mavlink-specialist

mavlink-specialist is an agent for Claude Code from atretyak1985/swarmery. It costs 33 tokens per session (3,304 once invoked), scanned A, original, Apache-2.0.

An agent for implementing MAVLink communication between drones, simulators, and a Python edge service. MAVLink is a protocol for exchanging flight data and commands; ArduPilot SITL simulates a drone for development and testing.

In plain words
What is it for?
Use it to parse and generate MAVLink messages, manage UART, UDP, and TCP connections, and test drone communication with ArduPilot SITL.
Why use it?
It helps ensure telemetry fields are converted correctly, connections recover after interruption, and messages are handled without drops.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the uav-pack plugin — 3 skills, 4 agents shipped together

Good fit Use it to parse and generate MAVLink messages, manage UART, UDP, and TCP connections, and test drone communication with ArduPilot SITL.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/atretyak1985/swarmery/mavlink-specialist
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.

Clone the repo
git clone --depth 1 https://github.com/atretyak1985/swarmery

Made for: Claude Code.

Or install uav-pack, the plugin that ships this one along with the rest of its 3 skills, 4 agents.

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 mavlink-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/atretyak1985/swarmery/mavlink-specialist/github.svg)](https://agentmods.dev/agents/atretyak1985/swarmery/mavlink-specialist)
Your own site
<a href="https://agentmods.dev/agents/atretyak1985/swarmery/mavlink-specialist"><img src="https://agentmods.dev/badge/agents/atretyak1985/swarmery/mavlink-specialist/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 mavlink-specialist

Your own site · 80×15
<a href="https://agentmods.dev/agents/atretyak1985/swarmery/mavlink-specialist"><img src="https://agentmods.dev/badge/agents/atretyak1985/swarmery/mavlink-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,304 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 $0.00033 $0.03304
Opus 5 $0.00016 $0.01652
Sonnet 5 $0.00007 $0.00661
Haiku 4.5 $0.00003 $0.00330

Measured 9d ago against content hash 73c6b38ceb7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

mavlink-specialist 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.

plugins/uav-pack/agents/mavlink-specialist.md · 258 lines

How it starts

The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

MAVLink Specialist for drone communication. Single responsibility: implement MAVLink message parsing and generation, manage UART/UDP/TCP connections, and integrate with ArduPilot SITL for testing -- all within the edge service repo (project.json → device; Python + pymavlink). Upstream: @tech-lead (Phase 4 implementation). Downstream: @telemetry-processor (receives parsed telemetry via WebSocket), @embedded-systems (hardware-layer UART). [PE/Foundational/1.4] [PE/Chaining/6.1]

Goal & success criteria [PE/Workflow/8.1]

  • Goal: Deliver correct, tested MAVLink message handling in the edge service that parses telemetry and generates commands at the target throughput with zero dropped messages under normal conditions.
  • Success criteria (falsifiable):
    • GLOBAL_POSITION_INT parse accuracy: lat/lon match SITL within +/-1e-7 degrees
    • Message throughput: 5 Hz sustained for 60s with zero drops
    • Connection retry: reconnects within 30s after disconnect
    • SITL test suite: passes 100% before merge
    • Unit test coverage for parsers: >= 90% line coverage
    • Every parser function has a unit test verifying field conversion (e.g., lat / 1e7 yields degrees)
  • Stop conditions: All SITL tests pass. Escalate to @tech-lead after 2 failed SITL test iterations.
  • Out of scope: WebSocket fan-out from parsed telemetry (delegate to @telemetry-processor), hardware-layer UART faults (delegate to @embedded-systems), Helm/deploy changes (delegate to @helm-deployment).

Inputs and outputs

Inputs (from upstream) [PE/Chaining/6.1]

  • task: string -- which MAVLink messages or commands to implement
  • plan: reference -- Phase 3 plan with step files (optional)
  • context: reference -- Phase 2 context artifact (optional)

Outputs (to downstream) [PE/Output/2.1] [PE/Output/2.3]

  • Format: Modified/created Python source files in the edge service repo (project.json → device)
  • Length budget: Completion Report <= 30 lines [PE/Output/2.4]
  • Completion Report template:
    ## Completion Report
    Status: [x] Done
    Completed by: @mavlink-specialist
    Date: {today}
    Changes made:
    - {file path}: {what was done}
    Messages affected: {HEARTBEAT, GLOBAL_POSITION_INT, etc.}
    SITL test result: pass (60s @ 5Hz, 0 drops) / fail (details)
    COMMAND_LONG included: Yes (user sign-off obtained) / No
    Issues / deviations: None / {description}
    Next step ready: Yes
    
  • Final chat message: diff summary + SITL test results

Read the full file on GitHub · 258 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. 9d ago First seen · 258 lines · 33 tokens per session scan A 73c6b38ceb7e

Subscribe to this mod's changes

mavlink-specialist is an agent published in the GitHub repository atretyak1985/swarmery (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 33 tokens to every session and 3,304 once invoked, about $0.0002 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 agents, from other repositories

backend-development-test-automator

Create comprehensive test suites including unit, integration, and E2E tests. Supports TDD/BDD workflows. Use for test creation during feature development.

wshobson/agents · 37 tokens

DiffblueCover

Expert agent for creating unit tests for java applications using Diffblue Cover.

github/awesome-copilot · 18 tokens

tester

Test writing (unit, integration, e2e). Creates comprehensive test suites with proper coverage and edge cases.

AgentWorkforce/relay · 24 tokens

nestjs-testing-expert

NestJS testing specialist that provides unit tests, integration tests, end-to-end tests, test database setup, mocking strategies, and testing best practices. Use proactively when writing tests for NestJS applications, setting up testing infrastructure, creating test fixtures, mocking dependencies, or implementing…

giuseppe-trisciuoglio/developer-kit · 65 tokens

spring-boot-unit-testing-expert

Provides expert unit testing capability with Spring Test, JUnit 5, and Mockito for Spring Boot applications. Handles comprehensive test strategies, test architecture, and testing best practices. Use proactively when writing unit tests, improving test coverage, or reviewing testing strategies.

giuseppe-trisciuoglio/developer-kit · 58 tokens

nestjs-unit-testing-expert

Expert in unit testing with NestJS, Jest, and testing utilities that provides comprehensive test strategies, test architecture, and testing best practices for TypeScript applications. Use PROACTIVELY for writing unit tests, improving test coverage, or reviewing testing strategies in NestJS applications.

giuseppe-trisciuoglio/developer-kit · 60 tokens