Development
Plugin
open-claudecode
完整开源的 Claude Code 项目 - 基于 Anthropic 官方源码重建 🌐 Languages: 中文 | English
Plugin Signal75/100Solid
maintained90
capable79
documented50
adopted63
Install on Claude Code
> /plugin marketplace add LING71671/Open-ClaudeCode
Stats
934
Stars
1,223
Forks
Active
Maintenance
TypeScript
Language
18d ago
Last commit
4mo ago
Created
Repo: LING71671/Open-ClaudeCode
What's inside
Skills
15/claude-opus-4-5-migrationMigrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string updates and prompt adjustments for known Opus 4.5 behavioral differences. Does NOT/frontend-designCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics./gstack-csoSecurity audit workflow for OPC code, providers, plugins, Electron surfaces, local HTTP bridges, filesystem access, and command execution./gstack-document-releaseUpdate or audit OPC documentation after code changes. Use when behavior, setup, CLI flags, desktop workflow, provider support, or plugin surfaces changed./gstack-investigateSystematic root-cause debugging for OPC work. Use when there is a bug, crash, regression, failing command, flaky behavior, provider issue, or unexplained output. Requires evidence before fixes./gstack-qa-onlyRead-only QA report for an OPC desktop flow, CLI command, local URL, staging URL, or documented user journey. Does not modify code.
Show all 15 skillsShow fewer
/gstack-reviewPre-landing code review for the current OPC branch or diff. Use before merging, shipping, or asking whether a change is safe./writing-rulesThis skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on hookify rule syntax and patterns./agent-developmentThis skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts,/command-developmentThis skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in/hook-developmentThis skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events/mcp-integrationThis skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP,/plugin-settingsThis skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior configurable./plugin-structureThis skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "use ${CLAUDE_PLUGIN_ROOT}", "add commands/agents/skills/hooks", "configure auto-discovery", or needs/skill-developmentThis skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude
Agents
14agent-sdk-verifier-pyUse this agent to verify that a Python Agent SDK application is properly configured, follows SDK best practices and documentation recommendations, and is ready for deployment or testing. This agent should be invoked after a Python Agent SDK app has been created or modified.agent-sdk-verifier-tsUse this agent to verify that a TypeScript Agent SDK application is properly configured, follows SDK best practices and documentation recommendations, and is ready for deployment or testing. This agent should be invoked after a TypeScript Agent SDK app has been created orcode-architectDesigns feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequencescode-explorerDeeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting dependencies to inform new developmentcode-reviewerReviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to report only high-priority issues that truly matterconversation-analyzerUse this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Examples: <example>Context: User is running /hookify command without arguments\nuser: "/hookify"\nassistant: "I'll analyze the conversation to find behaviors you want to
