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-add-waypointgit 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-add-waypoint)<a href="https://agentmods.dev/skills/darwin-agent/car-bench-trace/navigation-add-waypoint"><img src="https://agentmods.dev/badge/skills/darwin-agent/car-bench-trace/navigation-add-waypoint/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-add-waypoint"><img src="https://agentmods.dev/badge/skills/darwin-agent/car-bench-trace/navigation-add-waypoint.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 | $0.00229 | $0.03165 |
| Opus 5 | $0.00114 | $0.01582 |
| Sonnet 5 | $0.00046 | $0.00633 |
| Haiku 4.5 | $0.00023 | $0.00316 |
Grade A, and why
navigation-add-waypoint 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add an intermediate waypoint
A multi-stop route is active and the user wants to insert a new intermediate stop, leaving the final destination unchanged. Inserting splices a stop into the chain, so it needs the two route legs that touch the new stop: the leg leading into it (from the neighbour before) and the leg leading away from it (to the neighbour after). Sometimes the user doesn't say which position; sometimes the add tool is missing or state reads back unreadable. The same method handles all of these.
When this applies
"Add a stop at after ", "put in between", "add a stop at before I reach " — while a route is already active and the endpoint stays the same. Often paired with an info-only sub-question ("am I low on battery?", "find me a charging station ~100 km ahead", "how long to charge?"). (To swap a stop for another, remove a stop, or change the endpoint, see the other navigation skills.)
This skill is only for inserting into an existing active route. If the user is planning a brand-new trip from scratch and wants the whole multi-stop route set at once, that is set_new_navigation with the full ordered leg list — do NOT set the first leg, activate, and then bolt stops on with the add tool. Only use add-waypoint when navigation is already active when the add request arrives. Read the nav state to tell which situation you are in.
Tools
get_current_navigation_state({detailed_information:true})— read the ordered waypoints, start, and routes so you know the neighbours of the new stop. May return"unknown"fields, leaving ids unreadable, or may be missing.get_location_id_by_location_name({location})— resolve a location/city name to an id. It does NOT resolve points of interest. If the new stop is a POI you already found (a charging station, restaurant, etc.), you already have its POI id from that search — use it directly and skip this call.get_routes_from_start_to_destination({start_id, destination_id})— fetch routes for each adjoining leg (neighbour-before → new stop, and new stop → neighbour-after).navigation_add_one_waypoint({waypoint_id_to_add, route_id_leading_to_new_waypoint, waypoint_id_after_new_waypoint, route_id_leading_away_from_new_waypoint, waypoint_id_before_new_waypoint})— insert the new stop. Requires route-consistent before/after ids; mismatched ids error. May be missing.get_user_preferences()— read a standing route preference when the user ties a leg's route to it.
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 · 82 lines · 229 tokens per session scan A eb215863e0f6
navigation-add-waypoint is a skill published in the GitHub repository Darwin-Agent/Car-bench-TRACE (8 stars, last pushed 8d ago), licensed MIT. It adds 229 tokens to every session and 3,165 once invoked, about $0.0011 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…