Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/luckiday/vibe-hardwarenpx agentmods add skills/luckiday/vibe-hardware/vibe-plmWrote 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-plm)<a href="https://agentmods.dev/skills/luckiday/vibe-hardware/vibe-plm"><img src="https://agentmods.dev/badge/skills/luckiday/vibe-hardware/vibe-plm.svg" alt="Measured on agentmods" 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 | $0.00384 | $0.02906 |
| Opus 5 | $0.00192 | $0.01453 |
| Sonnet 5 | $0.00077 | $0.00581 |
| Haiku 4.5 | $0.00038 | $0.00291 |
Grade A, and why
vibe-plm 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vibe-PLM — the product manifest + cross-domain integration
A small embedded product is three things that must agree (see
docs/architecture.md): firmware, PCB, enclosure. Each
has its own skill and its own self-contained loop. vibe-plm is the thin layer that
holds them together — it owns the contracts between the domains, not the work
inside any one of them. It answers: what is this product, at which revision, and do
the three halves still agree?
This is not a fourth design tool. It writes no KiCad, no build123d, no firmware. It owns one manifest + three interface files and a check that they're consistent. The actual work stays in
vibe-firmware/vibe-pcb/vibe-cad.
The product is ONE manifest
The source of truth is product.yaml at the product root. It holds product
identity, the revision, the per-domain status, and — the important part — the
interface contracts. Everything cross-cutting lives here so a beginner changes one
file and knows what else must move. See examples/pager-buddy/product.yaml and
references/manifest-and-interfaces.md for the full schema.
product: pager-buddy
revision: v2026-06-19 # vYYYY-MM-DD — bump on ANY cross-domain change
firmware: { dir: firmware/, status: stub }
pcb: { dir: pcb/, status: stub }
cad: { dir: cad/, status: stub }
interfaces:
pinmap: pcb/pinmap.yaml # pcb -> firmware
board_step: pcb/board.step # pcb -> cad (generated artifact)
enclosure_constraints: cad/constraints.yaml # cad <-> pcb
The three interface contracts (the only cross-skill coupling allowed)
The repo rule is that a skill's code never calls another skill's code. So the domains are coupled only through data files — these three contracts. Each has a producer and a consumer; the producer regenerates it, the consumer reads it.
| Contract | Direction | File | What it carries | Kind |
|---|---|---|---|---|
| pinmap | pcb → firmware | pcb/pinmap.yaml |
the net map: pin ↔ signal ↔ bus/address | source (must exist) |
| board_step | pcb → cad | pcb/board.step |
the board 3D for the 0 mm³ fit-check | artifact (generated; warn until built) |
| enclosure_constraints | cad ↔ pcb | cad/constraints.yaml |
the shared fit numbers (outline, holes, stack, ports, windows) | source (must exist) |
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 · 195 lines · 384 tokens per session scan A c1c9899e2187
vibe-plm is a skill published in the GitHub repository luckiday/vibe-hardware (5 stars, last pushed 16d ago), licensed MIT. It adds 384 tokens to every session and 2,906 once invoked, about $0.0019 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.