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-voicegit 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-voice)<a href="https://agentmods.dev/skills/luckiday/vibe-hardware/vibe-voice"><img src="https://agentmods.dev/badge/skills/luckiday/vibe-hardware/vibe-voice/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-voice"><img src="https://agentmods.dev/badge/skills/luckiday/vibe-hardware/vibe-voice.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 | $0.00360 | $0.02114 |
| Opus 5 | $0.00180 | $0.01057 |
| Sonnet 5 | $0.00072 | $0.00423 |
| Haiku 4.5 | $0.00036 | $0.00211 |
Grade A, and why
vibe-voice 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 8d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voice-guided procedures (the agent talks; the user's hands stay on the hardware)
Text instructions fail in one specific situation: the user's hands and eyes are not on the terminal. Someone holding a probe on a test point, pressing a button on a board, watching an LED, or walking back from the printer is not reading your scrollback. The instruction was written; it was never received.
Speech fixes the channel mismatch. It is also worse than text at almost everything else — you cannot re-read it, skim it, or copy from it. So the two channels split the work, and this skill is mostly about that split.
Where this fits in vibe-hardware
The other four skills are domains (a manifest, firmware, a board, a shell). This one is a channel, and it turns on at exactly the moments the domain loops hand control back to a human:
| Moment | Skill it belongs to | Why speech |
|---|---|---|
| Flash + monitor, bring up one peripheral at a time | vibe-firmware |
hands on the USB cable and the reset button, eyes on the LED |
| Bench-verify a fabricated board — continuity, probing a test point, first power-up | vibe-pcb |
one hand per probe; nothing left for the keyboard |
| Test-fit a print, check a port lines up with its cutout, seat the board in the shell | vibe-cad |
the user is at the printer, not the terminal |
| The release checklist's real-hardware test before an OTA | vibe-plm |
a gate that is only ever passed by a human doing a physical thing |
Prose hand-off only — those skills never call this one's code, and this one never calls theirs.
When to speak
Speak only when one of these is true:
- The user's attention is away from the screen — they are handling hardware, at another machine, or across the room.
- Timing matters — the instruction has a "now" or a duration in it.
- You are blocked on them — you cannot proceed until a human acts, and they need to know you are waiting.
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.
- 8d ago First seen · 171 lines · 360 tokens per session scan A fb0f59733499
vibe-voice is a skill published in the GitHub repository luckiday/vibe-hardware (5 stars, last pushed 16d ago), licensed MIT. It adds 360 tokens to every session and 2,114 once invoked, about $0.0018 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.