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-startgit 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-start)<a href="https://agentmods.dev/skills/darwin-agent/car-bench-trace/navigation-start"><img src="https://agentmods.dev/badge/skills/darwin-agent/car-bench-trace/navigation-start/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-start"><img src="https://agentmods.dev/badge/skills/darwin-agent/car-bench-trace/navigation-start.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 | $0.00340 | $0.05389 |
| Opus 5 | $0.00170 | $0.02694 |
| Sonnet 5 | $0.00068 | $0.01078 |
| Haiku 4.5 | $0.00034 | $0.00539 |
Grade A, and why
navigation-start 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 9d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start new navigation
No navigation is active and the user wants to begin one. You resolve the destination, fetch real route options from the current start, resolve which route per the user's cue, and activate it with set_new_navigation — the tool for a fresh start, which errors if a route is already running. A multi-leg trip that includes a charging stop is the same operation with more than one leg: resolve each leg's routes, then commit them all in a single set_new_navigation call, in order. The twist: the start tool may be missing, or its required route-id parameter removed, so navigation can't actually be activated.
When this applies
"Navigate to ", "take me to , start the fastest route", "set a route to but charge first / where my buffer runs out", and "restart / resume the route I stopped earlier" — when no navigation is currently active. (If a route is already active and the endpoint changes, that is navigation-change-destination. Adding/removing a stop on an active route is the other navigation skills.)
Tools
get_current_navigation_state({detailed_information})— confirm nothing is active before starting. May be the missing tool — then you cannot read or verify whether a route is running.get_location_id_by_location_name({location})— resolve a destination / named place to an id. Use only the city's main name (e.g. "Berlin", not "Berlin City Center"). It may return no match (or an error) when the place is not in the database — treat that as the clarify trigger: surface it and ask for a nearby larger city or a more specific name, don't silently substitute and don't retry the same string.get_routes_from_start_to_destination({start_id, destination_id})— fetch route options (fastest/shortest/alternatives) for each leg, from the current start (or, for an onward leg, from the charger).get_user_preferences()— read a standing route preference when the user invokes their usual route, instead of asking.set_new_navigation({route_ids})— activate navigation when none is running. Pass every leg's route id in order for a multi-leg trip. Errors while a route is already active. Its required route-id parameter may be removed, so calling it can't actually activate navigation.
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.
- 9d ago First seen · 107 lines · 340 tokens per session scan A 26eec9d01667
navigation-start is a skill published in the GitHub repository Darwin-Agent/Car-bench-TRACE (8 stars, last pushed 6d ago), licensed MIT. It adds 340 tokens to every session and 5,389 once invoked, about $0.0017 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.