
tesla-fleet-api
Use when integrating with Tesla's official Fleet API to read vehicle/energy device data or issue remote commands (e.g. start HVAC preconditioning, wake vehicle, charge controls). Covers onboarding (developer app registration, regions/base URLs), OAuth token flows (third-party + partner tokens, refresh rotation), required domain/public-key hosting, and using Tesla's official vehicle-command/tesla-http-proxy for signed vehicle commands.
- Installs
- 950
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/odrobnik/tesla-fleet-api-skill --skill tesla-fleet-api- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads tesla-fleet-api automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Tesla Fleet API
Control Tesla vehicles via the official Fleet API.
Scripts Overview
| Script | Purpose |
|---|---|
command.py | Vehicle commands (climate, charging, locks, etc.) |
vehicle_data.py | Read vehicle data (battery, climate, location, etc.) |
vehicles.py | List vehicles + refresh cache |
auth.py | Authentication and configuration |
tesla_oauth_local.py | OAuth helper with local callback server |
start_proxy.sh | Start the signing proxy (for vehicle commands) |
stop_proxy.sh | Stop the signing proxy |
Setup / Configuration
Setup is documented in SETUP.md:
- SETUP.md
State directory: {workspace}/tesla-fleet-api/
config.json(provider creds + non-token config)auth.json(tokens)vehicles.json(cached vehicle list)places.json(named locations)proxy/(TLS material for signing proxy)
No .env file loading — credentials in config.json or environment variables.
command.py - Vehicle Commands
Execute commands on your Tesla. Vehicle is auto-selected if you only have one.
Usage
command.py [VEHICLE] <command> [options]
VEHICLE- Vehicle name or VIN (optional if single vehicle)- Commands can be run without specifying vehicle:
command.py honk - Or with vehicle name:
command.py flash honk(vehicle "flash", command "honk")
Climate Control
Start/Stop Climate
command.py climate start
command.py climate stop
command.py flash climate start # specific vehicle
Set Temperature
command.py climate temps <driver_temp> [passenger_temp]
command.py climate temps 21 # both seats 21°C
command.py climate temps 22 20 # driver 22°C, passenger 20°C
Climate Keeper Mode
command.py climate keeper <mode>
Modes: off, keep, dog, camp
Seat Heater
command.py seat-heater --level <level> [--position <position>]
command.py seat-heater -l <level> [-p <position>]
Levels:
| Value | Name |
|---|---|
| 0 | off |
| 1 | low |
| 2 | medium |
| 3 | high |
Positions:
| Value | Names |
|---|---|
| 0 | driver, front_left, fl |
| 1 | passenger, front_right, fr |
| 2 | rear_left, rl |
| 3 | rear_left_back |
| 4 | rear_center, rc |
| 5 | rear_right, rr |
| 6 | rear_right_back |
| 7 | third_left |
| 8 | third_right |
Examples:
command.py seat-heater -l high # driver (default)
command.py seat-heater -l medium -p passenger
command.py seat-heater --level low --position rear_left
command.py seat-heater -l 2 -p 4 # medium, rear center
command.py seat-heater -l off -p driver # turn off
Seat Cooler (Ventilation)
command.py seat-cooler --level <level> [--position <position>]
command.py seat-cooler -l <level> [-p <position>]
Same levels and positions as seat heater.
Examples:
command.py seat-cooler -l medium -p driver
command.py seat-cooler -l high -p passenger
Seat Auto Climate
command.py seat-climate [--position <position>] <mode>
command.py seat-climate [-p <position>] <mode>
Modes: auto, on, off
Examples:
command.py seat-climate auto # driver auto
command.py seat-climate -p passenger auto
command.py seat-climate -p driver off # disable auto
Steering Wheel Heater
command.py steering-heater <on|off>
Examples:
command.py steering-heater on
command.py steering-heater off
Precondition Schedules
Modern API for scheduling departure preconditioning (replaces deprecated set_scheduled_departure).
Add Schedule
command.py precondition add --time <HH:MM> [--days <days>] [--id <id>] [--one-time] [--disabled]
command.py precondition add -t <HH:MM> [-d <days>] [--id <id>]
Days options:
| Value | Description |
|---|---|
all | Every day (default) |
weekdays | Monday through Friday |
weekends | Saturday and Sunday |
mon,tue,wed,... | Specific days (comma-separated) |
Day names: sun, mon, tue, wed, thu, fri, sat (or full names)
Examples:
command.py precondition add -t 08:00 # every day at 8am
command.py precondition add -t 08:00 -d weekdays # Mon-Fri
command.py precondition add -t 07:30 -d mon,wed,fri
command.py precondition add -t 09:00 --one-time # one-time only
command.py precondition add -t 08:30 --id 123 # modify existing schedule
command.py precondition add -t 08:00 --disabled # create but disabled
Remove Schedule
command.py precondition remove --id <id>
Examples:
command.py precondition remove --id 123
command.py precondition remove --id 1
Charging Control
Start/Stop Charging
command.py charge start
command.py charge stop
Set Charge Limit
command.py charge limit <percent>
Percent must be 50-100.
