Borrowing it
Nothing to install: this file belongs to weixiaospace/vscode-claude-copilot. 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/weixiaospace/vscode-claude-copilot/main/CLAUDE.mdgit clone --depth 1 https://github.com/weixiaospace/vscode-claude-copilotWrote 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/weixiaospace/vscode-claude-copilot/claude-md)<a href="https://agentmods.dev/instructions/weixiaospace/vscode-claude-copilot/claude-md"><img src="https://agentmods.dev/badge/instructions/weixiaospace/vscode-claude-copilot/claude-md.svg" alt="Measured on agentmods" 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 | $0.04692 | $0.04692 |
| Opus 5 | $0.02346 | $0.02346 |
| Sonnet 5 | $0.00938 | $0.00938 |
| Haiku 4.5 | $0.00469 | $0.00469 |
Grade A, and why
vscode-claude-copilot 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 7d 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
项目概述
Claude Copilot —— VSCode 扩展。为 Claude Code CLI 用户提供 plugins / MCP / skills / agents / workflows / output styles / rules / hooks / memory / settings / usage 一站式可视化管理,与官方 Claude Code 插件并存(不抢聊天入口)。
文档最后更新:2026-06-19(0.1.21 资源面板扩张:Agents / Workflows / Output Styles / Rules / Hooks 五大新面板 + file-resource 抽象层,详见 ADR-0001 和 CONTEXT.md)。
常用命令
pnpm install # 安装 root + webview-ui 依赖
pnpm build # esbuild + vite 链式构建(extension + 3 个 webview bundle)
pnpm test # Mocha + ts-node,148 个 core 层单测
pnpm package # 产 claude-copilot-<version>.vsix
开发调试:在 VSCode 打开此目录 → F5 启动 Extension Development Host。
技术栈
扩展本体
- TypeScript 5 + Node 18 CJS + esbuild 单文件打包
- VSCode API
^1.90.0 - Mocha +
assert单测(真实 fs 临时目录,零 mock) - pnpm workspace
WebView UI (webview-ui/)
- 纯 vanilla TypeScript(无 React / 无任何运行时框架)
- Vite 8 多入口构建 →
out/webview/assets/<name>.js - Tailwind CSS 4(
@tailwindcss/vite) - Usage 面板图表用 Chart.js 4 via jsdelivr CDN(CSP 白名单放行)
架构分层
src/
├── core/ 纯逻辑,零 vscode 依赖,TDD 覆盖(148 tests)
│ ├── claude-cli.ts CLI 二进制发现 + execFile 包装
│ ├── settings.ts 三层 settings.json 读取 + mergeForSave 合并
│ ├── providers.ts provider profile + matchProfileIdByEnv 反推
│ ├── file-resource.ts FileResourceDescriptor + listResource/createResource/deleteResource
│ │ + extractFrontmatter / parseInlineList。`recursive` 与 `flat-subdirs`
│ │ 两种 discovery;first-wins 同名去重。skills/agents/workflows/
│ │ output-styles/rules 全部 ride 此抽象(ADR-0001)
│ ├── skills.ts SKILL.md(flat-subdirs,identity=dir-name)
│ ├── agents.ts .md(recursive,identity=YAML name,frontmatter model/tools/color)
│ ├── workflows.ts .md(recursive,identity=filename)
│ ├── output-styles.ts .md(recursive,identity=filename-or-frontmatter)+ active selection
│ │ 读写 .claude/settings.local.json#outputStyle
│ ├── rules.ts .md(recursive,identity=filename)+ paths-scoped frontmatter 探测
│ ├── hooks.ts 4 源合并:user/project/local settings.json + plugin hooks/hooks.json
│ │ flattenHooks → {event, matcher, handler, source, sourceFile}
│ ├── memory.ts memory 文件扫描 + MEMORY.md 索引维护(bespoke:index 特殊)
│ ├── mcp.ts MCP server 用户级(CLI)+ 项目级(JSON)
│ ├── plugins.ts installed_plugins.json 解析 + marketplace 管理 + 类型/子项探测
│ └── usage.ts session jsonl 聚合(daily/model/project)
│
├── lib/ vscode 相关工具
│ ├── paths.ts CLAUDE_HOME 常量
│ ├── workspace.ts currentWorkspace() helper
│ ├── watchers.ts FileSystemWatcher 注册(auto-refresh)
│ ├── secrets.ts VSCode SecretStorage gateway
│ ├── status-bar.ts provider 状态栏
│ ├── migrate-providers.ts 一次性迁移
│ └── l10n.ts t() helper(vscode.l10n + en bundle fallback)
│
├── tree/ 11 个 TreeViewProvider
│ ├── file-resource-tree.ts 通用抽象:cache + inflight、scope 分组、adornment 注入
│ │ icon/display/tooltip。skills/agents/workflows/output-styles/rules
│ │ 的 tree 都是 ~15 LOC 的子类
│ ├── plugins-tree.ts Marketplaces + Installed(bespoke)
│ ├── mcp-tree.ts User + Project MCP server(bespoke)
│ ├── skills-tree.ts file-resource 子类
│ ├── agents-tree.ts file-resource 子类 + model · N tools · color 描述
│ ├── workflows-tree.ts file-resource 子类
│ ├── output-styles-tree.ts file-resource 子类,override loadAll 并发拉 active;⭐ 标记
│ ├── rules-tree.ts file-resource 子类,path-scoped chip
│ ├── hooks-tree.ts event 分组(PreToolUse / PostToolUse / …),每条带 source 标签
│ ├── memory-tree.ts 项目记忆列表(bespoke)
│ ├── settings-tree.ts Provider 可展开组 + 三层 settings 文件入口(bespoke)
│ └── usage-tree.ts 单一入口打开 usage WebView
├── commands/ 8 个 CRUD 命令模块
│ ├── file-resource-commands.ts 通用 .create / .delete 注册器(按 desc.kind 派发)
│ ├── skills.ts / agents.ts / workflows.ts / rules.ts 全部 ~12 LOC 描述符调用
│ ├── output-styles.ts 通用 + .setActive 命令(写 settings.local.json)
│ ├── plugins.ts / mcp.ts / memory.ts / providers.ts bespoke
├── webview/ 4 个 WebViewPanel host(usage/marketplace/settings/provider)
│ 每个 panel 注入 nonce + __l10n,CSP 白名单含 jsdelivr(仅 usage)
└── extension.ts activate() 入口,装配所有 provider/command/watcher
webview-ui/
├── usage.html + src/usage.ts + src/usage-dashboard.ts Chart.js 图表 + 日/周/月切换
├── marketplace.html + src/marketplace.ts + src/marketplace-browser.ts
├── settings.html + src/settings.ts + src/settings-form.ts provider 感知的可视化配置
├── src/rpc.ts postMessage 封装的 RPC
├── src/types.ts 与 extension 端共享的类型
├── src/l10n.ts t() helper,读 window.__l10n
└── src/index.css Tailwind @import
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.
- 7d ago First seen · 236 lines · 4,692 tokens per session scan A 97e00ab77ba5
vscode-claude-copilot CLAUDE.md is an instructions file published in the GitHub repository weixiaospace/vscode-claude-copilot (3 stars, last pushed 2mo ago), licensed MIT. It adds 4,692 tokens to every session, about $0.0235 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
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).
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).
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.
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.