Show all 14 agentsShow fewer
agent-creatorUse this agent when the user asks to "create an agent", "generate an agent", "build a new agent", "make me an agent that...", or describes agent functionality they need. Trigger when user wants to create autonomous agents for plugins. Examples: <example> Context: User wants toplugin-validatorUse this agent when the user asks to "validate my plugin", "check plugin structure", "verify plugin is correct", "validate plugin.json", "check plugin files", or mentions plugin validation. Also trigger proactively after user creates or modifies plugin components. Examples:skill-reviewerUse this agent when the user has created or modified a skill and needs quality review, asks to "review my skill", "check skill quality", "improve skill description", or wants to ensure skill follows best practices. Trigger proactively after skill creation. Examples: <example>code-simplifierUse this agent when code has been written or modified and needs to be simplified for clarity, consistency, and maintainability while preserving all functionality. This agent should be triggered automatically after completing a coding task or writing a logical chunk of code. Itcomment-analyzerUse this agent when you need to analyze code comments for accuracy, completeness, and long-term maintainability. This includes: (1) After generating large documentation comments or docstrings, (2) Before finalizing a pull request that adds or modifies comments, (3) Whenpr-test-analyzerUse this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Examples:\n\n<example>\nContext: Daisy has justsilent-failure-hunterUse this agent when reviewing code changes in a pull request to identify silent failures, inadequate error handling, and inappropriate fallback behavior. This agent should be invoked proactively after completing a logical chunk of work that involves error handling, catch blocks,type-design-analyzerUse this agent when you need expert analysis of type design in your codebase. Specifically use it: (1) when introducing a new type to ensure it follows best practices for encapsulation and invariant expression, (2) during pull request creation to review all types being added,
Commands
14/new-sdk-appCreate and setup a new Claude Agent SDK application/code-reviewCode review a pull request/clean_goneCleans up all git branches marked as [gone] (branches that have been deleted on the remote but still exist locally), including removing associated worktrees./commit-push-prCommit, push, and open a PR/commitCreate a git commit/feature-devGuided feature development with codebase understanding and architecture focus
Show all 14 commandsShow fewer
