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.
git clone --depth 1 https://github.com/supervised-nl/tesla-fleet-mcpWrote 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/rules/supervised-nl/tesla-fleet-mcp/tesla-safety)<a href="https://agentmods.dev/rules/supervised-nl/tesla-fleet-mcp/tesla-safety"><img src="https://agentmods.dev/badge/rules/supervised-nl/tesla-fleet-mcp/tesla-safety/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/rules/supervised-nl/tesla-fleet-mcp/tesla-safety"><img src="https://agentmods.dev/badge/rules/supervised-nl/tesla-fleet-mcp/tesla-safety.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 | $0.00362 | $0.00362 |
| Opus 5.5 | $0.00145 | $0.00145 |
| Sonnet 5.5 | $0.00072 | $0.00072 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
tesla-safety 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 1mo 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.
What it actually says
Tesla safety
- Never print VIN, Tesla Fleet tokens, Tessie tokens, refresh tokens, client secrets, or
TESLA_MCP_TOKENin chat or logs. - Refer to the vehicle by display name or model, not VIN.
- Use the plugin MCP server
tesla. Do not add a second Tesla MCP server. - Reads:
vehicles_list,vehicle_get,vehicle_data,nearby_chargers,mobile_enabled,recent_alerts,service_data,release_notes,energy_products,energy_live_status,energy_site_info. Prefervehicle_get. Do not wake the car for status unless the user asked. - Writes need explicit confirmation first. Do not skip the question.
- Extra confirm (repeat the action, wait for a second clear yes) before:
door_unlock,remote_start_drive,erase_user_data,clear_pin_to_drive_admin,reset_pin_to_drive_pin,speed_limit_clear_pin,speed_limit_clear_pin_admin,reset_valet_pin,set_valet_mode,guest_mode,speed_limit_activate,speed_limit_deactivate,speed_limit_set_limit. - Other writes still need one confirm: climate, charge, lock, honk, flash, trunk, windows, sentry, media, navigation, software update, schedules,
wake_up. - Do not poll
vehicle_data. Tesla bills per call. - Command writes need the host
TESLA_COMMAND_BASEproxy. If the tool errors about a missing proxy, say so.
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.
- 1mo ago Changed · +2 lines · +155 tokens per session 26692f17f54e
- 1mo ago First seen · 15 lines · 207 tokens per session scan A 2ee891ee7ce6
tesla-safety is a cursor rule published in the GitHub repository supervised-nl/tesla-fleet-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 362 tokens to every session, about $0.0014 per session on Opus 5.5. 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 cursor rules, from other repositories
embedded-stm32-hal
Embedded C/C++ rules for MCU, STM32, HAL, interrupts, DMA, memory constraints, and hardware-focused testing.
linux-nvidia-cuda-python-cursorrules-prompt-file
Cursor rules for Linux development with NVIDIA CUDA and Python integration.
ros-ros2
ROS and ROS2 rules for packages, nodes, launch files, messages, services, actions, simulation, and testing.
commit-authorship
Git commits must be authored by the user only (no Cursor co-author).
archcore-files
Enforce MCP-only operations when working with .archcore/ files.
execution
Repository execution and verification commands.