Borrowing it
Nothing to install: this file belongs to SensorsIot/Embedded-AI-Harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/SensorsIot/Embedded-AI-Harness/main/.claude/skills/sdr-receiver/SKILL.mdgit clone --depth 1 https://github.com/SensorsIot/Embedded-AI-HarnessWrote 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/sensorsiot/embedded-ai-harness/sdr-receiver)<a href="https://agentmods.dev/skills/sensorsiot/embedded-ai-harness/sdr-receiver"><img src="https://agentmods.dev/badge/skills/sensorsiot/embedded-ai-harness/sdr-receiver/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/sensorsiot/embedded-ai-harness/sdr-receiver"><img src="https://agentmods.dev/badge/skills/sensorsiot/embedded-ai-harness/sdr-receiver.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 | $0.00206 | $0.02855 |
| Opus 5.5 | $0.00082 | $0.01142 |
| Sonnet 5.5 | $0.00041 | $0.00571 |
| Haiku 4.5 | $0.00021 | $0.00285 |
Grade A, and why
sdr-receiver 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 2mo 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDR Receiver (/api/sdr/*)
The testbench Pi has one RTL2832U dongle behind the rtl_433 toolchain. Every
receive operation goes through /api/sdr/*. It is the receive-side counterpart
to the transmit-only signal-generator skill — never SSH in to run rtl_433
yourself, drive the API.
One dongle, one user. Every capture (and the whole live console) holds a
single-instance lock. While one is running, the others return
"SDR busy — a capture is already running". Stop the live console before a
one-shot, and vice-versa.
Always check status first
GET /api/sdr/status before anything:
{"ok": true, "active": false, "mode": null, "freq_hz": 0,
"hardware": {"rtl_433": true, "rtl_test": true, "device": true},
"available": true}
hardware.device: false/available: false→ the dongle isn't detected. TryPOST /api/sdr/reset(USB reset); if still absent, it's unplugged or the USB controller is wedged (see Dongle recovery).active: true→ something is already using the dongle; stop it first.
API summary
Every endpoint, with its request and response shape: FSD Appendix D.10.
Only the choice between them is this skill's: capture decodes, analyze gives
raw pulse timing when nothing decodes, power measures a level, and acquire
runs all three in sequence when you do not yet know what is on the air.
Common body fields: freq_hz (default 433.92 MHz), duration_s, gain
(number dB, or omit for AGC), sample_rate (default 250 kHz — keep low, it's a
Pi Zero 2 W), flex (an -X spec).
A dongle plugged in after boot is picked up automatically — status re-probes
while the SDR is idle, so there is no need to restart the portal. If device
stays false, the dongle really is absent or not enumerating.
Pin gain on anything you will compare. On AGC the tuner rescales from
whatever it saw recently, so the same quiet band reads tens of dB apart between
calls and a strong carrier compresses instead of standing clear. This bites
hardest on power, where the whole point is comparing numbers.
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.
- 2mo ago First seen · 227 lines · 206 tokens per session scan A e783f035ae9c
sdr-receiver is a skill published in the GitHub repository SensorsIot/Embedded-AI-Harness (273 stars, last pushed 20d ago), licensed MIT. It adds 206 tokens to every session and 2,855 once invoked, about $0.0008 per session on Opus 5.5. 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
m5stack-cap-lora-1262
Hardware reference and firmware helper for the M5Stack Cap LoRa-1262 (SKU U214) — a snap-on cap for the Cardputer Adv (K132-Adv) and CardputerZero that carries a Semtech SX1262 sub-GHz LoRa radio (868–923 MHz, +22 dBm TX, external RP-SMA antenna) and an ATGM336H-6N GNSS receiver (GPS/QZSS/BeiDou/Galileo/GLONASS, UART…
new-device-skill
Build or update an M5Stack hardware skill in this marketplace — a Controller (a board that runs firmware, like Core2 or AtomS3), a Unit (a peripheral you drive from a Controller, like a ToF sensor or a relay), or a Chip (an Espressif SoC capability layer, like esp32-c6). Use whenever adding a new board/unit/chip to…
m5stack-tab5
Hardware reference and development helper for the M5Stack Tab5 (product code C145) — an ESP32-P4-based 5" touchscreen IoT/industrial terminal with an ESP32-C6 wireless co-processor, MIPI-DSI display, MIPI-CSI camera, ES8388 audio codec, BMI270 IMU, RX8130CE RTC, RS485, and a removable NP-F550 battery. Use this skill…
vibe-industrial-design
Take a product's OUTER APPEARANCE (industrial design: form, proportion, panel split, CMF, controls layout) from a brief + AI-generated look images to a parametric three.js appearance model, a fixed-camera contact sheet, Blender Cycles finals, and a versioned ID report (md authority + Word snapshot) — driven by an AI…
vibe-pcb
Take a small PCB from a natural-language spec to an ERC/DRC-clean, review-grade KiCad design and a fab order — written for a PCB beginner driving KiCad via Claude Code. Use when designing a NEW dev board / module-carrier PCB, SWAPPING the module or sensor on an existing carrier, or CHANGING the layout / outline / net…
vibe-cad
Take a mechanical part / enclosure from a natural-language spec to a parametric build123d model, reviewed interactively in the latest CAD Viewer and exported as STEP/STL for print or tooling — written for a beginner driving CAD via Claude Code. Use when designing or revising an ENCLOSURE / bracket / carrier-shell…