zener-language

zener-language is a skill for Claude Code, Codex from diodeinc/pcb. It costs 19 tokens per session (2,105 once invoked), scanned A, original, MIT.

A set of instructions for working with Zener, a Starlark-based language for describing electronic circuits, physical parts, sourcing, layouts, and diagnostics. It explains how to inspect installed APIs and use modules and imports.

In plain words
What is it for?
Use it before reading or changing Zener files, especially when importing modules, connecting components, checking package APIs, or using the Zener command-line tools.
Why use it?
It reduces errors caused by guessing package APIs, command options, dependency paths, or circuit-module behavior. It requires checking the installed tools and documentation when exact behavior matters.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it before reading or changing Zener files, especially when importing modules, connecting components, checking package APIs, or using the Zener command-line tools.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/diodeinc/pcb/zener-language
Install

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.

Any agent
npx skills add diodeinc/pcb --skill zener-language
Clone the repo
git clone --depth 1 https://github.com/diodeinc/pcb

Made for: Claude Code, Codex.

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 zener-language

README.md
[![agentmods](https://agentmods.dev/badge/skills/diodeinc/pcb/zener-language/github.svg)](https://agentmods.dev/skills/diodeinc/pcb/zener-language)
Your own site
<a href="https://agentmods.dev/skills/diodeinc/pcb/zener-language"><img src="https://agentmods.dev/badge/skills/diodeinc/pcb/zener-language/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 zener-language

Your own site · 80×15
<a href="https://agentmods.dev/skills/diodeinc/pcb/zener-language"><img src="https://agentmods.dev/badge/skills/diodeinc/pcb/zener-language.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,105 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. Third-party audits
  • Socket pass 2 Oct 2026
  • Snyk pass 2 Oct 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00019 $0.02105
Opus 5.5 $0.00008 $0.00842
Sonnet 5.5 $0.00004 $0.00421
Haiku 4.5 $0.00002 $0.00211

Measured 14d ago against content hash c8bd07a6b20a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

zener-language 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 14d 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/zener-language/SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Zener Language

Zener is Starlark plus PCB-specific modules, typed electrical connections, physical parts, sourcing, layout, and diagnostics.

Discover Before Authoring

Use pcb list -m -json @stdlib or pcb list -m -json <package>[@<version>] to find a package's local source directory, then read its .zen files for the public API and exact behavior.

For CLI behavior, use the installed command's --help; do not invent or infer subcommands or flags. When version history matters, inspect the installed version and nearby entries in the pcb changelog instead of relying on old examples.

Modules and Components

A .zen file can be:

  • a normal Starlark module imported with load(); or
  • an instantiable schematic module imported with Module().

Relative paths stay within the current package. Cross-package imports use full package URLs:

load("./helpers.zen", "helper")
LocalBlock = Module("./LocalBlock.zen")
RemoteBlock = Module("github.com/org/repo/modules/RemoteBlock.zen")

An instantiation passes name=..., its public io() and config() inputs, and optional dnp and properties arguments.

name establishes instance-path identity, not a fixed reference designator. Refdes-like names are only annotation hints; exact source-reference preservation is not supported.

Use refdes-like names only when the user explicitly asks. In that case, set prefix= on the underlying Component() to match the refdes prefix.

Component() creates a physical part from name, symbol, and pins. The selected symbol is the authority for its footprint, part identity, datasheet, and pins. Keep those properties correct in .kicad_sym rather than repeating them in Zener. Omit true no_connect pins; they are wired to NotConnected() automatically.

Use Symbol(library, name=...) for multi-symbol libraries. Use Part(mpn=..., manufacturer=...) only when the symbol does not already provide part identity.

Read the full file on GitHub · 147 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. 14d ago Changed c8bd07a6b20a
  2. 20d ago Changed 2b9dfa26670f
  3. 21d ago Changed ad0cbb547be6
  4. 23d ago Changed · -2 lines 265773724868
  5. 1mo ago Changed · -6 lines f8e4515289b5
  6. 1mo ago Changed · -2 lines · -12 tokens per session ac646fea3ca8
  7. 1mo ago First seen · 157 lines · 31 tokens per session scan A e692f0e03fa9

Subscribe to this mod's changes

zener-language is a skill published in the GitHub repository diodeinc/pcb (465 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 2,105 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.

Related

Other skills, from other repositories

cardputer-buddy

Iterate on the Cardputer-Adv MicroPython app bundle (Claude Buddy, Snake, Hello) after the device is already provisioned via m5-onboard. Use when the user wants to add a new app, push a single changed .py without re-flashing, watch device serial logs, or run a one-shot REPL command. Trigger on "add an app", "push to…

anthropics/claude-plugins-official · 109 tokens

holoscan-install-wheel

Install Holoscan SDK 5.x CUDA 13 Python wheels in an isolated environment, choosing the full stack or version-matched components.

NVIDIA/skills · 34 tokens

doca-argp

Use this skill for hands-on DOCA Arg Parser CLI work on a shipped sample or new DOCA-using app — adding / removing / renaming flags; wiring docaargpinit → register params → docaargpstart → docaargpdestroy in order; picking a parameter type from the full public enum (DOCAARGPTYPESTRING, INT, BOOLEAN, DEVICE, DEVICEREP…

NVIDIA/skills · 267 tokens

holoscan-module-lifecycle

Develop external Holoscan Modules with the Holoscan CLI and use them in Holoscan applications: scaffold, test, Python bindings, DEB/WHEEL packaging, and clean-consumer proof.

NVIDIA/skills · 47 tokens

lua_package_authoring

Author or update Lua scripts bundled in an explicitly requested runtime Skill or launcher App; use with the owning creator, not for running existing packages or adding native firmware capabilities.

espressif/esp-claw · 38 tokens

triton-ascend

A guide to writing Triton kernels for Ascend NPUs. Triton is a Python-based language for describing parallel operations that run in blocks across the device.

mindspore-ai/akg · 28 tokens