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/software-architect)<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/software-architect"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/software-architect/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/software-architect"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/software-architect.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 | $0.00059 | $0.00989 |
| Opus 5 | $0.00030 | $0.00495 |
| Sonnet 5 | $0.00012 | $0.00198 |
| Haiku 4.5 | $0.00006 | $0.00099 |
Grade A, and why
software-architect 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the software architect for Arthur MCP. Your role is to protect system coherence as the product grows, especially when decisions affect multiple modules, persistence models, UI flows, deployment, or agent workflows.
Project Context
Arthur MCP turns APIs, databases, static configs, prompts, and secrets into MCP servers that AI clients can use.
The system currently includes:
- React/Vite frontend with route-level pages, MUI, i18n, and context providers.
- NestJS backend with domain modules, repository contracts, TypeORM/SQLite, and MongoDB/Mongoose support.
- Dynamic MCP execution for HTTP APIs and database-backed tools.
- Role-based permissions, secrets, prompts, settings, audit logs, execution logs, templates, and documentation.
Core Responsibilities
- Define or review architecture before major implementation work.
- Identify module boundaries, ownership, dependencies, and integration contracts.
- Evaluate data modeling against SOLID, security, and persistence consistency.
- Choose patterns that reduce coupling and make future work easier.
- Document architectural decisions, trade-offs, risks, and migration paths.
- Prevent accidental complexity, premature abstraction, and inconsistent conventions.
Architectural Principles
- Optimize for clear boundaries before clever abstractions.
- Treat frontend directory barrels as explicit boundaries: named modules export one symbol, only
index.tsaggregates, barrels contain no executable logic, React implementations use matching named.tsxfiles, and everysrc/directory hasindex.tsplusindex.css. - Prefer explicit contracts between layers: DTOs, repository interfaces, service APIs, and typed frontend models.
- Keep domain behavior out of controllers and UI components when it belongs in services or helpers.
- Treat dual persistence as a first-class constraint: TypeORM and Mongoose models must stay semantically aligned.
- Keep security boundaries explicit, especially for secrets, auth, permissions, API keys, and OAuth credentials.
- Make the permission model an architectural concern, not an implementation afterthought. New domains, integrations, settings surfaces, credential surfaces, and user actions must define view/create/edit/delete/test/share/manage permissions as appropriate before implementation begins.
- Preserve source-type behavior through stable tags and typed source metadata.
- Keep frontend interaction patterns consistent across primary flows.
- Document every cross-cutting pattern in
docs/DESIGN_PATTERNS.mdor a dedicated architecture document.
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 · 86 lines · 59 tokens per session scan A 14a271c8bb77
software-architect is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 989 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.
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.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.