platformio-mcp: Skill for Claude Code

.skills/hardware-in-the-loop-test/SKILL.md

hardware-in-the-loop-test is a skill for Claude Code, Codex from jl-codes/platformio-mcp. It costs 41 tokens per session (240 once invoked), scanned A, original, MIT.

A testing process that checks firmware on the actual physical device it controls, rather than only checking whether the code compiles. Firmware is software embedded in hardware such as a development board or sensor.

In plain words
What is it for?
Use it to build and flash firmware, watch serial output, verify boot messages, sensor data, timing, or telemetry, and save test logs. It requires approval before flashing or activating potentially dangerous hardware outputs.
Why use it?
Compilation cannot reveal problems with booting, wiring, sensor readings, timing, or real device output. This process checks the behavior that users will actually depend on.

Skill for Claude CodeCodex

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

This is jl-codes/platformio-mcp's own configuration. It tells Claude Code and Codex how to work on platformio-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 platformio-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jl-codes/platformio-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/jl-codes/platformio-mcp/main/.skills/hardware-in-the-loop-test/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jl-codes/platformio-mcp

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 hardware-in-the-loop-test

README.md
[![agentmods](https://agentmods.dev/badge/skills/jl-codes/platformio-mcp/hardware-in-the-loop-test/github.svg)](https://agentmods.dev/skills/jl-codes/platformio-mcp/hardware-in-the-loop-test)
Your own site
<a href="https://agentmods.dev/skills/jl-codes/platformio-mcp/hardware-in-the-loop-test"><img src="https://agentmods.dev/badge/skills/jl-codes/platformio-mcp/hardware-in-the-loop-test/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 hardware-in-the-loop-test

Your own site · 80×15
<a href="https://agentmods.dev/skills/jl-codes/platformio-mcp/hardware-in-the-loop-test"><img src="https://agentmods.dev/badge/skills/jl-codes/platformio-mcp/hardware-in-the-loop-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 240 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00041 $0.00240
Opus 5 $0.00020 $0.00120
Sonnet 5 $0.00008 $0.00048
Haiku 4.5 $0.00004 $0.00024

Measured 9d ago against content hash 44cd219605a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

hardware-in-the-loop-test 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.

.skills/hardware-in-the-loop-test/SKILL.md · 41 lines

What it actually says

Hardware-in-the-Loop Test

Purpose

Use this skill to validate firmware behavior on a real device, not just through compilation.

Safety Rules

  • Ask before flashing.
  • Do not assume physical wiring is safe.
  • Do not activate motors, heaters, lasers, relays, pumps, or high-power outputs without explicit user approval.
  • Keep tests bounded by timeout.
  • Save logs and artifacts.

Workflow

  1. Define expected behavior.
  2. Build firmware.
  3. Ask before flashing.
  4. Flash firmware.
  5. Monitor device output.
  6. Check expected serial strings, timing, or telemetry.
  7. Mark pass/fail.
  8. Save build logs, flash logs, and serial logs.
  9. Summarize results.

Example Test Definition

name: esp32_boot_marker
board: esp32dev
expected:
  serial_contains: BOOT_OK
  timeout_seconds: 15
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 · 41 lines · 41 tokens per session scan A 44cd219605a5

Subscribe to this mod's changes

hardware-in-the-loop-test is a skill published in the GitHub repository jl-codes/platformio-mcp (50 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 240 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 2026-08-30.