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 skills add geniuskey/klayout-draw-mcp --skill klayout-pnrgit clone --depth 1 https://github.com/geniuskey/klayout-draw-mcpWrote 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/skills/geniuskey/klayout-draw-mcp/klayout-pnr)<a href="https://agentmods.dev/skills/geniuskey/klayout-draw-mcp/klayout-pnr"><img src="https://agentmods.dev/badge/skills/geniuskey/klayout-draw-mcp/klayout-pnr/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.
<a href="https://agentmods.dev/skills/geniuskey/klayout-draw-mcp/klayout-pnr"><img src="https://agentmods.dev/badge/skills/geniuskey/klayout-draw-mcp/klayout-pnr.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00059 | $0.02155 |
| Opus 5 | $0.00030 | $0.01077 |
| Sonnet 5 | $0.00012 | $0.00431 |
| Haiku 4.5 | $0.00006 | $0.00215 |
Grade A, and why
klayout-pnr 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.
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KLayout Place & Route
This is not a P&R engine. It is a set of techniques for driving the
klayout-draw-mcp tools to do placement and routing well. The division of labour:
you (the agent) plan the floorplan, net list and routing order; the server
realises geometry and checks DRC. Iterate: route → drc_check → fix → repeat.
When to use
- Placing cells (standard-cell rows, arrays, abutment)
- Metal routing: multi-layer wires + vias, power rails
- Automatic routing: connecting a net list while avoiding obstacles
Workflow
- Start:
new_layout(top_cell, dbu=0.001)orload_gds(path)to edit existing. - Define library cells:
create_cell("NAND2")→add_box/add_polygon/add_viabuild it →use_cell(top)to return. (Orload_gdsa cell library.) - Place:
place_cell(cell, x, y, orient, nx, ny, dx, dy). For rows, compute positions with theplace_rowsrecipe, then oneplace_cellper placement. - Route:
add_wire(layer, points, width)for known paths (auto-inserts Manhattan corners) andadd_via(...)at layer changes. For many nets / obstacle avoidance, use the maze router below insiderun_script. - Check:
drc_check([...])— read the violation locations, adjust, re-run. - Save:
save_gds(path, open_after=True).
Tools vs. run_script
- Few shapes / known geometry → call the MCP tools directly (
place_cell,add_wire,add_via). Coordinates are micrometers; keep them on your routing grid. - Automatic placement/routing over many nets → use
run_script: build the layout programmatically withklayout.dband the recipes here, thensave_gds.
Layer & grid conventions
| Name | layer/dt | Use |
|---|---|---|
OD 3/0, POLY 6/0 |
device layers | |
M1 9/0, VIA1 11/0, M2 12/0 |
routing stack | |
PWR 90/0 |
power rails | |
BLOCK 200/0 |
routing blockage / debug marker |
Pick one routing pitch (e.g. 0.2 µm) and keep pins and wires on multiples of it. Convention: route M1 horizontal, M2 vertical, switch layers with a via at the turn.
What ships with it
4 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.
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.
- 10d ago First seen · 175 lines · 59 tokens per session scan A d2b5cdf23f09
klayout-pnr is a skill published in the GitHub repository geniuskey/klayout-draw-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 2,155 once invoked, about $0.0003 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.
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…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
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…
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…
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…
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.