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/furkanisikay/ardupilot-mcpWrote 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/commands/furkanisikay/ardupilot-mcp/diagnose)<a href="https://agentmods.dev/commands/furkanisikay/ardupilot-mcp/diagnose"><img src="https://agentmods.dev/badge/commands/furkanisikay/ardupilot-mcp/diagnose/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/commands/furkanisikay/ardupilot-mcp/diagnose"><img src="https://agentmods.dev/badge/commands/furkanisikay/ardupilot-mcp/diagnose.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 | $0.00018 | $0.00393 |
| Opus 5 | $0.00009 | $0.00197 |
| Sonnet 5 | $0.00004 | $0.00079 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
diagnose 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.
What it actually says
Diagnose the ArduPilot DataFlash log at: $ARGUMENTS
Use the ardupilot-mcp MCP tools and ground every claim in their output:
analyze_log(path)— run this first. It is the authoritative result: severity-ranked findings, each carrying official ArduPilot doc links, plus a summary. Everything you say should trace back to it.vehicle_profile(path)— frame, motor count, battery cells, hover throttle, power margin and thrust-to-weight. Use it to judge whether the airframe was physically capable (e.g. underpowered, marginal headroom) rather than guessing.- Drill into any finding worth the detail:
list_events(path, ...)for theERR/MODE/EV/MSGtimeline around the incident.query_timeseries(path, message_type, fields, start_s, end_s)for the raw numeric series behind a finding (e.g.VIBE,ATTDesRoll vs Roll,BATVolt).get_params(path, name_glob)/load_param_file(path)to check the configuration the vehicle actually flew.
- If asked about tuning, call
recommend_tuning(path, area)and present it as advice only — it is never applied to a vehicle.
Then explain, in plain language, what happened and why — citing the doc links the report gave you and the concrete numbers (timestamps, values, thresholds) from the tools. Do not assert anything the tools did not report. If the log is truncated, or a message a check needs wasn't logged, say so instead of guessing.
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.
- 10d ago First seen · 28 lines · 18 tokens per session scan A a0ecccc5e84e
diagnose is a command published in the GitHub repository furkanisikay/ardupilot-mcp (4 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 393 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.
Other commands, from other repositories
gpu
Diagnose GPU health, discover bounded recipes, and collect typed numeric evidence without guessing from screenshots.
debug
A command-line debugging toolkit for embedded programs using J-Link or OpenOCD, tools that connect a computer to a microcontroller for inspection.
la
A command for capturing and decoding signals with a Saleae logic analyzer, a device that records electrical digital signals over time. It supports buses such as UART, SPI, and I2C, which are common ways chips communicate with peripherals.
map
A parser for Keil compiler map files, which are build reports describing where program code and data are placed in memory. It reports object sizes, memory regions, symbols, and stack or heap details.
verify
An embedded-device verification workflow that checks a development step through building, flashing firmware, debugging with J-Link, and reading serial logs. Firmware is software that runs directly on a microcontroller or other device.
log
Analyze captured serial logs for key events.