/configureEnable or disable hookify rules interactively/helpGet help with the hookify plugin/hookifyCreate hooks to prevent unwanted behaviors from conversation analysis or explicit instructions/listList all configured hookify rules/create-pluginGuided end-to-end plugin creation workflow with component design, implementation, and validation/review-prComprehensive PR review using specialized agents/cancel-ralphCancel active Ralph Wiggum loop/ralph-loopStart Ralph Wiggum loop in current session
README
1Open-ClaudeCode
完整开源的 Claude Code 项目 - 基于 Anthropic 官方源码重建
🙏 特别感谢
本项目由衷感谢 Anthropic 公司的开源贡献！
Anthropic 通过 npm 包发布 Claude Code，使我们能够学习和研究这个优秀的 AI 编程助手架构。本项目的源码是从官方 npm 包的 source map 中恢复的，仅供学习和研究使用。
"您说的对，我不应该把map文件一并发布到npm中，这是一个非常严重的错误。"
我们理解 source map 文件本应用于开发调试，而非公开发布。Anthropic 对此问题的认识和处理方式值得我们学习。
📖 项目简介
Open-ClaudeCode 是一个完整的 Claude Code 开源版本，包含：
- ✅ 可运行的 CLI - 编译后的完整可执行文件 (v2.1.88)
- ✅ TypeScript 源码 - 1,902 个恢复的源文件供学习研究
- ✅ 官方插件 - 13 个 Anthropic 官方插件
- ✅ 配置示例 - 多种场景的 settings 配置
- ✅ 完整文档 - 项目说明、使用指南、CHANGELOG
📁 目录结构
Open-ClaudeCode/
├── package/ # 可运行的 CLI
│ ├── cli.js # 编译后的 CLI (12.5MB)
│ ├── cli.js.map # Source Map (57MB)
│ ├── package.json # 包配置
│ ├── bun.lock # Bun 锁文件
│ ├── sdk-tools.d.ts # SDK 类型定义 (117KB)
│ └── vendor/ # 原生二进制模块
│ ├── audio-capture/ # 音频捕获 (6 平台)
│ └── ripgrep/ # 代码搜索工具 (6 平台)
├── src/ # 完整 TypeScript 源码 (1,902 文件)
│ ├── tools/ # 30+ 工具实现 (184 文件)
│ ├── commands/ # 50+ 命令实现 (207 文件)
│ ├── services/ # API、MCP、OAuth 服务 (130 文件)
│ ├── components/ # React UI 组件 (389 文件)
│ ├── ink/ # Ink UI 框架 (96 文件)
│ ├── utils/ # 工具函数 (564 文件)
│ ├── hooks/ # React Hooks (104 文件)
│ ├── bridge/ # 桥接模块 (31 文件)
│ ├── vendor/ # 原生模块源码 (4 文件)
│ └── ... # 更多模块
├── plugins/ # 13 个官方插件
│ ├── agent-sdk-dev/
│ ├── claude-opus-4-5-migration/
│ ├── code-review/
│ ├── commit-commands/
│ ├── explanatory-output-style/
│ ├── feature-dev/
│ ├── frontend-design/
│ ├── hookify/
│ ├── learning-output-style/
│ ├── plugin-dev/
│ ├── pr-review-toolkit/
│ ├── ralph-wiggum/
│ └── security-guidance/
├── examples/ # 配置示例
│ └── settings/ # strict / lax / bash-sandbox
├── docs/ # 文档
├── README.md # 本文件
├── ACKNOWLEDGEMENTS.md # 感谢声明
├── CHANGELOG.md # 版本更新记录
├── LICENSE # 许可证说明
├── .gitignore # Git 忽略规则
└── .gitattributes # Git 属性
🚀 快速开始
前置要求
- Node.js 18+ (下载)
- API 密钥（任选一种）：
- 🔵 Anthropic 官方 API — 在 console.anthropic.com 注册获取 API Key
- 🟢 第三方代理 — 国内用户推荐，获取代理地址和 API Key
⚠️ OpenAI 格式代理（如 MiniMax、OpenRouter 等）请使用 Universal-AI-Protocol-Bridge 进行协议转换
- 🔴 Claude 订阅账号 — 运行后通过 OAuth 登录（需科学上网）
第一步：克隆并运行
# 1. 克隆仓库
git clone https://github.com/LING71671/Open-ClaudeCode.git
cd Open-ClaudeCode
# 2. 验证环境
node --version # 需要 >= 18.0.0
node package/cli.js --version # 应显示 2.1.88
# 3. 启动！
node package/cli.js
第二步：认证
首次运行需要认证，选择以下任一方式：
方式一：第三方代理（国内推荐 🇨🇳）
适合中国大陆用户，无需科学上网：
- 获取第三方代理的 API 地址和密钥
- 创建
settings.json：
{
"env": {
"ANTHROPIC_BASE_URL": "https://你的代理地址",
"ANTHROPIC_AUTH_TOKEN": "sk-你的密钥"
}
}
- 运行：
node package/cli.js --settings settings.json
方式二：Anthropic 官方 API
- 访问 console.anthropic.com 注册账号
- 获取 API Key（格式
sk-ant-...） - 创建
settings.json：
{
"env": {
"ANTHROPIC_AUTH_TOKEN": "sk-ant-你的密钥"
}
}
- 运行：
node package/cli.js --settings settings.json
方式三：Claude 订阅账号（OAuth）
需要 Claude 订阅 + 科学上网：
# 直接运行，会自动打开浏览器登录
node package/cli.js
🖥️ 运行截图
📖 使用教程
模式一：交互模式（推荐新手）
直接运行，像聊天一样对话：
node package/cli.js
进入后你会看到交互界面，可以直接输入问题或指令：