Examples:
command.py charge limit 80
command.py charge limit 90
command.py flash charge limit 70 # specific vehicle
Doors & Security
command.py lock # lock all doors
command.py unlock # unlock all doors
command.py honk # honk the horn
command.py flash # flash the lights
command.py wake # wake vehicle from sleep
With vehicle name:
command.py flash wake # wake vehicle named "flash"
command.py flash flash # flash lights on vehicle "flash"
vehicle_data.py - Read Vehicle Data
Fetch vehicle data with human-readable output by default.
Usage
vehicle_data.py [VEHICLE] [flags] [--json]
VEHICLE- Vehicle name or VIN (optional if single vehicle)- No flags = all data
--json= raw JSON output
Flags
| Flag | Long | Data |
|---|---|---|
-c | --charge | Battery level, charge limit, charging status |
-t | --climate | Interior/exterior temp, HVAC status |
-d | --drive | Gear, speed, power, heading |
-l | --location | GPS coordinates |
-s | --state | Locks, doors, windows, odometer, software |
-g | --gui | GUI settings (units, 24h time) |
--config-data | Vehicle config (model, color, wheels) |
Examples
# All data
vehicle_data.py
vehicle_data.py flash
# Specific data
vehicle_data.py -c # charge only
vehicle_data.py -c -t # charge + climate
vehicle_data.py flash -c -l # charge + location
# Raw JSON
vehicle_data.py --json
vehicle_data.py -c --json
Sample Output
🚗 My Tesla (online)
VIN: 5YJ... (redacted)
⚡ Charge State
────────────────────────────────────────
Battery: [███████████████░░░░░] 78%
Limit: 80%
State: Charging
Power: 11 kW (16A × 234V × 3φ)
Added: 37.2 kWh
Remaining: 10m
Range: 438 km (272 mi)
Cable: IEC
🌡️ Climate State
────────────────────────────────────────
Inside: 11.9°C
Outside: 6.0°C
Set to: 20.5°C
Climate: Off
auth.py - Authentication
Manage OAuth tokens and configuration.
Usage
auth.py <command> [options]
Commands
Login (OAuth Flow)
auth.py login
Interactive: generates auth URL, prompts for code, exchanges for tokens.
Exchange Code
auth.py exchange <code>
Exchange authorization code for tokens (non-interactive).
Refresh Tokens
auth.py refresh
Refresh access token. Note: refresh tokens rotate - the new one is saved automatically.
Register Domain
auth.py register --domain <domain>
Register your app domain with Tesla (required for signed commands).
After registration, enroll your virtual key:
https://tesla.com/_ak/<domain>
Show Config
auth.py config
Display current configuration (secrets redacted).
Set Config
auth.py config set [options]
Options:
--client-id <id>--client-secret <secret>--redirect-uri <uri>--audience <url>--base-url <url>--ca-cert <path>--domain <domain>
Examples:
# Initial setup
auth.py config set \
--client-id "abc123" \
--client-secret "secret" \
--redirect-uri "http://localhost:18080/callback"
# Configure proxy
auth.py config set \
--base-url "https://localhost:4443" \
--ca-cert "/path/to/tls-cert.pem"
tesla_fleet.py - List Vehicles
List vehicles with human-readable output.
python3 scripts/tesla_fleet.py vehicles
python3 scripts/tesla_fleet.py vehicles --json
Sample Output
🚗 Name: My Tesla
🔖 VIN: 5YJ... (redacted)
🟢 Status: Online
👤 Access: Owner
Configuration / Proxy / File layout
All setup + configuration is documented in SETUP.md.
Regional Base URLs
| Region | Audience URL |
|---|---|
| Europe | https://fleet-api.prd.eu.vn.cloud.tesla.com |
| North America | https://fleet-api.prd.na.vn.cloud.tesla.com |
| China | https://fleet-api.prd.cn.vn.cloud.tesla.cn |
OAuth token endpoint (all regions):
https://fleet-auth.prd.vn.cloud.tesla.com/oauth2/v3/token
Troubleshooting
"vehicle unavailable: vehicle is offline or asleep"
Wake the vehicle first:
command.py wake
"command not signed" / "vehicle rejected"
Ensure the signing proxy is running and configured. See SETUP.md § Proxy Setup.
