agentmods.dev

creating-packages

creating-packages is a skill for Claude Code from mawildoer/atopile-agent-skill. It costs 75 tokens per session (900 once invoked), scanned A, original, MIT.

A workflow for adding reusable electronic parts, components, or subcircuits to atopile projects.

In plain words
What is it for?
Use it to search the atopile registry, reuse local or vendored packages, add dependencies, create JLCPCB-based parts, and decide whether code belongs in a shared package or a board.
Why use it?
It helps avoid rewriting an existing part and keeps shared circuit packages organized, reviewable, and connected to available component libraries.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is path: ../packages/<package-name>.

Part of the atopile-dev plugin — 8 skills shipped together

not rated 10repo +1 2mo ago A scan 75 tokens original MIT

Good fit Use it to search the atopile registry, reuse local or vendored packages, add dependencies, create JLCPCB-based parts, and decide whether code belongs in a shared package or a board.

Compare 6 skills from other repositories ↓
View source ↗ mawildoer/atopile-agent-skill
Install

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.

Clone the repo
git clone --depth 1 https://github.com/mawildoer/atopile-agent-skill
agentmods
npx agentmods add skills/mawildoer/atopile-agent-skill/creating-packages

Made for: Claude Code.

Or install atopile-dev, the plugin that ships this one along with the rest of its 8 skills.

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 creating-packages

README.md
[![agentmods](https://agentmods.dev/badge/skills/mawildoer/atopile-agent-skill/creating-packages/github.svg)](https://agentmods.dev/skills/mawildoer/atopile-agent-skill/creating-packages)
Your own site
<a href="https://agentmods.dev/skills/mawildoer/atopile-agent-skill/creating-packages"><img src="https://agentmods.dev/badge/skills/mawildoer/atopile-agent-skill/creating-packages/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 creating-packages

Your own site · 80×15
<a href="https://agentmods.dev/skills/mawildoer/atopile-agent-skill/creating-packages"><img src="https://agentmods.dev/badge/skills/mawildoer/atopile-agent-skill/creating-packages.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 900 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 $0.00075 $0.00900
Opus 5 $0.00037 $0.00450
Sonnet 5 $0.00015 $0.00180
Haiku 4.5 $0.00007 $0.00090

Measured 10d ago against content hash 74b6678e60cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

creating-packages 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/creating-packages/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Creating Packages

For atopile syntax, interfaces, and design patterns, see the ato-language skill. For build workflow and debugging, see build-and-test.

Search Before You Create

Writing a new part/driver is the last resort. Stop as soon as you find something usable.

  1. The atopile registry — use the find_packages / inspect_package MCP tools, or browse packages.atopile.io. Install with ato dependencies add <name> (e.g. atopile/usb-connectors).

  2. Packages you can vendor — other repos and your own past projects often have a driver for the same IC. Copy it into a local packages/ directory and reference it via type: file in ato.yaml. Review and adapt — vendored packages may carry application-specific assumptions.

  3. Local shared packages — check the project's own packages/ (or equivalent) for something already vendored.

  4. Create new — only if nothing above works. Use ato create part to generate the footprint/symbol + a .ato stub from a JLCPCB search, then write the driver around it.

Package Conventions

These conventions keep packages predictable and reviewable. Adapt the exact namespace to your project.

  • Naming: <vendor>-<device> (e.g. ti-bq25756, microchip-emc2101).
  • Identifier: <namespace>/<package-name> in ato.yaml's package.identifier (the namespace is your project/org slug).
  • hide_designators: true on build targets — designators are assigned at the consuming board level, not in the package.
  • Two-file pattern:
    • The driver (<package-name>.ato) contains the reusable, configurable module that consumers import.
    • A separate test.ato instantiates it in one specific configuration, connects all interfaces, and adds assertions that verify that configuration. Consumers import from the driver, never from the test.
  • Layout: <package-name>/ato.yaml, <package-name>.ato (driver — importable), test.ato (build validation + design verification), parts/ (footprint/symbol/step files).
  • Verification status: every public module's docstring should declare its lifecycle state, updated as the module progresses:
    • UNVERIFIED — design complete, builds clean, not yet fabricated or tested
    • BUILT — PCB fabricated, not yet powered or tested
    • TESTED — powered and functionally verified on hardware
    • PRODUCTION — used in a shipped/deployed product

Read the full file on GitHub · 76 lines

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 · 76 lines · 75 tokens per session scan A 74b6678e60cb

Subscribe to this mod's changes

creating-packages is a skill published in the GitHub repository mawildoer/atopile-agent-skill (10 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 900 once invoked, about $0.0004 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.

Hardware and IoT
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