kicad-mcp-pro: Skill for Claude Code

.github/skills/code-review/SKILL.md

code-review is a skill for Claude Code from oaslananka/kicad-mcp-pro. It costs 110 tokens per session (3,227 once invoked), scanned A, original, MIT.

A code-review guide for GitHub pull requests in KiCad MCP Pro, a server that lets coding agents work with KiCad electronics projects. It covers code, tests, packaging, desktop software, automation, security, documentation, and releases.

In plain words
What is it for?
Reviewing changes to the Python server, KiCad connections, tool definitions, tests, package wrappers, Tauri/Rust desktop code, GitHub Actions, documentation, and generated files.
Why use it?
It helps reviewers find real correctness, security, compatibility, and release problems without wasting time on minor style issues or imagined failures.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

This is oaslananka/kicad-mcp-pro's own configuration. It tells Claude Code how to work on kicad-mcp-pro 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 kicad-mcp-pro configures →

Part of the kicad-pro plugin — 10 skills, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to oaslananka/kicad-mcp-pro. 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/oaslananka/kicad-mcp-pro/main/.github/skills/code-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/oaslananka/kicad-mcp-pro

Made for: Claude Code.

Or install kicad-pro, the plugin that ships this one along with the rest of its 10 skills, 1 MCP server.

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 code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/oaslananka/kicad-mcp-pro/code-review/github.svg)](https://agentmods.dev/skills/oaslananka/kicad-mcp-pro/code-review)
Your own site
<a href="https://agentmods.dev/skills/oaslananka/kicad-mcp-pro/code-review"><img src="https://agentmods.dev/badge/skills/oaslananka/kicad-mcp-pro/code-review/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 code-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/oaslananka/kicad-mcp-pro/code-review"><img src="https://agentmods.dev/badge/skills/oaslananka/kicad-mcp-pro/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,227 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00110 $0.03227
Opus 5 $0.00055 $0.01614
Sonnet 5 $0.00022 $0.00645
Haiku 4.5 $0.00011 $0.00323

Measured 9d ago against content hash 83fa49d527a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

code-review scanned grade A with 1 finding 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 9d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- `os.system`, `os.popen`, or equivalent shell execution in production paths;
.github/skills/code-review/SKILL.md · 420 lines

How it starts

The opening of the file, as written. The whole thing — 420 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KiCad MCP Pro Code Review

Review pull requests for correctness, security, contract stability, compatibility, test coverage, and release safety. Prefer a small number of high-confidence, actionable findings over broad style feedback.

KiCad MCP Pro is a production MCP server that drives real KiCad projects. Treat unsafe mutations, incorrect tool contracts, path/subprocess mistakes, protocol regressions, and misleading engineering verdicts as high-risk.

Review stance

  • Review the changed code and the behavior introduced by the change.
  • Comment on unchanged code only when the PR newly makes an existing defect reachable or materially increases its impact.
  • Do not invent failures, tool behavior, KiCad behavior, CI results, or browser evidence.
  • Distinguish a demonstrated defect from a possible improvement.
  • Prefer correctness and user-impact findings over formatting or naming nits already enforced by repository tooling.
  • Do not require a broad refactor when a focused fix addresses the defect.
  • If no actionable defect is found, do not manufacture a comment.

1. Gather review context first

Before writing findings:

  1. Read the PR title, description, changed files, and diff.
  2. Use GitHub MCP context when available to inspect:
    • linked issues or incidents referenced by the PR;
    • review-relevant PR metadata;
    • changed-file scope;
    • workflow/check status;
    • failed job logs when a failure is relevant to the changed code.
  3. Consult repository policy and architecture when needed:
    • ARCHITECTURE.md
    • CONTRIBUTING.md
    • SECURITY.md
    • docs/development/coding-standards.md
    • docs/development/testing-policy.md
    • docs/security/threat-model.md
    • .github/PULL_REQUEST_TEMPLATE.md
  4. Treat the PR head branch as the source of repository instructions and skill content.
  5. Use existing CI evidence when it is from the reviewed head commit and covers the exact concern. Do not claim a check passed if you did not observe it.

Read the full file on GitHub · 420 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. 9d ago First seen · 420 lines · 110 tokens per session scan A 83fa49d527a1

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository oaslananka/kicad-mcp-pro (77 stars, last pushed today), licensed MIT. It adds 110 tokens to every session and 3,227 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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

jlcpcb-headstage-pcb

A project-specific guide for reviewing and improving printed-circuit-board designs made for JLCPCB's electronics-manufacturing service. It also covers manufacturing files such as Gerbers and drill files.

Dissipative-ATLAS/jlceda-codex-mcp · 170 tokens

rtl-review

Audit RTL code for lint violations, synthesis hazards, coding-style compliance, and readability. Use when the user says "review this Verilog", "check my RTL", "lint this module", "is this code synthesizable", or shares an HDL file and asks for feedback before simulation or tape-in.

vibeic/vibe-ic · 63 tokens

circuit-design

Use when designing an electronic circuit from requirements, choosing topology or regulator type, selecting component values, planning protection circuits, or deciding what goes on a board before schematic capture begins. Also use when the user asks "what components do I need" or "how should I power this.".

ProductOfAmerica/mcp-server-kicad · 60 tokens

using-kicad

Use when starting any conversation involving electronics, KiCad, PCB design, schematic capture, circuit design, or EDA tasks.

ProductOfAmerica/mcp-server-kicad · 30 tokens

schematic-plan

Use after circuit-design produces a validated BOM (specs/bom.md) to plan exact component placement coordinates and wiring before schematic capture begins. Pure planning — no file modifications.

ProductOfAmerica/mcp-server-kicad · 39 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