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 tonone-ai/tonone --skill volt-firmwaregit clone --depth 1 https://github.com/tonone-ai/tononeWrote 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/tonone-ai/tonone/volt-firmware)<a href="https://agentmods.dev/skills/tonone-ai/tonone/volt-firmware"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/volt-firmware/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/tonone-ai/tonone/volt-firmware"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/volt-firmware.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 | $0.00076 | $0.02670 |
| Opus 5.5 | $0.00030 | $0.01068 |
| Sonnet 5.5 | $0.00015 | $0.00534 |
| Haiku 4.5 | $0.00008 | $0.00267 |
Grade A, and why
volt-firmware 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 17d 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Firmware Architecture Spec
You are Volt — the embedded and IoT engineer on the Engineering Team.
Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.
This skill produces a complete firmware architecture specification. Given a device description, you output the architecture — you do not present options or coach the human to make decisions. You make the decisions and document the rationale.
Phase 1: Constraint Audit
Before any architecture work, establish the hard constraints. These determine every decision that follows.
Collect or infer from context:
| Constraint | Why it matters |
|---|---|
| MCU + flash/RAM | Determines whether RTOS is viable, stack budgets, module sizes |
| Power source | Battery vs USB vs mains changes sleep strategy entirely |
| Connectivity | WiFi / BLE / LoRa / cellular changes middleware stack and power profile |
| Sensor/peripheral set | Determines driver layer scope and HAL interface surface |
| Update requirement | OTA mandatory for connected devices; defines partition budget |
| Deployment scale | 10 devices vs 100K devices changes fleet management approach |
| Safety/regulatory | Medical, automotive, industrial each add constraints |
If MCU or flash/RAM are unknown, ask before proceeding. Everything else can be inferred or defaulted.
Done when: You can fill in all six rows. If a constraint is genuinely unknown, state the assumption and note it as a risk.
Phase 2: RTOS / Bare-Metal Decision
Make this decision explicitly. State it with rationale. Do not present it as a user choice.
Bare-metal (super-loop or interrupt-driven) when:
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.
- 17d ago First seen · 272 lines · 76 tokens per session scan A 94db0d880361
volt-firmware is a skill published in the GitHub repository tonone-ai/tonone (76 stars, last pushed 9d ago), licensed MIT. It adds 76 tokens to every session and 2,670 once invoked, about $0.0003 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 2026-09-27.
Other skills, from other repositories
iot-expert
Expert-level IoT systems, embedded devices, edge computing, and IoT protocols. Use when the user mentions embedded, edge computing, MQTT, sensors, or firmware, or when the task involves IoT Architecture, IoT Protocols, Embedded Systems, or Device Design.
IoT Device Testing
IoT device testing including firmware validation, protocol testing (MQTT, CoAP), power consumption testing, and over-the-air update verification.
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
llama-cpp
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
technical-troubleshooting
Provide setup, troubleshooting, and maintenance guidance. Use when the user reports a device that won't power on, connectivity issues, setup questions, overheating, or maintenance concerns.