jlceda-mcp: Instructions file for Claude Code

CLAUDE.md

jlceda-mcp CLAUDE.md is an instructions file for Claude Code from ErikaAlk/jlceda-mcp. It costs 5,007 tokens per session, scanned A, original, MIT.

A set of instructions for Claude Code, an AI coding assistant, working on the jlceda-mcp project. It records the project structure, important rules, and limitations of the JLC EDA extension environment.

In plain words
What is it for?
Guiding changes to the jlceda-mcp project, especially its MCP server, broker, and JLC EDA extension; preserving cross-call state; and avoiding unsupported APIs.
Why use it?
It warns the coding agent about behaviors that can cause subtle bugs, such as the extension re-evaluating its code on every call and the sandbox lacking common browser networking APIs.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

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

Reuse

Borrowing it

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

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 jlceda-mcp CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/erikaalk/jlceda-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/erikaalk/jlceda-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,007 This file is loaded in full into every session.
When invoked 5,007 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 $0.05007 $0.05007
Opus 5.5 $0.02003 $0.02003
Sonnet 5.5 $0.01001 $0.01001
Haiku 4.5 $0.00501 $0.00501

Measured 1mo ago against content hash c5e67325cce6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

jlceda-mcp 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 1mo 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 · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — jlceda-mcp

新会话进来先读这份,再读 README.md(那份是给人看的用法)。 这份是给 agent 看的:架构、不许破坏的不变量、会浪费你半小时的坑。

两个组件

目录 是什么 跑在哪
src/ MCP server + 内嵌 broker Claude Code 起的 node 进程
jlc-bridge/ 嘉立创EDA 扩展 EDA 渲染进程的沙箱里
Claude Code ⇄(stdio) mcp-server ⇄(ws://127.0.0.1:18800/ws/bridge) JLC MCP 扩展 ⇄ EDA
                       └─ broker 就长在这里

⚠ 不变量 1:EDA 每次调用扩展都会把整个 bundle 重新求值一遍

这是这个项目最反直觉的一条,旧版三个 bug 里有两个是它造成的。

从 EDA 安装目录 assets/pro-api/*/api.js 的 Ta() 逆出来的事实: 菜单点击走 extensionApi.callFunctionInExtension → Ta(uuid, fnName),而 Ta 会

  1. 重新从 IndexedDB 读出 entry 文件的源码
  2. 在末尾拼一段 if (typeof fnName === 'function') { fnName(...) } else if (edaEsbuildExportName...)
  3. 包进 with (sandbox) { ... },用 AsyncFunction 整个重新 eval

也就是说:

模块级的 let / 闭包变量,在两次菜单点击之间不保留。 启动激活、点「状态」、点「暂停」,每一次都是一个全新的模块实例。

能跨越重新求值活下来的只有三样:

  • EDA 按 ID 托管的资源:sys_Timer 的定时器、sys_WebSocket 的连接、sys_Storage 的配置
  • globalThis 上挂的东西(沙箱没拦 globalThis,实测可读可写)
  • 已经跑起来的闭包(第一次求值时注册的 onMessage 回调会一直用那一版代码)

所以:所有跨调用的状态一律挂在 hub.ts 的 globalThis.__JLC_BRIDGE_HUB_V2__ 上, 每个导出函数第一件事都是 boot()(幂等)。别写 let connected = false 这种。

在扩展管理器里覆盖导入同 UUID 的扩展时,EDA 先卸载旧的那份(api.js 的 mw() → $v()),再写入新包、加载新代码, 已登录时紧接着按 onStartupFinished 激活(dw() → Ig())。$v() 依次删菜单、清掉这个扩展的 sys_Timer, 再对它的每条 sys_WebSocket 连接摘掉 message / open 监听、调 WebSocket.close(undefined, 原因)。 3.2.166(pro-api 0.3.4.b3076052)里这一调用会被 Chromium 拒绝(InvalidAccessError,关闭码 0 不合法),$v() 在这里中断: 新包没写进去,JLC MCP 菜单没了,旧扩展停在卸载了一半的状态,只能重启 EDA。卸载、停用扩展走的也是 $v(),一样会失败。 所以扩展连着的时候不能覆盖导入:先点「暂停桥接」(pause() → hardReset() 用不带参数的 close() 把连接从 EDA 的连接表里摘掉), 导入之后再点「恢复桥接」。这个顺序 2026-09-29 在真机上连续导入三次都成功,报错也是那天用调试端口抓到的(见「想看扩展里发生了什么」)。

globalThis 上的 hub 不归 EDA 管,导入前后是同一份,新代码拿到的是上一版留下的状态。 link.ts 靠 hub.codeBuild !== CODE_BUILD 发现这件事,推倒重连,并在运行日志里记一条「检测到扩展代码已更新(旧 → 新)」。别删。 CODE_BUILD 是「版本号+代码哈希」,哈希由 jlc-bridge/build/compile.js 在构建时对打包产物取 SHA-256 注入,改了代码、版本号不动也会变。

Read the full file on GitHub · 237 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. 1mo ago Changed · +71 lines · +2,527 tokens per session c5e67325cce6
  2. 2mo ago First seen · 166 lines · 2,480 tokens per session scan A 51ab99bc6f70

Subscribe to this mod's changes

jlceda-mcp CLAUDE.md is an instructions file published in the GitHub repository ErikaAlk/jlceda-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 5,007 tokens to every session, about $0.0200 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 2026-08-31.

Related

jlceda-mcp CLAUDE.md compared with instructions from other repositories

jlceda-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
jlceda-mcp CLAUDE.mdErikaAlk/jlceda-mcpInstructions file11mo agoMITA5,007Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144kyesterdayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot
generative-ai-for-beginners AGENTS.mdmicrosoft/generative-ai-for-beginnersInstructions file124kyesterdayMITA2,981Codex, OpenCode