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 MyTeslaMate/mcp-tesla --skill drive-recommendationsgit clone --depth 1 https://github.com/MyTeslaMate/mcp-teslaWrote 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/myteslamate/mcp-tesla/drive-recommendations)<a href="https://agentmods.dev/skills/myteslamate/mcp-tesla/drive-recommendations"><img src="https://agentmods.dev/badge/skills/myteslamate/mcp-tesla/drive-recommendations/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/myteslamate/mcp-tesla/drive-recommendations"><img src="https://agentmods.dev/badge/skills/myteslamate/mcp-tesla/drive-recommendations.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 | $0.00026 | $0.01883 |
| Opus 5 | $0.00013 | $0.00941 |
| Sonnet 5 | $0.00005 | $0.00377 |
| Haiku 4.5 | $0.00003 | $0.00188 |
Grade A, and why
drive-recommendations 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drive Recommendations
When to use
Activate this skill when the user asks anything along the lines of:
- "Any advice on how I drive?"
- "How can I get more range?"
- "Give me recommendations on my drives."
- "What should I change in my driving habits?"
- "Tell me one thing to improve in how I drive."
If the user wants a full breakdown (median Wh/km, outliers list, baseline
analysis) instead of focused advice, prefer the drive-efficiency-coach
skill.
Prerequisites
You need a TeslaMate car_id. If unknown:
- Call
teslamate_get_carsto list available cars. - If exactly one is returned, use it silently.
- If multiple, ask the user which one before continuing.
Workflow
1. Pull the dataset (current + previous period)
Call teslamate_get_car_drives twice:
- Current period — default: 30 days ago → now (RFC3339). If the user specifies a different period, use that instead.
- Previous period — same duration, immediately preceding the current window. For a 30-day current window, that means days -60 → -30.
Both calls use:
car_id: target carmin_distance: 5 (filters out parking-lot moves where Wh/km is meaningless)fetch_all:Truewhenever the window is longer than ~1 month — the TeslaMate API pages at 100 entries.
Always pass both start_date and end_date. Skip the previous-period
call only if the user explicitly says "just this month" / "no comparison".
2. Compute per-drive signals
For each drive:
- Distance in km (convert from miles if TeslaMate is configured that way).
- Energy used, from whichever field is present (
consumption_kwh, range delta × nominal Wh/km, or SoC delta × usable pack capacity). wh_per_km = energy_used_wh / distance_kmavg_speed_kmh = distance_km / (duration_min / 60)- Speed band: city (< 50 km/h), mixed (50–90), highway (> 90).
- Trip length: short (< 15 km), medium (15–60), long (> 60).
- Outside temperature if exposed.
- Skip drives where
distance_km < 5orenergy_used_wh <= 0.
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 · 173 lines · 26 tokens per session scan A aeb5e1da4cfa
drive-recommendations is a skill published in the GitHub repository MyTeslaMate/mcp-tesla (3 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 1,883 once invoked, about $0.0001 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…