> 帮我创建一个 Python Flask 项目
> 解释一下这段代码
> 帮我修复这个 bug
常用操作：
- 输入文字 → 按 Enter 发送
Ctrl+C→ 中断当前操作/help→ 查看所有可用命令/clear→ 清空对话/exit→ 退出
模式二：非交互模式（脚本/管道）
适合自动化、脚本调用：
# 简单问答
node package/cli.js -p "解释一下什么是闭包"
# 处理文件
node package/cli.js -p "帮我重构 src/main.ts 中的 getUser 函数"
# 指定模型
node package/cli.js -p "写一个排序算法" --model sonnet
# JSON 输出（适合程序处理）
node package/cli.js -p "列出当前目录的文件" --output-format json
模式三：继续上次对话
# 继续当前目录的最近对话
node package/cli.js -c
# 恢复指定会话
node package/cli.js -r <session-id>
⚙️ 常用配置
🔑 配置自己的 API（第三方代理 / 自定义端点）
如果你使用第三方 API 代理服务或有自定义端点，可以这样配置：
方式一：通过 Settings 文件（推荐，持久化）
- 创建配置文件：
// settings.json
{
"env": {
"ANTHROPIC_BASE_URL": "https://你的代理地址",
"ANTHROPIC_AUTH_TOKEN": "sk-你的API密钥"
}
}
- 运行时加载配置：
node package/cli.js --settings settings.json
方式二：通过环境变量（临时）
# PowerShell
$env:ANTHROPIC_BASE_URL = "https://你的代理地址"
$env:ANTHROPIC_AUTH_TOKEN = "sk-你的API密钥"
node package/cli.js
# CMD
set ANTHROPIC_BASE_URL=https://你的代理地址
set ANTHROPIC_AUTH_TOKEN=sk-你的API密钥
node package/cli.js
方式三：通过全局配置目录
Claude Code 会自动读取 ~/.claude/settings.json：
// C:\Users\你的用户名\.claude\settings.json (Windows)
// ~/.claude/settings.json (macOS/Linux)
{
"env": {
"ANTHROPIC_BASE_URL": "https://你的代理地址",
"ANTHROPIC_AUTH_TOKEN": "sk-你的API密钥"
}
}
配置后每次运行 node package/cli.js 都会自动使用这些设置。
支持的模型别名
# 常用模型
node package/cli.js --model sonnet # Claude Sonnet（默认）
node package/cli.js --model opus # Claude Opus（最强）
node package/cli.js --model haiku # Claude Haiku（最快）
# 指定完整模型名
node package/cli.js --model claude-sonnet-4-6
node package/cli.js --model claude-opus-4-6
⚠️ 注意事项
- 第三方代理可能不支持所有模型，请以代理方提供的模型列表为准
ANTHROPIC_AUTH_TOKEN和ANTHROPIC_API_KEY任选其一即可- 如果同时设置了环境变量和 settings 文件，环境变量优先级更高
- 不要在公开仓库分享包含 API Key 的配置文件
选择模型
# Sonnet（默认，速度快，性价比高）
node package/cli.js --model sonnet
# Opus（最强，但较慢较贵）
node package/cli.js --model opus
# Haiku（最快最便宜）
node package/cli.js --model haiku
权限模式
# 默认模式（每次操作需要确认）
node package/cli.js
# 自动接受编辑（不用每次确认文件修改）
node package/cli.js --permission-mode acceptEdits
# 跳过所有权限检查（⚠️ 仅限沙箱环境）
node package/cli.js --dangerously-skip-permissions
使用插件
# 从指定目录加载插件
node package/cli.js --plugin-dir ./plugins/code-review
# 加载多个插件
node package/cli.js --plugin-dir ./plugins/code-review --plugin-dir ./plugins/commit-commands
🎯 实战示例
示例 1：让 Claude 帮你写代码
# 进入你的项目目录
cd your-project
# 启动 Claude
node /path/to/Open-ClaudeCode/package/cli.js
# 然后输入：
> 帮我创建一个用户登录 API，使用 Express.js
> 给这个函数添加单元测试
> 修复 src/auth.ts 中的类型错误
示例 2：代码审查
# 使用 code-review 插件
node package/cli.js --plugin-dir ./plugins/code-review
# 或者直接让 Claude 审查
> 帮我审查最近的 git diff
> 检查这个 PR 有没有潜在问题
示例 3：Git 工作流
# 使用 commit-commands 插件
node package/cli.js --plugin-dir ./plugins/commit-commands
# 或者直接用内置命令
> /commit # 智能生成 commit message
📋 内置命令速查
在交互模式下输入 / 开头的命令：
| 命令 | 功能 |
|---|---|
/help | 显示帮助 |
/clear | 清空对话 |
/compact | 压缩对话历史 |
/model | 切换模型 |
/theme | 切换主题 |
/vim | 切换 Vim 模式 |
/cost | 查看费用统计 |
/stats | 查看使用统计 |
/share | 分享会话 |
/exit | 退出 |
❓ 常见问题
Q: 提示需要认证怎么办？
A: 首次运行需要登录。运行后会自动打开浏览器，用你的 Claude 账号登录即可。或者设置 ANTHROPIC_API_KEY 环境变量。
Q: 运行后卡住了？
A: 检查网络连接。如果在中国大陆，可能需要代理：
$env:HTTPS_PROXY="http://127.0.0.1:7890"
node package/cli.js
Q: 如何查看花了多少钱？
A: 在交互模式下输入 /cost 或 /stats 查看。
Q: 如何配置第三方代理或自定义 API？
A: 创建 settings.json 文件，内容如下：
