agentmods.dev

SchematronMCP: Instructions file for Claude Code

CLAUDE.md

SchematronMCP CLAUDE.md is an instructions file for Claude Code from AutumnsGrove/SchematronMCP. It costs 1,638 tokens per session, scanned A, original, MIT.

Project instructions for SchematronMCP, a local server that turns messy HTML web pages into structured JSON matching a chosen schema. It uses a language model on Apple Silicon and also provides a browser-based testing interface.

In plain words
What is it for?
Extracting structured information from HTML, validating results against schemas, running the local MCP server, and manually testing extraction through the web interface.
Why use it?
They explain the project's purpose and architecture so coding work follows the existing design. Local processing avoids sending page data to external APIs.

Instructions file for Claude Code

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

This is AutumnsGrove/SchematronMCP's own configuration. It tells Claude Code how to work on SchematronMCP 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 SchematronMCP configures →

not rated 0repo 10mo ago A scan 1,638 tokens original MIT
View source ↗ AutumnsGrove/SchematronMCP
Reuse

Borrowing it

Nothing to install: this file belongs to AutumnsGrove/SchematronMCP. 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/AutumnsGrove/SchematronMCP/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/AutumnsGrove/SchematronMCP

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 SchematronMCP CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/autumnsgrove/schematronmcp/claude-md/github.svg)](https://agentmods.dev/instructions/autumnsgrove/schematronmcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/autumnsgrove/schematronmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/autumnsgrove/schematronmcp/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 SchematronMCP CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/autumnsgrove/schematronmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/autumnsgrove/schematronmcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,638 This file is loaded in full into every session.
When invoked 1,638 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 $0.01638 $0.01638
Opus 5 $0.00819 $0.00819
Sonnet 5 $0.00328 $0.00328
Haiku 4.5 $0.00164 $0.00164

Measured 9d ago against content hash d52af4344ad9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

SchematronMCP 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 9d 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 · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Instructions - Claude Code

Note: This is the main orchestrator file. For detailed development guides, see the dev branch where ClaudeUsage/README.md contains comprehensive documentation.

Project Purpose

SchematronMCP is a Model Context Protocol (MCP) server that provides HTML-to-JSON extraction using the Schematron-3B model running locally via MLX. It enables AI agents to convert messy HTML into clean, structured JSON conforming to custom schemas.

Tech Stack

  • Language: Python 3.10+
  • Framework: Model Context Protocol (MCP) by Anthropic
  • Key Libraries:
    • mlx-lm (Apple Silicon inference)
    • lxml (HTML parsing/cleaning)
    • pydantic (schema validation)
    • gradio (web UI for testing)
  • Package Manager: uv (Python package manager)

Architecture Notes

  • MCP Server Architecture: Stdio-based server exposing tools via MCP protocol
  • Local Inference: Runs Schematron-3B quantized model via MLX on Apple Silicon
  • Dual Interface: MCP tools for Claude integration + Gradio web UI for manual testing
  • No API Keys Required: Fully local processing, no external API calls
  • Key Files:
    • schematron_mcp/server.py - Main MCP server implementation
    • schematron_mcp/inference/lm_studio.py - LM Studio inference backend
    • schematron_mcp/inference/mlx.py - MLX inference backend
    • examples/gradio_app.py - Web UI for testing
    • schematron_mcp/cleaning/html_cleaner.py - HTML preprocessing

Existing Documentation

  • README.md - Main project documentation and setup
  • docs/quickstart.md - Quick setup and usage guide
  • CONTRIBUTING.md - Contribution guidelines
  • docs/gradio-ui.md - Gradio web UI documentation
  • TODOS.md - Project task tracking
  • examples/README.md - Example usage and schemas

Essential Instructions (Always Follow)

Core Behavior

  • Do what has been asked; nothing more, nothing less
  • NEVER create files unless absolutely necessary for achieving your goal
  • ALWAYS prefer editing existing files to creating new ones
  • NEVER proactively create documentation files (*.md) or README files unless explicitly requested

Read the full file on GitHub · 194 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. 9d ago First seen · 194 lines · 1,638 tokens per session scan A d52af4344ad9

Subscribe to this mod's changes

SchematronMCP CLAUDE.md is an instructions file published in the GitHub repository AutumnsGrove/SchematronMCP (0 stars, last pushed 10mo ago), licensed MIT. It adds 1,638 tokens to every session, about $0.0082 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.

Browser automationData and AI
Related

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.

vercel/next.js · 7,296 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 · 5,153 tokens

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

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

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 · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens