vibe-firmware

vibe-firmware is a skill for Claude Code, Codex from luckiday/vibe-hardware. It costs 334 tokens per session (2,678 once invoked), scanned A, original, MIT.

A workflow for taking a plain-language specification for a small electronic device and producing firmware that builds and runs on its board. Firmware is the software stored on hardware; supported examples include ESP32, RP2040, STM32, and nRF boards.

In plain words
What is it for?
Use it to bring up a new board, add peripheral drivers, connect a device to a network service, build and flash firmware, monitor the device, and prepare updates.
Why use it?
It connects the device's behavior and wiring map to organized source code, repeatable builds, hardware flashing, and serial-log monitoring, reducing mismatches between software and electronics.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to bring up a new board, add peripheral drivers, connect a device to a network service, build and flash firmware, monitor the device, and prepare updates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/luckiday/vibe-hardware/vibe-firmware
Install

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.

Any agent
npx skills add luckiday/vibe-hardware --skill vibe-firmware
Clone the repo
git clone --depth 1 https://github.com/luckiday/vibe-hardware

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for vibe-firmware

README.md
[![agentmods](https://agentmods.dev/badge/skills/luckiday/vibe-hardware/vibe-firmware/github.svg)](https://agentmods.dev/skills/luckiday/vibe-hardware/vibe-firmware)
Your own site
<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.

agentmods 80×15 button for vibe-firmware

Your own site · 80×15
<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>
Per session 334 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,678 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 10d ago against content hash 28feff6cbda9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

skills/vibe-firmware/SKILL.md · 166 lines

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.md for the modular component layout, and examples/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
  1. 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).
  2. 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 thin main that 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.
  3. 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.
  4. 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.
  5. 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.

Read the full file on GitHub · 166 lines

Files

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.

Changes

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.

  1. 10d ago First seen · 166 lines · 334 tokens per session scan A 28feff6cbda9

Subscribe to this mod's changes

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.

Related

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…

google/skills · 83 tokens

jetson-diagnostic

Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.

NVIDIA/skills · 30 tokens

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…

NVIDIA/skills · 236 tokens

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…

SnailSploit/Claude-Red · 113 tokens

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…

NVIDIA/skills · 94 tokens

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.

NVIDIA/skills · 50 tokens