KiCadRoutingTools: Skill for Claude Code

.claude/skills/recommend-plane-mappings/SKILL.md

recommend-plane-mappings is a skill for Claude Code from drandyhaas/KiCadRoutingTools. It costs 89 tokens per session (2,231 once invoked), scanned A, original, MIT.

A KiCad board-review guide that recommends which electrical nets should use copper plane areas and which board layers should carry them. It bases the suggestions on the board stackup, connections, power needs, and signal-return paths.

In plain words
What is it for?
Use it when reviewing a KiCad PCB layout to plan ground and power pours, check existing copper zones, and decide whether the board needs a different layer stack.
Why use it?
It helps avoid choosing plane layers by guesswork, which can worsen signal quality, power delivery, or grounding. It also accounts for limits such as a two-layer board having no inner copper layers.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is drandyhaas/KiCadRoutingTools's own configuration. It tells Claude Code how to work on KiCadRoutingTools itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything KiCadRoutingTools configures →

Reuse

Borrowing it

Nothing to install: this file belongs to drandyhaas/KiCadRoutingTools. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/drandyhaas/KiCadRoutingTools/main/.claude/skills/recommend-plane-mappings/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/drandyhaas/KiCadRoutingTools

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.

agentmods badge for recommend-plane-mappings

README.md
[![agentmods](https://agentmods.dev/badge/skills/drandyhaas/kicadroutingtools/recommend-plane-mappings.svg)](https://agentmods.dev/skills/drandyhaas/kicadroutingtools/recommend-plane-mappings)
Your own site
<a href="https://agentmods.dev/skills/drandyhaas/kicadroutingtools/recommend-plane-mappings"><img src="https://agentmods.dev/badge/skills/drandyhaas/kicadroutingtools/recommend-plane-mappings.svg" alt="Measured on agentmods" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,231 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 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 $0.00089 $0.02231
Opus 5 $0.00044 $0.01115
Sonnet 5 $0.00018 $0.00446
Haiku 4.5 $0.00009 $0.00223

Measured 8d ago against content hash 9eb88e190763, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

recommend-plane-mappings 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 8d 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.

.claude/skills/recommend-plane-mappings/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Recommend Plane Mappings

When this skill is invoked with a KiCad PCB file, recommend which nets should get copper planes and on which layers, with the reasoning a layout engineer would apply.

Step 1: Read the Board

from kicad_parser import parse_kicad_pcb
pcb = parse_kicad_pcb('path/to/file.kicad_pcb')

print(pcb.board_info.copper_layers)                # e.g. ['F.Cu', 'In1.Cu', 'In2.Cu', 'B.Cu']
for layer in pcb.board_info.stackup:               # List[StackupLayer], ordered top to bottom
    print(layer.name, layer.layer_type, layer.thickness, layer.epsilon_r)

# Existing zones - don't silently duplicate them
for zone in pcb.zones:
    print(zone.net_name if hasattr(zone, 'net_name') else zone, getattr(zone, 'layer', '?'))

Report the layer count up front. On a 2-layer board there are no inner layers to give away: recommend a pour on B.Cu (and/or F.Cu) for GND, note the compromise, and suggest /recommend-stackup if the board's signal content justifies 4 layers.

Step 2: Identify Plane-Worthy Nets

Use pad counts plus the /analyze-power-nets approach (datasheet lookup for supply pins and current estimates) rather than name matching alone:

python3 -X utf8 py_router/list_nets.py path/to/file.kicad_pcb --power
  • GND (or the dominant ground net): always plane-worthy.
  • Power rails: plane-worthy when pad count is high or estimated current is large; a rail feeding a handful of pins is better served by wide traces (--power-nets / --power-nets-widths) - say so instead of forcing a plane.
  • Multiple low-current rails can share one split layer when their regions don't interleave; flag the split seams as return-path hazards for any signals that cross them.

Step 3: Assign Layers with SI Rationale

  • Put GND adjacent to the primary signal layers (return paths for outer-layer routing; on 4-layer boards: signals on F.Cu -> GND on In1.Cu).
  • Pair a power plane against GND where the stackup allows (interplane capacitance; e.g. VCC on In2.Cu against GND on In1.Cu).
  • High-speed content raises the stakes: reference-plane adjacency for the layers carrying fast signals comes first, rail convenience second.
  • Outer layers (F.Cu/B.Cu): pick the flood net by same-layer SMD pad count. An outer pour reaches its own-layer SMD pads by fill contact — zero vias for every such pad (the fanout's pour-direct drop skips the barrel when fill reaches the ball). list_nets.py --power prints per-net (F.Cu n SMD, B.Cu n SMD, TH n) for exactly this decision: between candidate nets for an outer flood, the one with the most SMD pads on that layer saves the most vias and escape congestion. TH-heavy nets gain nothing from layer choice (barrels connect everywhere), so don't let TH counts sway it.
  • Mention existing zones that already cover a recommendation instead of repeating them.

Read the full file on GitHub · 155 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. 8d ago First seen · 155 lines · 89 tokens per session scan A 9eb88e190763

Subscribe to this mod's changes

recommend-plane-mappings is a skill published in the GitHub repository drandyhaas/KiCadRoutingTools (395 stars, last pushed yesterday), licensed MIT. It adds 89 tokens to every session and 2,231 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 2026-08-30.

Related

Other skills, from other repositories

tao-train-visual-changenet

Visual ChangeNet for binary image classification and segmentation in AOI defect detection. Use when training, evaluating, exporting, or running inference for PCB defect detection or visual inspection, comparing image pairs for PASS/NOPASS classification, or producing change-segmentation masks. Trigger phrases include…

NVIDIA-TAO/tao-skill-bank · 92 tokens

cad-skills

Use when doing parametric 3D modeling, 2D drafting, geometric kernel development, BIM/IFC processing, PCB design, or AutoCAD .NET development. Index of 20 skills: FreeCAD, OpenSCAD, OCCT, CadQuery, KiCad, SolveSpace, QCAD, xBIM, Clipper2, TongWen and more.

znlgis/opengis-skills · 81 tokens

altium-library

Create and verify Altium schematic symbols (.SchLib) and PCB footprints (.PcbLib) from datasheets and 2D drawings, as code. Use whenever a part library must be made, fixed, measured from a drawing, or checked. Triggers: "make a footprint", "create a symbol", "add this part to the library", "SchLib", "PcbLib"…

ScottJeong/altium-claude-skills · 256 tokens

altium-pcb-placement

Altium PCB component placement — derive board size, decide rotation for main ICs and connectors, split zones, generate a 1:1 placement plan drawing, then inject real coordinates after approval, and check overlaps. Triggers: "PCB placement", "place the components", "how big should the board be", "board outline", "start…

ScottJeong/altium-claude-skills · 250 tokens

altium-schematic-review

Review an Altium schematic (.SchDoc) — find unconnected pins, missing footprint links and net errors, then judge each candidate against the datasheet before calling it a defect. Triggers: "review this schematic", "check my circuit", "ERC", "floating pins", "unconnected", "any missing footprints", "does this schematic…

ScottJeong/altium-claude-skills · 251 tokens

kicad-copilot-mcp

Use when KiCad Copilot MCP tools are available. Entry point for KiCad schematic and PCB workflows.

biosshot/kicad-copilot · 30 tokens