Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/linonon/mcpbookmarks/gemini-mdgit clone --depth 1 https://github.com/linonon/mcpbookmarksWrote 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/linonon/mcpbookmarks/gemini-md)<a href="https://agentmods.dev/instructions/linonon/mcpbookmarks/gemini-md"><img src="https://agentmods.dev/badge/instructions/linonon/mcpbookmarks/gemini-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 | $0.08423 | $0.08423 |
| Opus 5 | $0.04211 | $0.04211 |
| Sonnet 5 | $0.01685 | $0.01685 |
| Haiku 4.5 | $0.00842 | $0.00842 |
Grade A, and why
mcpbookmarks GEMINI.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 4d 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.
This is a copy
100% identical to mcpbookmarks CLAUDE.md — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 923 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Bookmarks - VSCode Extension
这个文档应该与 ./CLAUDE.md 中的说明保持同步更新, 应该保持一模一样的内容.
項目概述
這是一個 VSCode 擴展，提供「AI 書籤」功能。AI（通過 Claude Code）可以在代碼中標記重要位置，並寫入詳細說明，幫助理解和導航代碼庫。
核心功能
- AI 可調用的書籤工具 - 通過 MCP 協議暴露書籤操作
- 手動書籤管理 - 用戶可直接在 VSCode 中創建、編輯、刪除書籤
- 書籤側邊欄 - 在 VSCode 中顯示所有書籤，按文件分組
- 行內標記 - 在編輯器 gutter 區域顯示書籤圖標
- 懸浮預覽 - hover 時顯示書籤說明
技術架構
┌─────────────────────────────────────────────────────────┐
│ VSCode │
│ ┌─────────────────┐ ┌─────────────────────────────┐ │
│ │ 擴展 UI │◄───│ MCP Server (內嵌) │ │
│ │ - TreeView │ │ - add_bookmark │ │
│ │ - Decorations │ │ - list_bookmarks │ │
│ │ - HoverProvider│ │ - remove_bookmark │ │
│ └─────────────────┘ │ - update_bookmark │ │
│ └──────────▲──────────────────┘ │
└─────────────────────────────────────│────────────────────┘
│ MCP (stdio)
┌───────┴───────┐
│ Claude Code │
└───────────────┘
雙版本 MCP Server 架構 (重要!)
本項目有兩套獨立的 MCP Server 實現, 修改功能時必須同時修改兩邊:
| 版本 | 用途 | 文件 |
|---|---|---|
| Embedded | VSCode 擴展內嵌運行 | server.ts, handlers.ts, bookmarkStore.ts |
| Standalone | Claude Code 獨立運行 | serverStandalone.ts, handlersStandalone.ts, bookmarkStoreStandalone.ts |
為什麼有兩個版本?
- Embedded: 在 VSCode 進程內運行, 可以直接訪問 VSCode API (如
vscode.workspace) - Standalone: 通過
npx獨立運行, 不依賴 VSCode, Claude Code 使用這個版本
修改功能時的注意事項
任何 MCP 工具的修改都需要同時修改兩套文件!
例如添加新工具:
src/store/types.ts- 添加類型定義 (共用)src/store/bookmarkStore.ts+bookmarkStoreStandalone.ts- 添加存儲邏輯src/mcp/handlers.ts+handlersStandalone.ts- 添加處理函數src/mcp/server.ts+serverStandalone.ts- 添加工具定義和 switch case
重要: Serena MCP 行號偏移問題
使用 Serena MCP 獲取代碼符號位置時, 必須進行行號轉換:
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.
- 4d ago First seen · 923 lines · 8,423 tokens per session scan A cba43c77bf19
mcpbookmarks GEMINI.md is an instructions file published in the GitHub repository linonon/mcpbookmarks (1 stars, last pushed 6mo ago), licensed MIT. It adds 8,423 tokens to every session, about $0.0421 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to mcpbookmarks CLAUDE.md, differing in 2 lines, and is treated as a copy.
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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.