easyeda-mcp-fix: Instructions file for Claude Code

CLAUDE.md

easyeda-mcp-fix CLAUDE.md is an instructions file for Claude Code from sheares/easyeda-mcp-fix. It costs 2,036 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for an EasyEDA Pro bridge. EasyEDA Pro is electronic-design software for drawing circuit schematics and printed circuit boards, or PCBs.

In plain words
What is it for?
It is for reading, checking, and editing schematics and PCBs through Claude Code, including running the board checker. It also gives rules for undoing bad edits and troubleshooting setup.
Why use it?
It helps a new user set up the bridge safely, use the right commands for their operating system, and understand tool results instead of seeing raw data.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is sheares/easyeda-mcp-fix's own configuration. It tells Claude Code how to work on easyeda-mcp-fix 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 easyeda-mcp-fix configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sheares/easyeda-mcp-fix. 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/sheares/easyeda-mcp-fix/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/sheares/easyeda-mcp-fix

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 easyeda-mcp-fix CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sheares/easyeda-mcp-fix/claude-md/github.svg)](https://agentmods.dev/instructions/sheares/easyeda-mcp-fix/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sheares/easyeda-mcp-fix/claude-md"><img src="https://agentmods.dev/badge/instructions/sheares/easyeda-mcp-fix/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.

agentmods 80×15 button for easyeda-mcp-fix CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sheares/easyeda-mcp-fix/claude-md"><img src="https://agentmods.dev/badge/instructions/sheares/easyeda-mcp-fix/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,036 This file is loaded in full into every session.
When invoked 2,036 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.02036 $0.02036
Opus 5.5 $0.00814 $0.00814
Sonnet 5.5 $0.00407 $0.00407
Haiku 4.5 $0.00204 $0.00204

Measured 17d ago against content hash f0cc15209977, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

easyeda-mcp-fix 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 17d 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.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This folder is the EasyEDA Pro bridge for Claude Code: an MCP server plus an EasyEDA extension that let you read, check and edit the user's schematics and PCBs, and the /pcb-lint board checker. Assume the person you are talking to is a student, new to both this tool and Claude Code, unless they show otherwise. Explain in plain English and summarise tool results; never paste raw JSON at them.

Which folder are you in?

  • Release folder (usually ~/easyeda-mcp): has dist/, skills/, a .eext file and docs/student-guide.md, but no src/. Use the first three sections below.
  • Source clone: has src/ and tests/. Someone is working on the code; the last section applies as well.

Getting a newbie set up

docs/student-guide.md is the single source of truth for setup. Follow it step by step rather than from memory, and send the user to its Troubleshooting table when something fails.

  1. Find out their OS first and give only that OS's commands. Windows means native PowerShell, never WSL: EasyEDA runs on Windows, so Claude Code must too.
  2. Check the basics (guide step 1). You can run these for them: node --version (needs 20.5+), git --version (backups depend on git), claude --version.
  3. Register the server (guide step 4). Offer to run the claude mcp add command yourself. Use the real path of this folder's dist/mcp-server/index.js; the guide assumes ~/easyeda-mcp, so adjust it if they unzipped somewhere else. In a source clone, run npm install and npm run build first, because dist/ does not exist yet. The name must be easyeda (pcb-lint looks for mcp__easyeda__* tools).
  4. Install the skill (guide step 5). Offer to copy skills/pcb-lint into ~/.claude/skills/ for them.
  5. Hand over the EasyEDA steps. Only the user can do these: import the .eext (Advanced → Extension Manager → Import), switch on External Interactions and Show in top menu, open a schematic or PCB, then click Claude → Connect Claude. Say exactly where to click, and wait for them to confirm each step.
  6. Restart. The easyeda tools do not appear in the session that ran claude mcp add. Tell them to quit Claude Code, start it again in their own project folder, and ask "check the EasyEDA connection".
  7. Verify with server_info: you want extensionConnected: true and their project listed. If the bridge never connects, read ~/.easyeda-mcp/bridge.log.
  8. First tasks should be read-only (guide section 7): list components, show a part's nets, explain DRC errors, check the BOM for missing LCSC numbers. Move on to editing once they trust it.

Read the full file on GitHub · 64 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. 17d ago Changed f0cc15209977
  2. 27d ago First seen · 64 lines · 2,036 tokens per session scan A be64dfacf088

Subscribe to this mod's changes

easyeda-mcp-fix CLAUDE.md is an instructions file published in the GitHub repository sheares/easyeda-mcp-fix (0 stars, last pushed 18d ago), licensed MIT. It adds 2,036 tokens to every session, about $0.0081 per session on Opus 5.5. 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 2026-10-05.

Related

Other instructions, from other repositories

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens