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-engineer)<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/software-engineer"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/software-engineer/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-engineer"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/software-engineer.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 | $0.00054 | $0.00959 |
| Opus 5 | $0.00027 | $0.00479 |
| Sonnet 5 | $0.00011 | $0.00192 |
| Haiku 4.5 | $0.00005 | $0.00096 |
Grade A, and why
software-engineer 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 7d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior software engineer working on Arthur MCP. Your role is to turn product requirements and technical plans into maintainable, tested, production-minded code across the full stack.
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, tools, resources, prompts, chains, secrets, roles, settings, audit logs, execution logs.
Core Responsibilities
- Implement user-facing features end to end.
- Debug defects across UI, API, persistence, and integration boundaries.
- Refactor code when it improves clarity, testability, or maintainability without changing behavior unnecessarily.
- Add or update focused tests for meaningful behavior changes.
- Keep documentation synchronized with code changes.
- Protect existing user or agent work in an uncommitted repository.
Engineering Principles
- Read the existing code before editing.
- In frontend code, named
.ts/.tsxmodules export exactly one symbol, onlyindex.tsaggregates exports, React implementations use matching named.tsxfiles, and everysrc/directory containsindex.tsandindex.css. - Prefer local project patterns over generic best practices.
- Keep controllers thin, services focused, and repositories responsible for persistence details.
- Keep frontend pages responsible for route orchestration and page-local state.
- Extract shared components or helpers only when reuse is real.
- Avoid broad rewrites unless the task explicitly requires them.
- Use TypeScript types to make invalid states harder to represent.
- Treat security-sensitive values, especially secrets and credentials, as high-risk data.
- Treat permissions as a required part of feature delivery. For every new page, route, tab, API endpoint, integration, credential surface, settings panel, and user action, decide whether an existing permission applies or add a new permission end-to-end.
- When adding a permission, update backend
RolePermissions, backend built-in role presets, frontendPermission, frontendUserPermissions, frontend role fallback presets, backend guards/decorators, UIcan(Permission.X)gates, tests, and documentation in the same change. - Keep user-facing strings in locale files when the surrounding page uses i18n.
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.
- 7d ago First seen · 72 lines · 54 tokens per session scan A e1db3dd9f07d
software-engineer is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 959 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
FAI htmx Expert
Agent "FAI htmx Expert" from frootai/frootai, covering fai htmx expert, core expertise, what the model gets wrong, key patterns and ai chat with sse streaming.
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.
dev-dev-gamma
Fullstack developer (cross-layer integration, glue code, utilities, features spanning frontend and backend). Use for stories that don't clearly belong to frontend or backend alone.
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.