{
"env": {
"ANTHROPIC_BASE_URL": "https://你的代理地址",
"ANTHROPIC_AUTH_TOKEN": "sk-你的密钥"
}
}
然后运行 node package/cli.js --settings settings.json。也可以放到 ~/.claude/settings.json 实现全局配置。
Q: 可以在任何目录运行吗？
A: 可以！但建议在你的项目目录下运行，这样 Claude 可以访问项目文件。
Q: 和 npm 安装的区别？
A: 这个仓库提供的是从 npm 包恢复的完整源码，适合学习研究。功能上和 npm 安装的版本一致。
Q: 支持 OpenAI 格式的 API 吗？
A: Claude Code 原生使用 Anthropic API 格式。如果你需要使用 OpenAI SDK 格式调用，可以使用 Universal-AI-Protocol-Bridge 进行协议转换：
功能特性：
- 🔄 协议转换 - 将 OpenAI SDK 格式转换为 Anthropic/Claude API 格式
- 🌐 多协议支持 - OpenAI、Anthropic、Google Gemini、AWS Bedrock、Azure、Ollama 等
- ⚡ 流式传输优化 - 完整支持 SSE/NDJSON 流式响应
- 🔐 安全加密 - AES-GCM 加密保护 API Key
- ☁️ Cloudflare Workers - 边缘部署，全球低延迟
使用方法：
- 访问 在线测试地址 或自行部署
- 选择目标协议（如 Anthropic）并填入 API Key
- 生成代理 URL，将你的 OpenAI SDK
baseURL指向该地址即可
// 示例：使用 OpenAI SDK 调用 Claude
import OpenAI from 'openai';
const client = new OpenAI({
baseURL: 'https://your-bridge-url/proxy/{token}/v1',
apiKey: 'any-key' // 实际 Key 已加密在 token 中
});
// 现在可以用 OpenAI 格式调用 Claude 了！
const response = await client.chat.completions.create({
model: 'claude-3-5-sonnet-latest',
messages: [{ role: 'user', content: 'Hello!' }]
});
📚 学习源码
源码位于 src/ 目录，包含 1,902 个源文件：
# 查看入口点
cat src/main.tsx
# 查看工具实现
ls src/tools/
# 查看命令实现
ls src/commands/
使用插件
插件位于 plugins/ 目录，包含 13 个官方插件：
# 查看插件列表
ls plugins/
# 查看插件详情
cat plugins/ralph-wiggum/.claude-plugin/plugin.json
📊 项目统计
| 类别 | 数量 |
|---|---|
| TypeScript 源码 (.ts + .tsx) | 1,884 文件 |
| JavaScript 源码 (.js) | 18 文件 |
| 所有源码文件总计 | 1,902 文件 |
| 工具实现 | 30+ 个 |
| 命令实现 | 50+ 个 |
| 服务模块 | 15+ 个 |
| UI 组件 | 25+ 个 |
| 官方插件 | 13 个 |
| 原生模块 | 2 个 (audio-capture, ripgrep) |
| 支持平台 | 6 个 (macOS/Linux/Windows × arm64/x64) |
📜 许可证
本项目源码版权归 Anthropic PBC 所有。
本仓库仅供学习和研究使用，不代表 Anthropic 官方立场。
详见 LICENSE 和 ACKNOWLEDGEMENTS.md。
🔗 相关链接
最后更新: 2026-04-01
File tree
1636LING71671/Open-ClaudeCodeView on GitHub
.claude-plugin/
marketplace.json
.codex/
environments/
environment.toml
.gitattributes
.github/
workflows/
desktop-verify.yml
.gitignore
.mcp.json
ACKNOWLEDGEMENTS.md
agent-team-test-artifacts/
agent-1/
npm-cache/
_cacache/
content-v2/
sha512/
ba/
43/
2d6190a2d08edc0f7aedf3dae75f2db40ff66f9341a3fd25bad3161fcf5ef34ec94bcfe56e857c3f28f6feda7769dff01369d25dc8d12a74a42570d93b9d
index-v5/
8e/
df/
5472fe1cc0e8f0c6de8ab9638dcb0eb4220317269f225ef94e7896902fd7
_update-notifier-last-checked
CHANGELOG.md
CLAUDE.md
cliRunner.cjs
DESIGN.md
desktop/
build/
icon.icns
icon.png
icon.svg
conversationContext.js
electron/
appLifecycle.cjs
cliEventParser.cjs
cliRunner.cjs
cliRunner.constants.cjs
crashReporter.cjs
cspInterceptor.cjs
desktopStateStore.cjs
doctor.cjs
e2eVisualQa.cjs
electronSandboxPolicy.cjs
ipc/
clipboardStateIpc.cjs
diagnosticsIpc.cjs
healthIpc.cjs
humanGateIpc.cjs
loopEventIpc.cjs
projectIpc.cjs
providerIpc.cjs
runtimeIpc.cjs
sessionIpc.cjs
ipcContract.cjs
ipcHandlers.cjs
ipcValidation.cjs
ipcValidation.constants.cjs
longRunningToolMonitor.cjs
main.cjs
memoryPolicy.cjs
memoryStore.cjs
nvidiaClient.cjs
persistence/
privateJsonFile.cjs
sqliteStateStore.cjs
stateSchema.cjs
preload.cjs
processControl.cjs
projectFiles.cjs
promptRefiner.cjs
providerAnthropicProtocol.cjs
providerBridge.cjs
providerBridgeHttp.cjs
