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.
npx agentmods add instructions/klinkdev2026/klayout-klink/claude-mdgit clone --depth 1 https://github.com/klinkdev2026/klayout-klinkWrote 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/instructions/klinkdev2026/klayout-klink/claude-md)<a href="https://agentmods.dev/instructions/klinkdev2026/klayout-klink/claude-md"><img src="https://agentmods.dev/badge/instructions/klinkdev2026/klayout-klink/claude-md.svg" alt="Measured on agentmods" 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 | $0.03134 | $0.03134 |
| Opus 5 | $0.01567 | $0.01567 |
| Sonnet 5 | $0.00627 | $0.00627 |
| Haiku 4.5 | $0.00313 | $0.00313 |
Grade A, and why
klayout-klink CLAUDE.md 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 4d 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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
klink — AI-native control plane for KLayout
Let an AI agent (Claude Code / Codex) directly control the KLayout layout editor: draw shapes, manage cells/layers, place instances, run pya macros, and generate layouts with gdsfactory.
Architecture
AI agent
├── MCP: klink-mcp ← klink RPCs exposed as MCP tools
├── Skill: klayout ← RPC + pya macro domain knowledge
└── Skill: klayout-gdsfactory ← gdsfactory → KLayout bridge
│
▼
KLayout (klink_plugin) ← port 8765 (RPC) + 8082 (klive-compat)
Do not rely on a hard-coded RPC count. Query the live server:
from klink import KLinkClient
with KLinkClient().connect() as c:
print([m["name"] for m in c.methods()["methods"]])
MCP tools are organized along two orthogonal axes (klink/mcp/catalog.py):
intent/capability (read/write/verify/escape/all) and
domain/area (device_photonics, routing_backends, …). tools/list
always advertises every tool; call klink.find_tools to navigate them
(no args → domain index; domain=<token> → that area's tools; query=<keywords>
→ ranked matches). --profile accepts both axes — default
read,write,verify,escape.
Setup
Install the package (pip install klayout-klink) and the KLayout salt plugin,
then configure your agent's MCP server:
{
"mcpServers": {
"klayout": {
"command": "<python-that-has-klink>",
"args": ["-m", "klink.mcp", "--profile", "read,write,verify,escape",
"--session-id", "project-klink"],
"env": {
"KLINK_CONTEXT_ROOT": "<your-project>/.klink/sessions"
}
}
}
}
Interpreter rule: optional libraries (gdsfactory, klayout, numpy, …) must live
in the SAME Python that runs klink.mcp. klink does not bundle them — install
the one a feature needs yourself; the tool error names it. klink.status
reports interpreter and capabilities so you can verify.
Environment
- klink core is pure Python; its only runtime dependencies are its own two Rust
kernels (prebuilt wheels, byte-parity with the pure-Python reference), so
pip install klayout-klinkbrings klink + both accelerators. They are speed-only (pure-Python fallbacks exist);pip install --no-depsgives the pure-Python core alone. - gdsfactory must be in the SAME interpreter that runs
klink.mcp. - klink RPC port: 8765; klive-compat port: 8082.
- interaction context memory:
.klink/sessions/<session-id>/interaction_context.jsonl
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.
- 4d ago First seen · 316 lines · 3,134 tokens per session scan A 369af74dfcad
klayout-klink CLAUDE.md is an instructions file published in the GitHub repository klinkdev2026/klayout-klink (26 stars, last pushed 4d ago), licensed Apache-2.0. It adds 3,134 tokens to every session, about $0.0157 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 2026-08-30.
Other instructions, from other repositories
firmware CLAUDE.md
Claude Code instructions for OpenIPC/firmware, covering claude.md, what this is, before you start: is this the right repository?, build and common tasks.
Tutorial_AwesomeModernCPP AGENTS.md
AGENTS.md instructions for Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPP, covering agents.md, 这是什么, 通用 essentials(所有 agent 必读) and 你来做什么?(按场景路由).
brilliant_sdk AGENTS.md
Instructions for brilliantlabsAR/brilliant_sdk, covering brilliant sdk — agent guide, how an app works (the pattern behind everything), minimal reading paths, verify without hardware and testing.
NeoMind CLAUDE.md
Claude Code instructions for camthink-ai/NeoMind, covering neomind — edge ai platform for iot, development commands, ecosystem repositories, extension package contract (.nep) and device type template contract (json).
zmk-config AGENTS.md
AGENTS.md instructions for urob/zmk-config, covering customization guide, ground rules, how the multi-board layout works, adding a new board and where to change what.
ext-apps CLAUDE.md
Claude Code instructions for modelcontextprotocol/ext-apps, a project described as: Official repo for spec & SDK of MCP Apps protocol - standard for UIs embedded AI chatbots, served by MCP servers.