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 sensor-signal-filteringgit 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/sensor-signal-filtering)<a href="https://agentmods.dev/skills/wedsamuel1230/arduino-skills/sensor-signal-filtering"><img src="https://agentmods.dev/badge/skills/wedsamuel1230/arduino-skills/sensor-signal-filtering/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/sensor-signal-filtering"><img src="https://agentmods.dev/badge/skills/wedsamuel1230/arduino-skills/sensor-signal-filtering.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 | $0.00131 | $0.01105 |
| Opus 5 | $0.00066 | $0.00553 |
| Sonnet 5 | $0.00026 | $0.00221 |
| Haiku 4.5 | $0.00013 | $0.00111 |
Grade A, and why
sensor-signal-filtering 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sensor Signal Filtering
Design the signal chain from sensor output to reported value. Keep raw samples, filtered values, timing, saturation, and fault flags observable; a filter must not conceal a broken sensor or unsafe voltage.
Intake gate
Record or label unknowns before selecting a component or algorithm:
- exact board, MCU, core/framework, ADC channel, resolution, reference, input range, acquisition time, and toolchain versions
- sensor part/module, output type and drive impedance, supply, cable length, expected signal bandwidth, valid range, warm-up, and failure behavior
- sample period/jitter budget, acceptable latency, step-response requirement, threshold policy, calibration model, and available measurement tools
Resolve the board with board-support before board-specific ADC advice. For
physical or multi-session work, load embedded-project-loop first and keep its
measurement gate open.
Workflow
- Capture raw samples at a stated, repeatable rate before filtering. Separate sensor dynamics from spikes, aliasing, quantization, ADC settling, rail/ ground noise, EMI, and calibration error.
- Set the sampling rate from the signal bandwidth and latency budget. Check Nyquist and alias attenuation; do not use a software filter to recover information already aliased into the band.
- Choose one filter with an explicit window/alpha/model and calculate its startup behavior, delay, memory, CPU cost, and effect on thresholds. Common starting choices are moving-average for bounded windows, median for isolated spikes, and EMA/IIR for low-cost smoothing; model-based filters require a stated model and noise assumptions.
- Check the analog path: sensor loading, RC cutoff, ADC acquisition/settling, reference and ground, cable/noise coupling, input protection, voltage limits, decoupling, and motor/radio current return paths.
- Implement raw-plus-filtered telemetry and fault/saturation indicators. Validate deterministic vectors on the host before target compilation.
- Change one causal variable per hardware iteration. Measure the ADC pin and supply/ground with the same configuration used by the firmware.
What ships with it
6 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.
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 · 87 lines · 131 tokens per session scan A bf997e3cd2de
sensor-signal-filtering is a skill published in the GitHub repository wedsamuel1230/arduino-skills (21 stars, last pushed 23d ago), licensed MIT. It adds 131 tokens to every session and 1,105 once invoked, about $0.0007 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…