An operator for KLayout, a desktop editor used to view and edit the geometric layouts of chips, microelectronic devices, and photonic circuits.

Use it to inspect, create, modify, select, validate, and debug layout shapes and cells in KLayout.

It provides structured queries and validation for layout state, reducing reliance on screenshots when checking selections, cells, layers, and geometry.

klayout — Skill for Claude Code by klinkdev2026/klayout-klink

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 klinkdev2026/klayout-klink --skill klayout

Clone the repo

git clone --depth 1 https://github.com/klinkdev2026/klayout-klink

Made for: Claude Code.

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/klinkdev2026/klayout-klink/klayout/github.svg)](https://agentmods.dev/skills/klinkdev2026/klayout-klink/klayout)

Your own site

<a href="https://agentmods.dev/skills/klinkdev2026/klayout-klink/klayout"><img src="https://agentmods.dev/badge/skills/klinkdev2026/klayout-klink/klayout/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/klinkdev2026/klayout-klink/klayout"><img src="https://agentmods.dev/badge/skills/klinkdev2026/klayout-klink/klayout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,182 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

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 211
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00051	$0.06182
Opus 5.5	$0.00020	$0.02473
Sonnet 5.5	$0.00010	$0.01236
Haiku 4.5	$0.00005	$0.00618

Measured 25d ago against content hash 77e93c93914a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

klayout 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 25d 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.

klink/mcp/skills/klayout/SKILL.md · 565 lines

How it starts

The opening of the file, as written. The whole thing — 565 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KLayout Layout Operations

You control KLayout through MCP tools provided by klink-mcp. Tool names preserve their dotted RPC names, such as layout.info, selection.get, and shape.insert_box.

If you are unsure, call klink.guide first

klink.guide {} reports what is open, what intent state exists on disk, the literal call for each user intention, and a suggested next action. Every orchestrated tool result also carries next_action — follow it verbatim. The workflow lives in tool results, not in your memory.

Core Rule

Use structured layout state as the source of truth:

selection.get
interaction.selection.latest / recent, when available
shape.query
layout.info
cell.list / cell.tree
layer counts
geometry validators

Never call view.screenshot unless the user explicitly asks for a screenshot or visual artifact in the current conversation. Do not start screenshot capture automatically, do not use it as a fallback, and do not ask for it as a routine verification step.

Interaction Context Memory

klink-mcp may expose session-scoped interaction memory tools. This memory is external to the KLayout plugin and persists under:

.klink/sessions/<session-id>/interaction_context.jsonl

Use these tools for explicit sent/pinned user intent. For the MVP, stored memory is created when the user clicks the KLayout SEND toolbar action or when an agent calls selection.send_context, not from every ordinary GUI selection move:

User phrase	First tool
sent GUI context: just sent, this area, here, that one	`interaction.selection.latest` or `interaction.selection.recent`
multiple recent items: these three, the previous few	`interaction.selection.recent`
exact current selection	`selection.get`
explicit id such as `sel_0006`	`interaction.selection.get`
important reusable region	`interaction.selection.label`
the ruler(s) I sent / claim what I sent	`interaction.selection.latest` -> `rulers[].id` -> `region.claim`

Read the full file on GitHub · 565 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.

25d ago Changed · +26 lines 77e93c93914a
2mo ago First seen · 539 lines · 51 tokens per session scan A 31779ead417b

Subscribe to this mod's changes

klayout is a skill published in the GitHub repository klinkdev2026/klayout-klink (46 stars, last pushed 26d ago), licensed Apache-2.0. It adds 51 tokens to every session and 6,182 once invoked, about $0.0002 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.

Hardware and IoT

klayout next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
klayoutklinkdev2026/klayout-klink	Skill	46	26d ago	Apache-2.0	A	51	Claude Code
gke-compute-classesgoogle/skills	Skill	22k	yesterday	Apache-2.0	A	83	Claude Code, Codex
jetson-diagnosticNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	30	Claude Code, Codex
holoscan-install-wheelNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	34	Claude Code, Codex
offensive-z-waveSnailSploit/Claude-Red	Skill	10k	25d ago	MIT	A	113	Claude Code, Codex
doca-socket-relayNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	236	Claude Code, Codex
hsb-flashNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	B	94	Claude Code