providerBridgeMessages.cjs
providerBridgeStreams.cjs
providerChecker.cjs
providerConfig.cjs
providerIssue.cjs
providerModelDiscovery.cjs
providerProfilePolicy.cjs
providerProtocol.cjs
providerReasoningStore.cjs
providerRequestState.cjs
providerSecretVault.cjs
providerStreamAdapter.cjs
providerTransport.cjs
rateLimiter.cjs
redaction.cjs
runtimeSupervisor.cjs
selectionController.cjs
sendChannel.cjs
serviceProbe.cjs
sessionStore.cjs
supportBundle.cjs
userDataMigration.cjs
windowManager.cjs
package-lock.json
package.json
providerProfilePolicy.cjs
README.md
renderer/
app.js
assets/
opc-logo.svg
controllers/
chatController.js
projectController.js
projectFileController.js
promptComposerController.js
providerController.js
renderController.js
runController.js
serviceController.js
settingsController.js
css/
activity.css
base.css
inspector.css
message.css
modal.css
project.css
responsive.css
settings.css
shell.css
sidebar.css
styles.css
topbar.css
index.html
ports/
opcClient.js
services/
activity.js
completionGuard.js
confirmationBanner.js
logBuffer.js
markdownRenderer.js
messageActions.js
messageScroll.js
providerEditorModel.js
providerHealth.js
providerIssueRules.js
providerPanelViewModel.js
renderScheduler.js
reportSelection.js
sessionBanner.js
settingsHelpers.js
settingsProviderPanel.js
speedReader.js
state/
advancedPermissionPolicy.js
agentContextBudget.js
agentContract.js
agenticEvaluationScenarios.js
agentProviderRouter.js
agentRuntimeProfile.js
agentStepRunner.js
agentTaskLedger.js
agentTaskStepEngine.js
agentToolEvidence.js
agentToolPlanner.js
agentToolRegistry.js
agentVerificationEngine.js
agentWorkerRuntime.js
builtInSkills.js
commandPolicy.js
competenceProfile.js
conversationContext.js
projectFileIndex.js
projectRuntimeContext.js
providerFailurePolicy.js
providerRuntimeDiagnostics.js
runAudit.js
runRequestPlanner.js
runResumeRecovery.js
runRuntimeState.js
runTaskPlanner.js
runTaskQueue.js
runtimeDiagnostics.js
runtimeQualityDashboard.js
stateRepository.js
stateRules.js
stateStore.js
taskCheckpointStore.js
taskCheckpointSummarizer.js
taskManager.js
workspaceTrust.js
views/
inspectorView.js
messageView.js
projectContextView.js
runtimeContextView.js
sidebarView.js
toolView.js
scripts/
electronEnv.cjs
installApplications.cjs
openApplications.cjs
stateRules.js
test/
accessibilitySmoke.test.cjs
appLifecycle.test.cjs
cliEventParser.test.cjs
cliRunner.test.cjs
cliRunnerConstants.test.cjs
cspInterceptor.test.cjs
desktopStateStore.test.cjs
doctor.test.cjs
electronEnv.test.cjs
electronSandboxPolicy.test.cjs
electronSmoke.cjs
electronVisualSmoke.cjs
helpers/
rendererModules.cjs
installApplications.test.cjs
ipcContract.test.cjs
ipcHandlers.test.cjs
ipcLoopGuards.test.cjs
ipcValidation.test.cjs
ipcValidationConstants.test.cjs
longTaskCycle.test.cjs
memoryPolicy.test.cjs
privateJsonFile.test.cjs
promptRefiner.test.cjs
providerBridge.test.cjs
providerBridgeMessages.test.cjs
providerChecker.test.cjs
providerConfig.test.cjs
providerIssue.test.cjs
providerModelDiscovery.test.cjs
providerProfilePolicy.test.cjs
providerRequestState.test.cjs
providerTransport.test.cjs
redaction.test.cjs
rendererActivityUi.test.cjs
