Borrowing it
Nothing to install: this file belongs to ProductOfAmerica/mcp-server-kicad. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ProductOfAmerica/mcp-server-kicad/main/CLAUDE.mdgit clone --depth 1 https://github.com/ProductOfAmerica/mcp-server-kicadWrote 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/productofamerica/mcp-server-kicad/claude-md)<a href="https://agentmods.dev/instructions/productofamerica/mcp-server-kicad/claude-md"><img src="https://agentmods.dev/badge/instructions/productofamerica/mcp-server-kicad/claude-md/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/instructions/productofamerica/mcp-server-kicad/claude-md"><img src="https://agentmods.dev/badge/instructions/productofamerica/mcp-server-kicad/claude-md.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 | $0.03542 | $0.03542 |
| Opus 5 | $0.01771 | $0.01771 |
| Sonnet 5 | $0.00708 | $0.00708 |
| Haiku 4.5 | $0.00354 | $0.00354 |
Grade A, and why
mcp-server-kicad 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 12d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
uv sync --frozen --all-extras --dev # setup (CI uses exactly this)
uv run pytest -v -n auto # full suite (CI uses -n auto everywhere)
uv run pytest tests/test_cst.py -v # one file (no -n: worker startup dwarfs the run)
uv run pytest -k test_name # one test
uv run ruff check . # lint
uv run ruff format --check . # format check (CI enforces)
uv run pyright # type check (basic mode)
uv run python mcp_server_kicad/_cst.py # CST self-check (demo() asserts)
Tests that shell out to kicad-cli (ERC, DRC, exports) auto-skip when it is not installed; so does the autouse fixture in tests/conftest.py that validates every generated .kicad_sch is parseable by kicad-cli. Confirm kicad-cli resolves locally (KICAD_CLI_PATH, PATH, the macOS app bundle, or the versioned Windows install roots) or a green run proves less than it looks. Tests that intentionally write invalid files use @pytest.mark.no_kicad_validation.
That validation fixture is what makes the suite slow: it spawns a kicad-cli process per generated schematic, ~380 ms each. It is memoised on the file's UUID-normalised digest, so each distinct schematic body is validated once per process rather than once per test (376 spawns -> 186, measured 2026-08-10); test_validation_memo.py guards the key against collapsing anything but a UUID. With -n auto on top, a full local run went 213 s -> 40 s on 16 cores.
Run a server by hand: uv run mcp-server-kicad (stdio), or via the MCP Inspector command in README.md.
Architecture
Five MCPServer servers, one module each: schematic.py, pcb.py, project.py, symbol.py, footprint.py. Each defines its own mcp instance and main() console script; server.py merges all tools into the unified kicad server through _copy_tools, which reaches into the private _tool_manager._tools (no public copy API; test_tool_annotations.py depends on the same internals). Every tool passes one of the annotation presets from _shared.py (_READ_ONLY, _ADDITIVE, _DESTRUCTIVE, _EXPORT) and returns a Pydantic model from models.py when it has structured output.
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.
- 12d ago First seen · 68 lines · 3,542 tokens per session scan A b281c51b0ca5
mcp-server-kicad CLAUDE.md is an instructions file published in the GitHub repository ProductOfAmerica/mcp-server-kicad (8 stars, last pushed 28d ago), licensed MIT. It adds 3,542 tokens to every session, about $0.0177 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 instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).