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.
npx skills add wedsamuel1230/arduino-skills --skill board-selectiongit clone --depth 1 https://github.com/wedsamuel1230/arduino-skillsWrote 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/skills/wedsamuel1230/arduino-skills/board-selection)<a href="https://agentmods.dev/skills/wedsamuel1230/arduino-skills/board-selection"><img src="https://agentmods.dev/badge/skills/wedsamuel1230/arduino-skills/board-selection/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/skills/wedsamuel1230/arduino-skills/board-selection"><img src="https://agentmods.dev/badge/skills/wedsamuel1230/arduino-skills/board-selection.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 | $0.00063 | $0.00791 |
| Opus 5 | $0.00032 | $0.00396 |
| Sonnet 5 | $0.00013 | $0.00158 |
| Haiku 4.5 | $0.00006 | $0.00079 |
Grade A, and why
board-selection 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 12d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Board Selection
Choose a concrete board target from requirements rather than a marketing family name. This skill produces a decision record that downstream skills can consume.
Boundary With Board Support
Use board-support when the user has named a board and needs its exact profile,
capabilities, pin hazards, source status, or framework compatibility. Use this
skill when the user is choosing, replacing, or comparing boards against project
requirements. Consume the board-support profile instead of repeating or
guessing its facts.
Intake
Capture required voltage and rails, inputs/outputs, PWM/ADC/timers, buses and protocols, memory/flash/PSRAM, radio/USB, timing, power source and peak load, physical constraints, production quantity, toolchain, library constraints, security/update needs, and recovery access.
Read ../../references/boards/README.md and use ../board-support/SKILL.md for
the relevant exact profile. If the board is not covered, use the vendor product
page, MCU/module datasheet, board schematic, and selected framework variant
source. Label inferred values.
Process
- Turn requirements into hard constraints and preferences.
- Eliminate candidates that fail voltage, pin direction, peripheral, memory, power, or recovery constraints.
- Compare remaining boards across exact SKU, framework/core, toolchain, library architecture, upload path, security/update support, availability, and maintenance horizon.
- Record the selected board, rejected alternatives, reasons, open risks, and the exact build identifier/FQBN/environment.
- Hand the board profile to
pin-assignment,wiring-safety-check,library-selection,memory-budgeting, andhardware-tddas applicable.
Output
Return a compact table with requirement, constraint, candidate result,
source, and verification status, followed by the decision and open risks.
Do not present a board-family fact as a board-revision guarantee.
Anti-rationalization
| Shortcut | Response |
|---|---|
| "ESP32" is precise enough. | Ask for module suffix, DevKit revision, flash/PSRAM, and USB use. |
| "The board has enough memory." | Separate nominal memory, application memory, heap/stack, filesystem, and OTA partitions. |
| "USB power will run it." | Check rail voltage, regulator headroom, startup peaks, and external loads. |
| "Any Arduino library will work." | Check architecture, framework, version, API, and dependency compatibility. |
| "It compiles, so it is the right board." | Keep electrical, hardware, system, and deployment proof open. |
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.
- 12d ago First seen · 76 lines · 63 tokens per session scan A 28831986b76c
board-selection is a skill published in the GitHub repository wedsamuel1230/arduino-skills (21 stars, last pushed 23d ago), licensed MIT. It adds 63 tokens to every session and 791 once invoked, about $0.0003 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.
Other skills, from other repositories
cardputer-buddy
Iterate on the Cardputer-Adv MicroPython app bundle (Claude Buddy, Snake, Hello) after the device is already provisioned via m5-onboard. Use when the user wants to add a new app, push a single changed .py without re-flashing, watch device serial logs, or run a one-shot REPL command. Trigger on "add an app", "push to…
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
google-cloud-filestore-autoscale
Inspects Google Cloud Filestore capacity and utilization, evaluates storage scaling rules, and performs capacity autoscaling (scale UP for low free space or scale DOWN for cost optimization). Use when monitoring Filestore instance headroom, resizing instance shares, configuring automated growth/shrink thresholds…
developer-device-platform-basics
Provides guidance and instructions on managing remote devices on Developer Device Platform (DDP). Use when reserving remote Android devices, establishing connection tunnels, checking session status, or extending/cancelling leases. Don't use for iOS or local device/hardware inquiries.
gke-ai-troubleshooting-tpu-vbar-oom
Diagnoses and prevents vbarcontrolagent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbarcontrolagent crashes, memory cgroup OOMs in serial console…
m5-onboard
End-to-end onboarding for a freshly-plugged-in M5Stack ESP32 device (Cardputer, Cardputer-Adv, Core, CoreS3, Stick) — detect on USB, flash UIFlow 2.0 firmware, and install the Claude Buddy MicroPython app bundle. Use whenever the user plugs in or wants to flash/provision/reset an M5Stack or ESP32 board, or says…