electronic-mcp-server: Skill for Claude Code

.github/skills/code-review-facilitator/SKILL.md

code-review-facilitator is a skill for Claude Code, Codex from wedsamuel1230/electronic-mcp-server. It costs 68 tokens per session (2,894 once invoked), scanned A, a copy of code-review-facilitator, MIT.

A code-review skill for Arduino, ESP32, and RP2040 microcontroller projects, with a static checker for common problems.

In plain words
What is it for?
It reviews individual files or whole projects, reports issues by severity, and gives checklists and concrete suggestions for improving the code.
Why use it?
It helps find memory-safety issues, structural problems, and other pitfalls before embedded code is published or finalized.

Skill for Claude CodeCodex

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

This is wedsamuel1230/electronic-mcp-server's own configuration. It tells Claude Code and Codex how to work on electronic-mcp-server 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 electronic-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to wedsamuel1230/electronic-mcp-server. 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/wedsamuel1230/electronic-mcp-server/main/.github/skills/code-review-facilitator/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/wedsamuel1230/electronic-mcp-server

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 code-review-facilitator

README.md
[![agentmods](https://agentmods.dev/badge/skills/wedsamuel1230/electronic-mcp-server/code-review-facilitator/github.svg)](https://agentmods.dev/skills/wedsamuel1230/electronic-mcp-server/code-review-facilitator)
Your own site
<a href="https://agentmods.dev/skills/wedsamuel1230/electronic-mcp-server/code-review-facilitator"><img src="https://agentmods.dev/badge/skills/wedsamuel1230/electronic-mcp-server/code-review-facilitator/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 code-review-facilitator

Your own site · 80×15
<a href="https://agentmods.dev/skills/wedsamuel1230/electronic-mcp-server/code-review-facilitator"><img src="https://agentmods.dev/badge/skills/wedsamuel1230/electronic-mcp-server/code-review-facilitator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,894 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 95% copy Near-identical to another mod 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 $0.00068 $0.02894
Opus 5 $0.00034 $0.01447
Sonnet 5 $0.00014 $0.00579
Haiku 4.5 $0.00007 $0.00289

Measured 10d ago against content hash ce2eeea5f393, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

code-review-facilitator 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/analyze_code.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

This is a copy

95% identical to code-review-facilitator — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.github/skills/code-review-facilitator/SKILL.md · 497 lines

How it starts

The opening of the file, as written. The whole thing — 497 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review Facilitator

Provides systematic code review for microcontroller projects.

Resources

This skill includes bundled tools:

  • scripts/analyze_code.py - Static analyzer detecting 15+ common Arduino issues

Quick Start

Analyze a file:

uv run scripts/analyze_code.py sketch.ino

Analyze entire project:

uv run scripts/analyze_code.py --dir /path/to/project

Interactive mode (paste code):

uv run scripts/analyze_code.py --interactive

Filter by severity:

uv run scripts/analyze_code.py sketch.ino --severity warning

When to Use

  • "Review my code"
  • "Is this code okay?"
  • "How can I improve this?"
  • Before publishing to GitHub
  • After completing a feature
  • When code "works but feels wrong"

Review Categories

1. 🏗️ Structure & Organization

Check For:

□ Single responsibility - each function does ONE thing
□ File organization - separate concerns (config, sensors, display, network)
□ Consistent naming convention (camelCase for variables, UPPER_CASE for constants)
□ Reasonable function length (< 50 lines ideally)
□ Header comments explaining purpose

Common Issues:

Issue Bad Good
God function 200-line loop() Split into readSensors(), updateDisplay(), etc.
Mixed concerns WiFi code in sensor file Separate network.cpp/h
Unclear names int x, temp1, val; int sensorReading, temperatureC;

Example Refactoring:

// ❌ Bad: Everything in loop()
void loop() {
  // 50 lines of sensor reading
  // 30 lines of display update
  // 40 lines of network code
}

// ✅ Good: Organized functions
void loop() {
  SensorData data = readAllSensors();
  updateDisplay(data);
  if (shouldTransmit()) {
    sendToServer(data);
  }
  handleSleep();
}

2. 💾 Memory Safety

Critical Checks:

□ No String class in time-critical code (use char arrays)
□ Buffer sizes declared as constants
□ Array bounds checking
□ No dynamic memory allocation in loop()
□ Static buffers for frequently used strings

Read the full file on GitHub · 497 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 497 lines · 68 tokens per session scan A ce2eeea5f393

Subscribe to this mod's changes

code-review-facilitator is a skill published in the GitHub repository wedsamuel1230/electronic-mcp-server (1 stars, last pushed 8mo ago), licensed MIT. It adds 68 tokens to every session and 2,894 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to code-review-facilitator, differing in 12 lines, and is treated as a copy.