drone-autopilot-mavlink

drone-autopilot-mavlink is a skill for Claude Code, Codex from hamzabellouch/agent-skills. It costs 69 tokens per session (1,803 once invoked), scanned A, original, MIT.

Guidance for controlling autonomous drones through MAVLink, a communication protocol used between flight controllers, onboard computers, and ground stations. It covers telemetry, mission commands, positioning, and flight safety for PX4 and ArduPilot.

In plain words
What is it for?
Use it to build autonomous flight routines, read live drone data, enforce geofences, track RTK GPS position, and connect a companion computer such as a Raspberry Pi or Jetson.
Why use it?
It helps avoid unsafe or unreliable flight-control code by providing patterns for monitoring the aircraft, handling failures, and communicating with its autopilot.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to build autonomous flight routines, read live drone data, enforce geofences, track RTK GPS position, and connect a companion computer such as a Raspberry Pi or Jetson.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hamzabellouch/agent-skills/drone-autopilot-mavlink
Install

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.

Any agent
npx skills add hamzabellouch/agent-skills --skill drone-autopilot-mavlink
Clone the repo
git clone --depth 1 https://github.com/hamzabellouch/agent-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for drone-autopilot-mavlink

README.md
[![agentmods](https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/drone-autopilot-mavlink/github.svg)](https://agentmods.dev/skills/hamzabellouch/agent-skills/drone-autopilot-mavlink)
Your own site
<a href="https://agentmods.dev/skills/hamzabellouch/agent-skills/drone-autopilot-mavlink"><img src="https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/drone-autopilot-mavlink/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.

agentmods 80×15 button for drone-autopilot-mavlink

Your own site · 80×15
<a href="https://agentmods.dev/skills/hamzabellouch/agent-skills/drone-autopilot-mavlink"><img src="https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/drone-autopilot-mavlink.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,803 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.01803
Opus 5 $0.00034 $0.00901
Sonnet 5 $0.00014 $0.00361
Haiku 4.5 $0.00007 $0.00180

Measured 8d ago against content hash ffaca7dc0ef6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

drone-autopilot-mavlink 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 8d 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.

Autonomous Systems and Robotics/drone-autopilot-mavlink/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This skill details architecture, telemetry stream decoding, offboard velocity/position control, fail-safe state machine design, and companion computer integration for autonomous Unmanned Aerial Vehicles (UAV) running PX4 or ArduPilot firmware.


MAVLink (Micro Air Vehicle Link) is a lightweight binary protocol over UDP/Serial for communicating between Flight Controllers (PX4/ArduPilot), Companion Computers (Raspberry Pi/Jetson), and Ground Control Stations (QGroundControl):

+------------------------------------+          UDP / Serial (MAVLink 2.0)          +--------------------------------------+
|        Companion Computer          | <------------------------------------------> |           Flight Controller          |
|  (MAVSDK / PyMAVLink / Offboard)   |                                              |      (PX4 / ArduPilot Autopilot)     |
+------------------------------------+                                              +--------------------------------------+
                  |                                                                                    |
            REST / gRPC                                                                           PWM / CAN Bus
                  v                                                                                    v
+------------------------------------+                                              +--------------------------------------+
|       Cloud Telemetry / Fleet      |                                              |     ESC / Motors / GPS / RTK / IMU   |
+------------------------------------+                                              +--------------------------------------+

2. Autonomous Offboard Flight Script (MAVSDK Python)

Below is a production-grade, asynchronous offboard mission script using MAVSDK Python featuring heartbeat verification, pre-arm safety checks, takeoff, velocity guidance, geofencing, and automated Return-to-Launch (RTL):

Read the full file on GitHub · 170 lines

Changes

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.

  1. 8d ago First seen · 170 lines · 69 tokens per session scan A ffaca7dc0ef6

Subscribe to this mod's changes

drone-autopilot-mavlink is a skill published in the GitHub repository hamzabellouch/agent-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 1,803 once invoked, about $0.0003 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 2026-09-03.

Related

Other skills, from other repositories

native-modules

When integrating device APIs, bridging to native SDKs, or debugging platform-specific behavior.

sawrus/agent-guides · 0 tokens

aerospace-engineering-technician

Use when a task needs the judgment of an Aerospace Engineering and Operations Technologist/Technician — verifying an installed fastener's preload against a drawing's torque callout via the T=K·D·F relationship, reducing strain-gauge data from a structural proof-load test into stress and checking it against an…

wonsukchoi/domain-experts · 169 tokens

audiovisual-equipment-installer

Use when a task needs the judgment of an audiovisual equipment installer/repairer — diagnosing an EDID or HDCP handshake failure between a source and a display, sizing a display's screen size and brightness for a room's viewing distance and ambient light, specifying an HDMI/HDBaseT/AVoIP signal run against its rated…

wonsukchoi/domain-experts · 114 tokens

auto-glass-installer-repairer

Use when a task needs the judgment of an auto-glass installer/repairer — deciding whether a chip or crack qualifies for resin repair versus full replacement, calculating a safe drive-away time for the adhesive and conditions on a job, determining whether a windshield replacement triggers ADAS camera recalibration, or…

wonsukchoi/domain-experts · 86 tokens

automotive-engineer

Use when a task needs the judgment of an Automotive Engineer — computing weight transfer and tire friction-circle limits for a braking-while-cornering maneuver to set brake-force distribution, sizing a powertrain and gear ratio against a 0-60 mph acceleration target while checking traction versus power limits, sizing…

wonsukchoi/domain-experts · 160 tokens

automotive-engineering-technician

Use when a task needs the judgment of an Automotive Engineering Technician — setting up and instrumenting test equipment (strain-gauge bridges, thermocouples, load/torque sensors) to an engineer's written test plan, selecting DAQ sample rate and an SAE J211 CFC filter class for a vehicle test channel, verifying…

wonsukchoi/domain-experts · 207 tokens