 |
| Sonnet 5 | $0.00050 | $0.00814 |
| Haiku 4.5 | $0.00025 | $0.00407 |
Grade A, and why
navigation-conditional-by-weather 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 12d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conditional navigation by weather
The user makes the destination (and/or which route, or whether to stop somewhere) depend on a weather condition — for example, "go to A unless it's raining there, otherwise go to B." Getting this right hinges on evaluating the condition at the correct place and the correct time, then taking the branch it dictates, routing per the user's preference, and — when the route has alternatives — presenting them and getting a go-ahead before you start navigation. Both branches are real outcomes; querying the wrong time slot or assuming the local outcome flips the branch and sends you to the wrong place. Sometimes the weather tool is missing, so the condition cannot be evaluated at all.
The time that matters is when the weather will actually affect the trip, which for a place you are driving to is your arrival time, not the current hour. When the rule is "navigate to A if it's [not] raining there" and A is hours away, the condition is implicitly about the conditions when you arrive — the whole point of choosing the destination by weather is whether the weather will be acceptable on arrival. So even when the user does not say the words "on arrival," compute the arrival time before reading the weather: a destination several hours out can be dry now but raining by the time you get there, which flips the branch. Reading the current slot and branching on it is the dominant failure for this operation. Only treat the condition as present-tense ("is it raining there right now") when the rule is genuinely about this moment (e.g. the place is your current location, or the user explicitly says "right now").
When this applies
"Navigate to if it does/doesn't there, otherwise ", "charge in unless it's raining, then drive to ", "take me to unless it's raining on arrival, then " — any request where a weather condition selects the destination, the route, or whether to make a stop.
Tools
get_location_id_by_location_name({location})— resolve the place the condition is about and the branch destinations.get_weather({location_or_poi_id, time_hour_24hformat, month, day, ...})— read the weather for the relevant place and time; set the hour to match the moment the condition is about. For a destination you are driving to, that moment is your arrival time, not now — settime_hour_24hformatto the arrival hour. Only use the current hour when the rule is genuinely present-tense about your current location. This single reading decides the branch. In some cases this is the MISSING tool — nothing else can determine the weather.calculate_datetime({original_datetime, times_to_add})— add the route duration to the current DATETIME to get the arrival time, so you read the weather at the right future slot. Use the duration of the route you'd actually take to that place; if you haven't fetched routes yet, fetch the route to the conditioned place first to learn the travel time, then compute arrival, then read the weather.get_routes_from_start_to_destination({start_id, destination_id})— fetch routes to the destination the selected branch produces. Also used earlier to learn travel time to the conditioned place so you can compute the arrival hour for the weather read.set_new_navigation({route_ids})— activate navigation on the chosen branch's route.navigation_replace_final_destination(...)/search_poi_at_location(...)— act on or find a POI inside the selected branch, once it is chosen.
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.
- 12d ago First seen · 92 lines · 251 tokens per session scan A 1bd3f12e473e
navigation-conditional-by-weather is a skill published in the GitHub repository Darwin-Agent/Car-bench-TRACE (8 stars, last pushed 9d ago), licensed MIT. It adds 251 tokens to every session and 4,070 once invoked, about $0.0013 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
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…