rendererConversationContext.test.cjs
rendererProject.test.cjs
rendererPromptComposer.test.cjs
rendererProviderModels.test.cjs
rendererRunTaskModels.test.cjs
rendererRuntime.test.cjs
rendererSettings.test.cjs
rendererSidebarView.test.cjs
rendererState.test.cjs
rendererStateRepository.test.cjs
runtimeSupervisor.test.cjs
selectionController.test.cjs
sendChannel.test.cjs
serviceProbe.test.cjs
srcBridgeRefactorGates.test.cjs
srcRefactorGates.test.cjs
stateSchema.test.cjs
supportBundle.test.cjs
userDataMigration.test.cjs
windowManager.test.cjs
docs/
OPC_DOMAIN_GLOSSARY.md
OPC_FULL_AUDIT_2026-06-08.md
OPC_LOOP_ENGINEERING_AUDIT_2026-06-21.md
OPC_PRODUCTION_HARDENING_2026-06-08.md
OPC_SCALE_READINESS.md
OPC_SURGICAL_REFACTORING.md
OPC_VS_CODEX_AUDIT.md
examples/
hooks/
bash_command_validator_example.py
settings/
README.md
settings-bash-sandbox.json
settings-lax.json
settings-strict.json
index.html
LICENSE
package/
package-lock.json
package.json
bun.lock
cli.js
cli.js.map
LICENSE.md
package.json
README.md
sdk-tools.d.ts
vendor/
audio-capture/
arm64-darwin/
audio-capture.node
arm64-linux/
audio-capture.node
arm64-win32/
audio-capture.node
x64-darwin/
audio-capture.node
x64-linux/
audio-capture.node
x64-win32/
audio-capture.node
ripgrep/
arm64-darwin/
rg
arm64-linux/
rg
arm64-win32/
rg.exe
COPYING
x64-darwin/
rg
x64-linux/
rg
x64-win32/
rg.exe
plugins/
agent-sdk-dev/
.claude-plugin/
plugin.json
agents/
agent-sdk-verifier-py.md
agent-sdk-verifier-ts.md
commands/
new-sdk-app.md
README.md
claude-opus-4-5-migration/
.claude-plugin/
plugin.json
README.md
skills/
claude-opus-4-5-migration/
references/
effort.md
prompt-snippets.md
SKILL.md
code-review/
.claude-plugin/
plugin.json
commands/
code-review.md
README.md
commit-commands/
.claude-plugin/
plugin.json
commands/
clean_gone.md
commit-push-pr.md
commit.md
README.md
explanatory-output-style/
.claude-plugin/
plugin.json
hooks/
hooks-handlers/
session-start.sh
hooks.json
README.md
feature-dev/
.claude-plugin/
plugin.json
agents/
code-architect.md
code-explorer.md
code-reviewer.md
commands/
feature-dev.md
README.md
frontend-design/
.claude-plugin/
plugin.json
README.md
skills/
frontend-design/
SKILL.md
gstack-workflows/
.claude-plugin/
plugin.json
README.md
skills/
gstack-cso/
SKILL.md
gstack-document-release/
SKILL.md
gstack-investigate/
SKILL.md
gstack-qa-only/
SKILL.md
gstack-review/
SKILL.md
hookify/
.claude-plugin/
plugin.json
.gitignore
agents/
conversation-analyzer.md
commands/
configure.md
help.md
hookify.md
list.md
core/
... 1600 moreShowing a partial view of a very large repo.
FAQ
open-claudecode is a Claude Code plugin with 15 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes claude-opus-4-5-migration, frontend-design, gstack-cso. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is open-claudecode?
- 完整开源的 Claude Code 项目 - 基于 Anthropic 官方源码重建 🌐 Languages: 中文 | English
- How do I install open-claudecode?
- Run these in Claude Code: /plugin marketplace add LING71671/Open-ClaudeCode. Then prompt normally.
- Does open-claudecode auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is open-claudecode free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.