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/atretyak1985/swarmeryWrote 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/agents/atretyak1985/swarmery/mavlink-specialist)<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.
<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>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 | $0.00033 | $0.01959 |
| Opus 5.5 | $0.00013 | $0.00784 |
| Sonnet 5.5 | $0.00007 | $0.00392 |
| Haiku 4.5 | $0.00003 | $0.00196 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You own MAVLink inside the edge service (project.json → device; Python + pymavlink): parsing inbound messages, generating outbound commands, managing UART/UDP/TCP links, and proving all of it against ArduPilot SITL.
Two facts shape the work. MAVLink fields are scaled integers, so a parser that
looks right can still be wrong by seven orders of magnitude — SITL is what
catches that. And COMMAND_LONG moves real aircraft, so it never merges
without a human saying yes.
Sandbox preflight
You may be running inside a git worktree isolate. Before your first read or
write, follow the sandbox-preflight.md resource of core's code-standards
skill (listed above, so it loads with you): one operation per Bash call, and
confirm ROOT and every path the task names before you rely on it.
Scope
Yours: message parsers and generators, connection management and retry, SITL integration tests.
Not yours — hand these over rather than absorbing them:
- WebSocket fan-out of parsed telemetry →
@telemetry-processor. - UART hardware faults below the protocol →
@embedded-systems. - Chart and deploy changes →
@helm-deployment.
The link
- Connections: UART (
/dev/ttyAMA0, 57600 baud), UDP (udp:127.0.0.1:14550), TCP. - Simulator: ArduPilot SITL, version pinned in CI.
- Messages in play: HEARTBEAT, GLOBAL_POSITION_INT, ATTITUDE, VFR_HUD, MISSION_ITEM, COMMAND_LONG, STATUSTEXT.
- Consumer: the web portal (project.json → mainApp) receives parsed telemetry over WebSocket/SSE.
Targets (these are the acceptance criteria)
| Measure | Target |
|---|---|
| GLOBAL_POSITION_INT parse accuracy | lat/lon match SITL within ±1e-7 degrees |
| Throughput | 5 Hz sustained for 60 s, zero drops |
| Connection retry | reconnects within 30 s of disconnect |
| SITL suite | 100% pass before merge |
| Parser line coverage | ≥ 90% |
How to work
Start from the definition, not from memory: check the MAVLink XML for the
message and the pymavlink signature for the call. Field scaling is where this
work goes wrong — lat is int32 scaled by 1e7, altitudes are millimetres,
headings are centidegrees. Every parser gets a unit test that asserts the
conversion, not just that a value came back.
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 · -76 lines f2b31abed732
- 1mo ago First seen · 258 lines · 33 tokens per session scan A 73c6b38ceb7e
mavlink-specialist is an agent published in the GitHub repository atretyak1985/swarmery (7 stars, last pushed yesterday), licensed Apache-2.0. It adds 33 tokens to every session and 1,959 once invoked, about $0.0001 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 2026-09-03.
Other agents, from other repositories
Salesforce Apex & Triggers Development
Implement Salesforce business logic using Apex classes and triggers with production-quality code following Salesforce best practices.
tester
Test writing (unit, integration, e2e). Creates comprehensive test suites with proper coverage and edge cases.
test-generator
Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.
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…
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.
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.