vscode-web-components-ai AGENTS.md

A project guide for AI assistants working on a VS Code extension that exposes information about web components through MCP. Web components are reusable custom browser elements, and MCP is a way for AI tools to access structured project information.

In plain words
What is it for?
Use it when developing, testing, formatting, bundling, or publishing the vscode-web-components-ai extension.
Why use it?
It tells agents what the project does, what it needs installed, and which commands check, build, format, and package the extension. This helps them follow the repository’s development process.

Instructions file for CodexOpenCode

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/d13/vscode-web-components-ai/agents-md
Clone the repo
git clone --depth 1 https://github.com/d13/vscode-web-components-ai

Made for: Codex, OpenCode.

Per session 1,377 This file is loaded in full into every session.
When invoked 1,377 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 $0.01377 $0.01377
Opus 5 $0.00688 $0.00688
Sonnet 5 $0.00275 $0.00275
Haiku 4.5 $0.00138 $0.00138

Measured yesterday against content hash f3134fa30c79, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vscode-web-components-ai AGENTS.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 yesterday.

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.

AGENTS.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI-powered coding assistants (Augment Agent Mode, Augment Auggie CLI, Copilot Agent Mode, Claude Code, Cursor, Windsurf, etc.) when working with code in this repository. Read this before writing, editing, or executing anything in this repo.

Project Overview

This is a VS Code extension that provides web component information to AI assistants via Model Context Protocol (MCP). The extension discovers custom elements manifests in workspaces and exposes them through an MCP server with HTTP/SSE transports.

Common Commands

Prerequisites

  • nvm use - Switch to the correct Node.js version
  • corepack enable - Enable corepack for package manager
  • pnpm install - Install dependencies

Development

  • pnpm run build - Build extension in development mode
  • pnpm run bundle - Build extension for production
  • pnpm run watch - Watch mode for development
  • pnpm run clean - Clean build artifacts

Code Quality

  • pnpm run lint - Run ESLint on TypeScript files
  • pnpm run lint:fix - Run ESLint with auto-fix
  • pnpm run format - Format code with Prettier
  • pnpm run format:check - Check code formatting

Packaging & Publishing

  • pnpm run package - Create VSIX package
  • pnpm run package-pre - Create pre-release VSIX package
  • pnpm run pub - Publish to marketplace
  • pnpm run pub-pre - Publish pre-release to marketplace
  • pnpm run generate:licenses - Generate license files

Architecture Overview

Core Components

Extension Entry Point (src/extension.ts):

  • Main activation point that initializes logging, configuration, and container
  • Sets up the dependency injection container and registers commands

Container (src/container.ts):

  • Dependency injection container managing all services and providers
  • Central point for service resolution and lifecycle management

MCP Provider (src/mcp/provider.ts):

  • Core MCP server implementation providing web component data
  • Serves HTTP and SSE endpoints for AI assistant integration
  • Implements MCP tools: search-components, get-component-details, list-all-components

Read the full file on GitHub · 178 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. yesterday First seen · 178 lines · 1,377 tokens per session scan A f3134fa30c79

Subscribe to this mod's changes

vscode-web-components-ai AGENTS.md is an instructions file published in the GitHub repository d13/vscode-web-components-ai (11 stars, last pushed 10mo ago), licensed MIT. It adds 1,377 tokens to every session, about $0.0069 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 2026-08-30.