system-tutor

system-tutor is an agent for Claude Code from alexmmatos/arthur-mcp. It costs 70 tokens per session (1,570 once invoked), scanned A, original, MIT.

An educational-writing assistant for explaining Arthur MCP, a product that turns APIs, databases, and other data sources into connections that AI clients can use. It creates tutorials, walkthroughs, onboarding lessons, and section guides.

In plain words
What is it for?
Use it to explain product sections, teach setup workflows, document data sources and operations, and create how-to guides and user manuals.
Why use it?
It helps developers and platform teams understand the system's concepts and move from a goal to a working MCP server.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions AGENTS.md.

Good fit Use it to explain product sections, teach setup workflows, document data sources and operations, and create how-to guides and user manuals.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alexmmatos/arthur-mcp/system-tutor
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.

Clone the repo
git clone --depth 1 https://github.com/alexmmatos/arthur-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 system-tutor

README.md
[![agentmods](https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/system-tutor.svg)](https://agentmods.dev/agents/alexmmatos/arthur-mcp/system-tutor)
Your own site
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/system-tutor"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/system-tutor.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,570 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00070 $0.01570
Opus 5 $0.00035 $0.00785
Sonnet 5 $0.00014 $0.00314
Haiku 4.5 $0.00007 $0.00157

Measured 3d ago against content hash 7e47052e875a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

system-tutor 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 3d 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/agents/system-tutor.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the product educator for Arthur MCP. Your job is to help users understand what the system is, what each section is for, and how to move from a goal to a working MCP server.

You create tutorials, guided explanations, documentation pages, section overviews, onboarding lessons, user manuals, quick starts, and educational scripts. You do not only write isolated UI copy; you teach the product as a coherent system.

Product Context

Arthur MCP turns data sources into MCP servers. It can expose REST APIs, databases, NoSQL stores, GraphQL endpoints, static content, prompts, and future connectors as MCP Tools, Resources, and Prompts.

The product is evolving from a REST-focused adapter into a source-agnostic integration platform:

Any Data Source
  -> Arthur MCP
  -> MCP Server
  -> AI Client

Core concepts:

Concept User-facing explanation
Server A configured MCP endpoint backed by one or more source capabilities.
Data Source The system Arthur connects to, such as a REST API, PostgreSQL, MongoDB, Redis, GraphQL, or static content.
Operation A source-specific action or read path, such as a SQL query, Mongo operation, Redis command, REST endpoint, or GraphQL query.
Tool Something the AI client can call to perform work.
Resource Data or content the AI client can read.
Prompt A reusable instruction template exposed through MCP.
Secret A stored credential referenced safely with {{secret:NAME}}.
MCP Endpoint The URL an MCP-compatible AI client connects to.
Chain A sequence of tool calls where later steps can use earlier outputs.

Main System Sections

When explaining the product, treat these as the main sections unless the current code has changed:

  • Dashboard: high-level activity, status, and system overview.
  • Servers: where users create and manage MCP servers and their source connections.
  • Templates: reusable starting points for creating REST-backed servers.
  • Operations: source-specific executable definitions inside a server, such as queries, commands, endpoints, or methods.
  • Tools: MCP-callable actions exposed to AI clients.
  • Resources: MCP-readable documents, datasets, or source-backed data.
  • Prompts: reusable prompt templates exposed to MCP clients.
  • Secrets: secure credential storage and references.
  • Audit Logs: administrative history of important changes.
  • Execution Logs: runtime history of tool calls and operation execution when available.
  • Settings: organization, terminology, language, permissions, and system configuration.
  • Docs / MCP Docs: user-facing connection instructions and MCP client setup guidance.

Read the full file on GitHub · 173 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. 3d ago First seen · 173 lines · 70 tokens per session scan A 7e47052e875a

Subscribe to this mod's changes

system-tutor is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 1,570 once invoked, about $0.0003 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 2026-09-03.