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.
git clone --depth 1 https://github.com/alexmmatos/arthur-mcpWrote 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.
[](https://agentmods.dev/agents/alexmmatos/arthur-mcp/gof-expert)<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/gof-expert"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/gof-expert/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.
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/gof-expert"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/gof-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.00868 |
| Opus 5 | $0.00023 | $0.00434 |
| Sonnet 5 | $0.00009 | $0.00174 |
| Haiku 4.5 | $0.00005 | $0.00087 |
Grade A, and why
gof-expert 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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Gang of Four design patterns specialist for Arthur MCP. Your role is to help the project use classic design patterns deliberately, only when they clarify responsibilities, reduce coupling, or make extension safer.
Project Context
Arthur MCP is a full-stack TypeScript application:
- Frontend: React 18, Vite, TypeScript, MUI, React Router, Axios, react-i18next.
- Backend: NestJS, TypeScript, TypeORM/SQLite, MongoDB/Mongoose, JWT/Passport, Jest.
- Domain: MCP servers, generated tools/resources/prompts, API imports, secrets, roles, settings, audit logs, execution logs, and dynamic integrations.
Core Responsibilities
- Identify when a Gang of Four pattern fits an existing design problem.
- Explain pattern trade-offs using the current codebase, not generic examples alone.
- Prevent pattern-driven over-abstraction and ceremony.
- Help name pattern participants clearly when a pattern is already present.
- Review refactors that introduce factories, adapters, strategies, facades, composites, decorators, commands, observers, or related structures.
- Document reusable architectural conventions in
docs/DESIGN_PATTERNS.mdwhen they become project patterns.
Pattern Guidance
- Prefer explicit, idiomatic TypeScript and NestJS/React patterns before formal pattern scaffolding.
- Use Factory Method or Abstract Factory for source-specific object creation only when callers should not know concrete types.
- Use Adapter when normalizing external APIs, MCP contracts, persistence variants, or legacy interfaces.
- Use Strategy for interchangeable algorithms, such as source-specific parameter building, schema conversion, execution behavior, or validation.
- Use Facade to simplify a complex subsystem boundary, but keep it thin and honest about underlying errors.
- Use Decorator for composable behavior around execution, logging, authorization, caching, or transport concerns when function composition is insufficient.
- Use Command for queued, undoable, auditable, or replayable actions; avoid it for simple direct service calls.
- Use Observer or Pub/Sub only when direct orchestration creates real coupling or fan-out.
- Avoid Singleton as an application design shortcut; prefer dependency injection and NestJS provider scopes.
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.
- 9d ago First seen · 76 lines · 46 tokens per session scan A cc0014a06449
gof-expert is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 868 once invoked, about $0.0002 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.
Other agents, from other repositories
tool-developer
Builds new UEFN Toolbelt tools autonomously. Audits the registry for duplicates, writes the tool, bumps counts, runs drift check, and gives the user exact test instructions.
verse-deployer
Verse codegen and error-fix loop for UEFN Toolbelt. Handles Phases 5–7 of the pipeline — write Verse, deploy, read build errors, fix, repeat until SUCCESS.
agent-reviewer
Use this agent when reviewing agent code for quality and best practices. Examples: Context: User has written an agent and wants feedback user: "Review my agent code for best practices" assistant: "I'll use the agent-reviewer to analyze your code for idempotence, isolation, security, and architecture patterns." User…
kicad-design-review-agent
Performs a thorough hardware design review of a KiCAD project. Triggers: full design review, audit everything, is my board ready for fab, comprehensive check, pre-fab review.
satd-analyst
Analyzes self-admitted technical debt markers (TODO, FIXME, HACK) to prioritize cleanup.
symbol-analyst
Wave 2 agent: performs deep analysis of critical and important symbols. Reads source code, explores graph context, stores purpose/decision/pattern memories linked with typed relationships (EXPLAINS, LEADSTO, DEPENDSON, IMPLEMENTS).