vscode_mcp copilot-instructions.md

Instructions for a VS Code extension that shares the current editor state with language-model clients through an MCP server. MCP is a standard way for an AI tool to access external tools or context.

In plain words
What is it for?
Guiding changes to the VS Code extension, its standalone TypeScript MCP server, shared editor-state file, and tool that returns the current selection.
Why use it?
They document the project’s two-process design and important implementation rules, reducing the risk of breaking editor-state sharing or the server’s message stream.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/user-ic/vscode_mcp/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/user-ic/vscode_mcp

Made for: GitHub Copilot.

Per session 333 This file is loaded in full into every session.
When invoked 333 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00333 $0.00333
Opus 5 $0.00167 $0.00167
Sonnet 5 $0.00067 $0.00067
Haiku 4.5 $0.00033 $0.00033

Measured 2d ago against content hash 5734cde7325b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vscode_mcp copilot-instructions.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 2d 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.

.github/copilot-instructions.md · 31 lines

What it actually says

VS Code Editor MCP — Copilot Instructions

This project is a VS Code extension that embeds a Model Context Protocol (MCP) server exposing the editor's state to LLM clients.

Architecture

  • src/extension.ts — VS Code extension entry point. Listens to editor events and writes the active editor state to a shared JSON file in the OS temp dir.
  • src/server.ts — Standalone MCP server (stdio transport). Reads the shared JSON file and exposes the get_selection tool.
  • src/state.ts — Shared types and the temp file path used by both sides.

The extension and the MCP server run in separate processes. They communicate through the JSON state file (vscode-editor-mcp-state.json in os.tmpdir()).

MCP TypeScript SDK (v2)

Rules

  • Never use console.log in server.ts; stdout corrupts the JSON-RPC stream. Use console.error (stderr) for logging.
  • Keep line/character numbers 1-based in anything user- or LLM-facing.
  • Build with npm run build; output goes to out/.
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. 2d ago First seen · 31 lines · 333 tokens per session scan A 5734cde7325b

Subscribe to this mod's changes

vscode_mcp copilot-instructions.md is an instructions file published in the GitHub repository user-ic/vscode_mcp (0 stars, last pushed 21d ago), licensed MIT. It adds 333 tokens to every session, about $0.0017 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.

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 · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 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 · 4,345 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

vercel/next.js · 7,296 tokens