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/mawildoer/atopile-agent-skillnpx agentmods add skills/mawildoer/atopile-agent-skill/board-designWrote 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/mawildoer/atopile-agent-skill/board-design)<a href="https://agentmods.dev/skills/mawildoer/atopile-agent-skill/board-design"><img src="https://agentmods.dev/badge/skills/mawildoer/atopile-agent-skill/board-design/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/mawildoer/atopile-agent-skill/board-design"><img src="https://agentmods.dev/badge/skills/mawildoer/atopile-agent-skill/board-design.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 | $0.00043 | $0.01390 |
| Opus 5 | $0.00022 | $0.00695 |
| Sonnet 5 | $0.00009 | $0.00278 |
| Haiku 4.5 | $0.00004 | $0.00139 |
Grade A, and why
board-design 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 11d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Board Design
For atopile syntax and patterns, see the ato-language skill. For build workflow, see build-and-test. For creating new shared packages, see creating-packages.
A board is a composition: you instantiate packages (MCU, regulators, connectors, application ICs) and wire them together at the board level. The board module's body should read like a block diagram — major blocks first, then the connections between them.
File Structure
<board-name>/
<board-name>.ato # Main board module
ato.yaml # Build manifest
layouts/ # KiCad layout files (created by ato build)
parts/ # Board-specific parts (from ato create part)
ato.yaml template
requires-atopile: ^0.15.7
paths:
src: ./
layout: ./layouts
builds:
<board-name>:
entry: <board-name>.ato:<BoardModule>
hide_designators: true
dependencies:
# Local packages:
- type: file
identifier: <namespace>/<package-name>
path: ../packages/<package-name>
# Registry packages:
- type: registry
identifier: atopile/<package-name>
release: <version>
Board module template
#pragma experiment("BRIDGE_CONNECT")
#pragma experiment("TRAITS")
import Resistor
import Capacitor
from "<namespace>/<mcu-package>/<mcu-package>.ato" import MyMCU
from "atopile/usb-connectors/usb-connectors.ato" import USBCConn
module MyBoard:
"""One-line description of what this board does."""
# --- Major blocks ---
mcu = new MyMCU
usb = new USBCConn
# --- Power ---
# power_in ~> regulator ~> power_3v3
# power_3v3 ~ mcu.power
# --- Communication / control ---
# usb.usb2 ~ mcu.usb
# app_ic.i2c ~ mcu.i2c[0]
# --- Ground domains tied together ---
# power_hv.lv ~ power_3v3.lv
Composition Methodology
- Instantiate the major blocks first — MCU, power source/regulators, connectors, application ICs. Give them clear names.
- Establish power rails — identify each voltage rail, route the input source through regulators to each rail (
power_in ~> regulator ~> power_3v3), and connect every block's power interface to the right rail. - Wire the standard MCU peripherals consistently — pick the same peripheral assignment convention across boards (e.g. always
mcu.i2c[0]for the primary on-board I2C bus, a fixed UART for debug). Document which MCU pins each peripheral consumes so you don't double-assign a pin that's already used by a peripheral. - Connect application buses — wire each application IC's communication interface to an MCU peripheral (
app_ic.i2c ~ mcu.i2c[0],app_ic.spi ~ mcu.spi[0]). For single control lines use a GPIO: connect.linefor the signal and set.referenceto the rail that defines its logic level. - Use bridge syntax for inline series elements —
~>for things like current-sense modules in a power path (requiresBRIDGE_CONNECT). - Tie ground domains together explicitly at the board level — don't rely on implicit shared ground.
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.
- 11d ago First seen · 128 lines · 43 tokens per session scan A bb1b0276130f
board-design is a skill published in the GitHub repository mawildoer/atopile-agent-skill (10 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 1,390 once invoked, about $0.0002 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.