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/readme)<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/readme"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/readme.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01803 |
| Opus 5 | $0.00000 | $0.00901 |
| Sonnet 5 | $0.00000 | $0.00361 |
| Haiku 4.5 | $0.00000 | $0.00180 |
Grade A, and why
README 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 8d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Agents
This directory contains specialist agent definitions for Claude Code. Keep this index updated whenever an agent is added, renamed, or removed.
How To Use This Directory
- Use the specialist whose scope matches the task.
- Read the relevant agent file before relying on its guidance.
- Keep all agent documentation in English.
- Treat these agents as project context, not as a replacement for reading the current code.
- Treat permissions as a mandatory part of every feature. Any new page, tab, API endpoint, integration, credential surface, settings panel, or user action must explicitly reuse an existing permission or add a new permission across backend, frontend, role presets, UI gates, tests, and documentation.
Available Specialists
| Agent | File | Use When |
|---|---|---|
backend-test-engineer |
.claude/agents/backend-test-engineer.md |
Writing, reviewing, debugging, and improving backend tests for NestJS services, controllers, guards, repositories, DTOs, and API/e2e flows. |
cloud-expert |
.claude/agents/cloud-expert.md |
Designing or reviewing AWS, GCP, or Azure architecture; cloud security; managed services; cost control; Well-Architected reviews. |
compliance-counsel |
.claude/agents/compliance-counsel.md |
Reviewing software licenses, dependency obligations, attribution, distribution risk, contributor policies, and compliance/legal notes. |
developer-advocate |
.claude/agents/developer-advocate.md |
Creating developer quickstarts, demos, examples, launch content, DX reviews, and community feedback loops. |
devops-expert |
.claude/agents/devops-expert.md |
Creating or reviewing CI/CD, GitHub Actions, deploy automation, infrastructure scripts, monitoring, logging, or operational workflows. |
docker-compose-expert |
.claude/agents/docker-compose-expert.md |
Writing, reviewing, or debugging Docker Compose files, service dependencies, networks, volumes, environment variables, and healthchecks. |
docker-expert |
.claude/agents/docker-expert.md |
Writing, reviewing, or debugging Dockerfiles, multi-stage builds, image size, container security, and production image practices. |
frontend-test-engineer |
.claude/agents/frontend-test-engineer.md |
Writing, reviewing, debugging, and improving frontend tests for React pages, feature components, hooks, API client behavior, routing, permissions, i18n, forms, and user-visible flows with Vitest and React Testing Library. |
gof-expert |
.claude/agents/gof-expert.md |
Choosing, reviewing, naming, or refactoring toward Gang of Four design patterns without over-engineering. |
mobile-first-expert |
.claude/agents/mobile-first-expert.md |
Creating or reviewing responsive/mobile-first layouts, adapting pages and components for small screens, touch targets, breakpoint behavior, and mobile usability fixes. |
nestjs-expert |
.claude/agents/nestjs-expert.md |
Creating, reviewing, or refactoring NestJS modules, controllers, services, DTOs, guards, interceptors, persistence, authentication, and tests. |
oss-scout |
.claude/agents/opensource-expert.md |
Researching, comparing, or choosing open source libraries, frameworks, and tools using current project health signals. |
product-owner |
.claude/agents/project-owner.md |
Writing user stories, acceptance criteria, product specs, backlog prioritization, MVP scope, and requirements documentation. |
react-frontend-engineer |
.claude/agents/react-frontend-engineer.md |
Implementing, debugging, refactoring, and testing React/TypeScript frontend features using Feature-Driven Architecture, Atomic Design, controlled barrel exports, hooks, forms, routes, API integration, i18n, and state. |
render-expert |
.claude/agents/render-expert.md |
Configuring, optimizing, or debugging Render.com deployments, render.yaml, environment variables, health checks, and service setup. |
software-architect |
.claude/agents/software-architect.md |
Designing or reviewing architecture, module boundaries, data modeling, integration strategy, cross-cutting patterns, and technical roadmap decisions. |
software-engineer |
.claude/agents/software-engineer.md |
Implementing, debugging, refactoring, and testing full-stack features across frontend, backend, persistence, and documentation. |
solid-expert |
.claude/agents/solid-expert.md |
Reviewing responsibilities, interfaces, dependency direction, substitutability, extensibility, and maintainability against SOLID principles. |
system-tutor |
.claude/agents/system-tutor.md |
Creating user-facing tutorials, walkthroughs, section guides, onboarding paths, and product explanations for Arthur MCP. |
ui-expert |
.claude/agents/ui-expert.md |
Creating, redesigning, or reviewing React, TypeScript, and MUI UI components/pages in the project's "openclaw" style while respecting Feature-Driven Architecture, Atomic Design, and barrel exports. |
ux-analyst |
.claude/agents/ux-analyst.md |
Auditing user journeys, usability, onboarding, friction points, empty/error/loading states, and user-facing flows while respecting frontend feature boundaries and shared UI conventions. |
vercel-expert |
.claude/agents/vercel-expert.md |
Configuring, optimizing, or debugging Vercel deployments, vercel.json, environment variables, domains, previews, and frontend hosting. |
tool-instructor |
.claude/agents/tool-instructor.md |
Writing user-facing copy: tooltips, helper text, empty states, error messages, onboarding guides, and in-app documentation for Arthur MCP. |
naming-expert |
.claude/agents/naming-expert.md |
Naming variables, functions, components, routes, API endpoints, DB columns, MCP tools, prompts, and UI labels — consistently and clearly across the full stack. |
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.
- 8d ago First seen · 69 lines · 0 tokens per session scan A d98d0efbb862
README is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,803 tokens. 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.
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.
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.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.