w3c-mcp: Instructions file for Claude Code

CLAUDE.md

w3c-mcp CLAUDE.md is an instructions file for Claude Code from shuji-bonji/w3c-mcp. It costs 851 tokens per session, scanned A, original, MIT.

A project guide for coding agents working on W3C MCP, a server that provides web standards information such as specifications, CSS properties, HTML elements, and WebIDL through the Model Context Protocol.

In plain words
What is it for?
Use it when building, testing, formatting, or troubleshooting the W3C MCP server, especially when handling missing specifications or converting specification data.
Why use it?
It gives agents the project background, commands, coding rules, and required error-handling patterns so changes fit the existing codebase.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is shuji-bonji/w3c-mcp's own configuration. It tells Claude Code how to work on w3c-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything w3c-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to shuji-bonji/w3c-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/shuji-bonji/w3c-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/shuji-bonji/w3c-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for w3c-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/shuji-bonji/w3c-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/shuji-bonji/w3c-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/shuji-bonji/w3c-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/shuji-bonji/w3c-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for w3c-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/shuji-bonji/w3c-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/shuji-bonji/w3c-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 851 This file is loaded in full into every session.
When invoked 851 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00851 $0.00851
Opus 5.5 $0.00340 $0.00340
Sonnet 5.5 $0.00170 $0.00170
Haiku 4.5 $0.00085 $0.00085

Measured 2mo ago against content hash 28e1d2237425, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

w3c-mcp 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 2mo 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.

CLAUDE.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance for Claude Code when working on this project.

Project Overview

W3C MCP Server — an MCP (Model Context Protocol) server that exposes W3C/WHATWG/IETF web specifications (spec metadata, WebIDL, CSS properties, HTML elements) to AI assistants. Data comes from official npm packages (web-specs, @webref/*); this server adds caching, search, and MCP-shaped tools on top of them.

Common Commands

npm run build      # Compile TypeScript
npm run dev        # Watch mode compilation
npm test           # Run Vitest — run before committing
npm run check      # Biome lint + format (auto-fix)

Code Conventions

Error handling

Throw the custom error classes in src/errors/index.ts (SpecNotFoundError, WebIDLNotFoundError, CSSNotFoundError, ElementsNotFoundError) and let toolHandler() in src/index.ts format them via formatErrorResponse(). Not-found errors should include up to 10 spec-name suggestions generated by src/utils/suggestions.ts.

Tool registration (MCP SDK v2)

Tools are registered in createServer() (src/index.ts) with McpServer.registerTool(name, { description, inputSchema }, toolHandler(...)). inputSchema is the zod object from src/schemas/index.ts — the SDK validates arguments against it before the handler runs and generates the tools/list JSON Schema from it, so put parameter descriptions in .describe() on the zod fields rather than in a separate JSON Schema. Startup goes through serveStdio(), which serves both the initialize (2024-11-05 … 2025-11-25) and server/discover (2026-07-28) openings from the same factory.

Data mapping

Use toSpecSummary() / toSpecSummaries() from src/utils/mapper.ts for any SpecDetail → SpecSummary conversion. Do not reimplement this mapping inline.

Imports (ESM)

  • Use the .js extension on local relative imports (e.g. from './foo.js') — this is required for Node ESM, even in .ts source.
  • Use the node: prefix for built-ins (node:fs, node:path, ...).

Read the full file on GitHub · 84 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. 2mo ago Changed · +18 lines · +235 tokens per session 28e1d2237425
  2. 2mo ago First seen · 66 lines · 616 tokens per session scan A 6d80296707cb

Subscribe to this mod's changes

w3c-mcp CLAUDE.md is an instructions file published in the GitHub repository shuji-bonji/w3c-mcp (4 stars, last pushed 4d ago), licensed MIT. It adds 851 tokens to every session, about $0.0034 per session on Opus 5.5. 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

w3c-mcp CLAUDE.md compared with instructions from other repositories

w3c-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
w3c-mcp CLAUDE.mdshuji-bonji/w3c-mcpInstructions file44d agoMITA851Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode