ardupilot-mcp: Command for Claude Code

.claude/commands/add-check.md

add-check is a command for Claude Code from furkanisikay/ardupilot-mcp. It costs 15 tokens per session (528 once invoked), scanned A, original, MIT.

A command for adding a new ArduPilot flight-log diagnosis check. Each check looks for a defined condition in recorded vehicle data and reports findings.

In plain words
What is it for?
Creating, registering, and optionally documenting a deterministic check for specific DataFlash messages, parameters, vehicles, or behaviours.
Why use it?
It guides developers to base thresholds and message meanings on authoritative ArduPilot or MAVLink sources, reducing unsupported or false warnings.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions AGENTS.md.

This is furkanisikay/ardupilot-mcp's own configuration. It tells Claude Code how to work on ardupilot-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ardupilot-mcp configures →

Part of the ardupilot-mcp plugin — 2 commands, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to furkanisikay/ardupilot-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/furkanisikay/ardupilot-mcp/main/.claude/commands/add-check.md
Clone the repo
git clone --depth 1 https://github.com/furkanisikay/ardupilot-mcp

Made for: Claude Code.

Or install ardupilot-mcp, the plugin that ships this one along with the rest of its 2 commands, 1 MCP server.

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 add-check

README.md
[![agentmods](https://agentmods.dev/badge/commands/furkanisikay/ardupilot-mcp/add-check/github.svg)](https://agentmods.dev/commands/furkanisikay/ardupilot-mcp/add-check)
Your own site
<a href="https://agentmods.dev/commands/furkanisikay/ardupilot-mcp/add-check"><img src="https://agentmods.dev/badge/commands/furkanisikay/ardupilot-mcp/add-check/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 add-check

Your own site · 80×15
<a href="https://agentmods.dev/commands/furkanisikay/ardupilot-mcp/add-check"><img src="https://agentmods.dev/badge/commands/furkanisikay/ardupilot-mcp/add-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 528 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 $0.00015 $0.00528
Opus 5 $0.00008 $0.00264
Sonnet 5 $0.00003 $0.00106
Haiku 4.5 $0.00002 $0.00053

Measured 10d ago against content hash 454d19a5ba57, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

add-check 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 10d 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.

.claude/commands/add-check.md · 36 lines

What it actually says

Add a new diagnostic check to this repo following the rules in AGENTS.md. The user's request: $ARGUMENTS

Do all of the following:

  1. Ground it first. Identify the DataFlash message(s)/parameter(s) involved and the exact threshold/behaviour, and find an AUTHORITATIVE source for every number/enum (ArduPilot wiki/firmware LogStructure.h/AP_Logger.h, the parameter docs, or MAVLink). Do not invent thresholds. If you have real logs in _reallogs/, inspect a few to ground the values and find positive/negative cases.

  2. Create ardupilot_mcp/checks/<name>.py with an @register_check class: id, title, category, requires (message types; or set() + guard internally), optional vehicles (e.g. {"copter","heli"}), description, and a pure deterministic run(self, log) -> list[Finding]. Put thresholds in named constants WITH a source comment. Cite the concrete numbers in each finding's explanation; numeric evidence in samples=. Be conservative to avoid false positives.

  3. Register it: add "<name>" to _CHECK_MODULES in ardupilot_mcp/checks/__init__.py, and (optionally) map it in CHECK_TOPICS in ardupilot_mcp/ardupilot_docs.py.

  4. Write tests/checks/test_<name>.py using make_flight_log / build_series (synthetic — no real .bin): the skipped/empty case, a clean no-finding case, and one case per severity it can emit.

  5. Update docs: add the check to the catalogue in README.md, add a CHANGELOG.md entry, and record any new threshold + its source in docs/SOURCES.md.

  6. Verify green: run ruff check ardupilot_mcp tests, ruff format ardupilot_mcp tests, mypy ardupilot_mcp, and pytest (including tests/test_docs_sync.py). If you have _reallogs/, confirm the new check flags the intended log and leaves clean flights clean.

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. 10d ago First seen · 36 lines · 15 tokens per session scan A 454d19a5ba57

Subscribe to this mod's changes

add-check is a command published in the GitHub repository furkanisikay/ardupilot-mcp (4 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 528 once invoked, about $0.0001 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 2026-08-31.