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 pin-assignmentgit 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/pin-assignment)<a href="https://agentmods.dev/skills/wedsamuel1230/arduino-skills/pin-assignment"><img src="https://agentmods.dev/badge/skills/wedsamuel1230/arduino-skills/pin-assignment/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/pin-assignment"><img src="https://agentmods.dev/badge/skills/wedsamuel1230/arduino-skills/pin-assignment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00070 | $0.00844 |
| Opus 5 | $0.00035 | $0.00422 |
| Sonnet 5 | $0.00014 | $0.00169 |
| Haiku 4.5 | $0.00007 | $0.00084 |
Grade A, and why
pin-assignment 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pin Assignment
Produce a board-aware pin plan without losing the repository's declaration convention. A logical declaration ID is not automatically a physical GPIO number; keep those layers distinct.
Intake
Record the exact board/revision, MCU/module, framework/core version, toolchain,
signal names, direction, voltage, current, pull requirements, bus ownership,
boot/debug/USB/radio constraints, and whether the user wants declarations,
physical wiring, or both. Resolve the target through
../board-support/SKILL.md first; its resolution_status must be resolved
for the requested pin-advice purpose. Load the matching file under
../../references/boards/ before selecting a physical pin. If the board is a
bounded family with missing identity fields, stop and request them instead of
using a similar profile.
Process
- Classify every signal as input, output, analog, PWM, bus, interrupt, boot, debug, USB, flash, PSRAM, or radio related.
- Reserve board-specific flash, PSRAM, USB, boot-strapping, debug, and default bus pins unless the exact board documentation approves reuse.
- Reject a candidate whose direction, pull capability, voltage, current, ADC, PWM, or protocol behavior does not match the signal.
- Keep logical IDs stable and allocate them in the requested fixed order.
- If the user requests only declarations, emit only the declarations as plain text. Do not add a code fence, heading, explanation, or trailing comment.
- If a physical map is requested, provide it separately and label assumptions and source-backed constraints.
Required declaration convention
For the user's custom output mode, use raw C++ declarations in numeric order:
constexpr int btn_esc = 101;
constexpr int btn_enter = 102;
constexpr int led_status = 103;
Use the next sequential logical value for each requested signal. These values are stable logical identifiers unless the user explicitly defines them as physical GPIO numbers. Never replace this format with an enum, macro, array, namespace, explanatory wrapper, or reordered declaration list.
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 · 81 lines · 70 tokens per session scan A 0469bc7f7cc3
pin-assignment is a skill published in the GitHub repository wedsamuel1230/arduino-skills (21 stars, last pushed 22d ago), licensed MIT. It adds 70 tokens to every session and 844 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-dynamic-slices-monitoring
Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice provisioning failures, validating single-slice or multi-slice (JobSet) workload manifests, or safely patching stuck finalizers and disabling the slice controller. Don't use…
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…