What is scaffold-hw-project?

A starter structure for hardware-as-code projects, where geometry and requirements are represented in files and checked by executable simulations or audits. It includes design records, material data, build-source files, visualisation, trade-off, FEA, and CAD-import tooling.

Use it when starting a hardware, CAD, simulation, or digital-twin project that needs traceable design data, automated audits, visualisation, trade-off studies, or finite-element analysis.

It provides a repeatable project foundation for checking physical designs instead of leaving requirements and geometry only in informal documents.

scaffold-hw-project — Skill for Claude Code by JMMonte

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add JMMonte/agentic-digital-twin

Claude Code

/plugin install agentic-digital-twin

Made for: Claude Code.

Or install agentic-digital-twin, the plugin that ships this one along with the rest of its 8 skills, 1 agent.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jmmonte/agentic-digital-twin/scaffold-hw-project/github.svg)](https://agentmods.dev/skills/jmmonte/agentic-digital-twin/scaffold-hw-project)

Your own site

<a href="https://agentmods.dev/skills/jmmonte/agentic-digital-twin/scaffold-hw-project"><img src="https://agentmods.dev/badge/skills/jmmonte/agentic-digital-twin/scaffold-hw-project/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jmmonte/agentic-digital-twin/scaffold-hw-project"><img src="https://agentmods.dev/badge/skills/jmmonte/agentic-digital-twin/scaffold-hw-project.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,689 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.

Model	Per session	Once invoked
Fable 5.1	$0.00127	$0.01689
Opus 5	$0.00063	$0.00844
Sonnet 5	$0.00025	$0.00338
Haiku 4.5	$0.00013	$0.00169

Measured 12d ago against content hash 3e10de360239, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

scaffold-hw-project 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 12d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (templates/audit.py, templates/fea_continuum.py, templates/import_cad.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/scaffold-hw-project/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scaffold a hardware-as-code project

This skill stands up the full methodology skeleton in a new (or existing) project directory. Everything it writes is a runnable, opinionated starting point drawn from a working monorepo — not vague prose. The user fills in the geometry; the harness and the conventions are already correct.

What you produce

<project>/
├── AGENTS.md              # repository map + workflow + guardrails (CLAUDE.md symlinks to it)
├── GUARDRAILS.md          # the living gotcha checklist (project-local copy)
├── design/
│   ├── design.json        # SINGLE SOURCE OF TRUTH (anchors [PUB] + derived)
│   ├── materials.json     # cited material-property source of truth (NEVER hallucinate)
│   └── Design.cs          # build-source MIRROR stub (or Design.py — match the kernel)
├── audit.py               # scored audit harness (PASS/WARN/FAIL, exit 1 on FAIL)
├── viz.py                 # rerun visualization harness
├── tradeoff.py            # placement-level scored tradeoff study + sensitivity
├── fea_continuum.py       # tier-3 continuum FEA (gmsh + CalculiX), validated vs the analytic tier
├── import_cad.py          # bring-your-own-CAD: import STEP/STL -> out/imported.json for the audits
├── mfg/
│   ├── judgment.json      # AGENT layer: decomposition, COTS placements, harness
│   └── packaging_solve.py # AUTOMATION layer: scores the judgment, exit 1 on FAIL
└── out/                   # build/viz/sim artifacts (gitignored; history/ for milestones)

Procedure

Confirm the target. Ask the user for the project directory name and the geometry kernel they will use (PicoGK/C#, build123d/Python, OpenSCAD, CadQuery, …). The build-source mirror is named to match (Design.cs for C#, design_mirror.py for Python). Default to the project root the user is in if they don't specify.
Copy the templates. The template files live next to this skill at ${CLAUDE_PLUGIN_ROOT}/skills/scaffold-hw-project/templates/. Copy each to its destination and rename AGENTS.md ↔ CLAUDE.md (symlink CLAUDE.md -> AGENTS.md so both AI harnesses read the same canonical file). Copy the plugin's top-level GUARDRAILS.md (${CLAUDE_PLUGIN_ROOT}/GUARDRAILS.md) into the project so its own lessons accrue beside its code.

Read the full file on GitHub · 120 lines

Files

What ships with it

11 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.

12d ago First seen · 120 lines · 127 tokens per session scan A 3e10de360239

Subscribe to this mod's changes

scaffold-hw-project is a skill published in the GitHub repository JMMonte/agentic-digital-twin (2 stars, last pushed 3mo ago), licensed MIT. It adds 127 tokens to every session and 1,689 once invoked, about $0.0006 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.

Claude Code Hardware and IoT agentic-ai ai-agents cad claude-code-plugin digital-twin

cad-construction

Use after the design concept is settled (via design-first-iteration or equivalent) and the user is ready to translate it into parametric CAD geometry — component decomposition, parameter hierarchy, construction sequencing. Primary platform Fusion 360; the workflow also applies to SolidWorks, Onshape, FreeCAD…

Ed3Design/ed3design-engineering-bundles · 175 tokens

bom-validation-workflow

Use when validating a Bill of Materials (BOM) for a Maker-3D project — an embedded controller project, a speaker/audio build, a smart-home build, or any other physical build with more than 5 components. Trigger on phrases like "check the BOM", "validate the parts list", "review the parts list", "missing components"…

Ed3Design/ed3design-engineering-bundles · 181 tokens

victron-cerbo-modbus-device-onboarding

Use when a new Victron Modbus-TCP device (EV Charging Station, energy meter, inverter) is connected to the Cerbo GX LAN but does not appear in the Cerbo UI or D-Bus, despite being reachable via ping. Trigger on phrases like "EVCS not visible in Cerbo", "new Modbus device does not appear", "Cerbo does not detect…

Ed3Design/ed3design-engineering-bundles · 161 tokens

mechanical-design-principles

Guides mechanical design decisions toward elegant, manufacturable, serviceable solutions with a strong bias toward tool-less assembly, monolithic parts, and form-follows-function. Provides the design rules (the WHAT and WHY — overhang, wall thickness, snap-fit sizing, tolerances, material matching). Load when the user…

Ed3Design/ed3design-engineering-bundles · 204 tokens

hsb-ip-packetizer

Choose or explain HSB Sensor RX packetizer fields for HOLOLINKdef.svh. Do not use for full defs, validation, or runtime APB programming.

NVIDIA/skills · 40 tokens

jetson-diagnostic

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

NVIDIA/skills · 30 tokens