Token expired
auth.py refresh
Multiple vehicles
Specify vehicle by name or VIN:
command.py flash climate start
command.py 5YJ... honk
Complete Command Reference
command.py
climate start|stop
climate temps <driver> [passenger]
climate keeper off|keep|dog|camp
seat-heater -l <level> [-p <position>]
seat-cooler -l <level> [-p <position>]
seat-climate [-p <position>] auto|on|off
steering-heater on|off
precondition add -t <HH:MM> [-d <days>] [--id <id>] [--one-time]
precondition remove --id <id>
charge start|stop
charge limit <percent>
lock
unlock
honk
flash
wake
vehicle_data.py
[VEHICLE] [-c] [-t] [-d] [-l] [-s] [-g] [--config-data] [--json]
auth.py
login
exchange <code>
refresh
register --domain <domain>
config
config set [--client-id] [--client-secret] [--redirect-uri] [--audience] [--base-url] [--ca-cert] [--domain]
FAQ
What does the tesla-fleet-api skill do?
Use when integrating with Tesla's official Fleet API to read vehicle/energy device data or issue remote commands (e.g. start HVAC preconditioning, wake vehicle, charge controls). Covers onboarding (developer app registration, regions/base URLs), OAuth token flows (third-party + partner tokens, refresh rotation), required domain/public-key hosting, and using Tesla's official vehicle-command/tesla-http-proxy for signed vehicle commands.
How do I install tesla-fleet-api?
Run npx skills add https://github.com/odrobnik/tesla-fleet-api-skill --skill tesla-fleet-api in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/tesla-fleet-api/ (personal) or .claude/skills/tesla-fleet-api/ (project).
Which AI agents can use tesla-fleet-api?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is tesla-fleet-api safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains tesla-fleet-api?
It is published by odrobnik in odrobnik/tesla-fleet-api-skill. It has 950 recorded installs.
Popular backend & apis skills
find-skills
vercel-labs/skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
entra-app-registration
microsoft/azure-skills
Guides Microsoft Entra ID app registration, OAuth 2.0 authentication, and MSAL integration. USE FOR: create app registration, register Azure AD app, configure OAuth, set up authentication, add API permissions, generate service principal, MSAL example, console app auth, Entra ID setup, Azure AD authentication. DO NOT USE FOR: Key Vault secrets (use azure-keyvault-expiration-audit), general Azure resource security guidance.
google-agents-cli-adk-code
google/agents-cli
This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management" — in a project that needs ADK (Agent Development Kit) API patterns and code examples. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, the graph Workflow API, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).
embedded-captions
heygen-com/hyperframes
Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet anchor rail is the default; embed every word only when the user explicitly wants a fully cinematic treatment. The workflow runs locally end to end, including transcription and subject matting; split multi-shot footage before applying it.
entra-agent-id
microsoft/azure-skills
Provision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token exchange (fmipath, OBO, cross-tenant) including the Microsoft Entra SDK for AgentID sidecar. USE FOR: Agent Identity Blueprint, BlueprintPrincipal, agent OAuth, fmipath token exchange, agent OBO, Workload Identity Federation for agents, polyglot agent auth, Microsoft.Identity.Web.AgentIdentities. DO NOT USE FOR: standard Entra app registration (use entra-app-registration), Microsoft Foundry agent authoring (use microsoft-foundry).
neon
neondatabase/agent-skills
Overview of Neon, a complete set of cloud backend primitives around Lakebase Postgres: Auth, Object Storage, Functions, the AI Gateway, and Realtime. Start here to choose Neon for undecided login, files, APIs, and LLM calls, set up the CLI or MCP server, and follow the branch-first workflow. Use when building an app or backend on Neon, or when "Neon" or "Lakebase Postgres" is mentioned. Child skill neon-postgres wins for an existing DATABASEURL, SQL, schema, inspect, or search. Child skill neon-auth wins for login, users, sessions, identity routing, and Managed Better Auth setup. Child skill neon-realtime wins for live queries in reactive apps and agents. Also use for object storage, S3, buckets, serverless functions, function triggers, cron, AI gateway, LLM calls, realtime, logs, Loki, Grafana, observability, postgres, database, backend, Claimable Neon, neon.new, or a no-signup database.