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-change-destinationgit 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-change-destination)<a href="https://agentmods.dev/skills/darwin-agent/car-bench-trace/navigation-change-destination"><img src="https://agentmods.dev/badge/skills/darwin-agent/car-bench-trace/navigation-change-destination/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-change-destination"><img src="https://agentmods.dev/badge/skills/darwin-agent/car-bench-trace/navigation-change-destination.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 | $0.00207 | $0.04647 |
| Opus 5 | $0.00103 | $0.02323 |
| Sonnet 5 | $0.00041 | $0.00929 |
| Haiku 4.5 | $0.00021 | $0.00465 |
Grade A, and why
navigation-change-destination 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 11d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Change the final navigation destination
Navigation is active and the user wants a different endpoint. The new destination may be a city name, described indirectly (a landmark, "the capital of X"), chosen from POIs in a place, or — when they want to cut a trip short — an existing earlier stop on the current route. You resolve the destination, fetch route options when a genuinely new leg is needed, and commit the change exactly once with the tool that fits the change. Sometimes the route is under-specified; sometimes an edit or follow-on tool is missing. The same method handles all of these.
When this applies
"Change my destination to …", "let's go to … instead", "navigate to …", "swap the end for ", "drop the last stop / end at instead", often bundled with a follow-on ("…and do I have enough range?") — while a route is active. (To start navigation when none is active, or to add a stop without changing the endpoint, see the other navigation skills.)
Tools
get_current_navigation_state({detailed_information:true})— read the current start so you can request routes from it. Usually still available even when edit tools are gone.get_location_id_by_location_name({location})— resolve a place name (including one you inferred from an indirect description) to a location id.get_user_preferences()— read the user's standing route preference when they invoke their usual route. This disambiguates that case — not a question.search_poi_at_location({location_id, category_poi})— when the destination is a POI, list candidates for the user to pick.get_routes_from_start_to_destination({start_id, destination_id})— fetch route options to the new endpoint. Only when you can actually commit the change — don't fetch and pretend.navigation_replace_final_destination({new_destination_id, route_id_leading_to_new_destination})— the correct tool when the endpoint becomes a genuinely new place (one new leg, one route id leading from the previous waypoint to it). May be the missing one. When present, use it. It will error if the new destination is already a waypoint on the route — that case is a delete, not a replace.navigation_delete_destination({destination_id_to_delete})— the correct tool when the user wants to end at a stop that is already an earlier waypoint (drop the current final destination so the last intermediate stop becomes the endpoint). No new route is needed; the existing leg to the prior stop is kept. Needs an active multi-stop route. May be the missing one.set_new_navigation({route_ids})— activate a fresh route; errors while navigation is active. Not a way to switch an active route. Often also removed.navigation_replace_one_waypoint,navigation_delete_waypoint,delete_current_navigation— may be stripped/erroring; not substitutes for a final-destination change.get_charging_specs_and_status({})— read battery/range; a common follow-on that may be missing even when the destination edit works.- For a charging-stop follow-on:
get_user_preferences({points_of_interest:{charging_stations:true}})reads the standing rule for where to charge (the deciding factor for the search point, not a question);get_distance_by_socconverts a preferred SOC threshold to a distance;search_poi_along_the_route({route_id, category_poi:"charging_stations", at_kilometer})finds the station (at_kilometeris required for charging stations);call_phone_by_numberdials a station only when the user asks.
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.
- 11d ago First seen · 108 lines · 207 tokens per session scan A a6b4ca0fc082
navigation-change-destination is a skill published in the GitHub repository Darwin-Agent/Car-bench-TRACE (8 stars, last pushed 8d ago), licensed MIT. It adds 207 tokens to every session and 4,647 once invoked, about $0.0010 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…
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…
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…