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 luckiday/vibe-hardware --skill vibe-firmwaregit clone --depth 1 https://github.com/luckiday/vibe-hardwareWrote 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/luckiday/vibe-hardware/vibe-firmware)<a href="https://agentmods.dev/skills/luckiday/vibe-hardware/vibe-firmware"><img src="https://agentmods.dev/badge/skills/luckiday/vibe-hardware/vibe-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/luckiday/vibe-hardware/vibe-firmware"><img src="https://agentmods.dev/badge/skills/luckiday/vibe-hardware/vibe-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 | $0.00334 | $0.02678 |
| Opus 5 | $0.00167 | $0.01339 |
| Sonnet 5 | $0.00067 | $0.00536 |
| Haiku 4.5 | $0.00033 | $0.00268 |
Grade A, and why
vibe-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 10d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Text → firmware (beginner + agent → a board that runs)
The method and rules below are platform-agnostic. ESP-IDF is the worked-through platform — see
references/esp-idf-structure.mdfor the modular component layout, andexamples/pager-buddy/firmware/for a building example. Fill in the equivalent commands for Arduino-CLI / PlatformIO / Zephyr.
The firmware half of a small product. You describe what the device should do and which
pins go where (from the same net map the vibe-pcb board
uses); the agent writes the drivers + app, builds them reproducibly, and you flash and
watch the serial log.
The loop
spec + pin map ─► code ─► build (pinned) ─► flash + monitor ─► (OTA when fielded)
(shared with drivers reproducible real hardware test-before-release
the PCB net map) + app container serial log
- Spec — what it does + the pin/peripheral map. Reuse the board's net map so firmware pins and the PCB agree (a swapped sensor → a one-line pin + address change).
- Code — as layered components, not one
main.c. Build a board-support layer first (the one home for pins + low-level init + a typed API), then one component per domain (display, audio, net…), then a thinmainthat wires them. Board specifics (pins, bus speeds, addresses) live in the BSP header — config-as-code that mirrors the net map. See Structure below +references/esp-idf-structure.md. - Build — reproducibly. Build inside a pinned toolchain (a Docker image at a fixed SDK version, or a locked PlatformIO/SDK pin), not whatever is on your host. Version drift between a local SDK and CI is the #1 source of "works on my machine" bugs and silent ABI/heap differences. Make the pinned build the standard; a local build is a personal convenience only.
- Flash + monitor — flash over USB and read the serial log. Bring up one peripheral at a time; confirm on the bench before adding the next.
- OTA (fielded devices) — ship updates over the air with rollback protection, and never publish to real/fleet devices without a real-hardware test first — a clean compile is not enough (a code-clean path can still exhaust RAM or crashloop only on hardware with a live peripheral). Gate the publish behind a deliberate, post-test trigger.
What ships with it
3 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.
- 10d ago First seen · 166 lines · 334 tokens per session scan A 28feff6cbda9
vibe-firmware is a skill published in the GitHub repository luckiday/vibe-hardware (5 stars, last pushed 18d ago), licensed MIT. It adds 334 tokens to every session and 2,678 once invoked, about $0.0017 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 2026-08-31.
Other skills, from other repositories
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…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.