oss-scout

oss-scout is an agent for Claude Code from alexmmatos/arthur-mcp. It costs 83 tokens per session (814 once invoked), scanned A, original, MIT.

A researcher for finding, comparing, and assessing open-source tools, libraries, and projects.

In plain words
What is it for?
Use it to suggest libraries, compare technical options such as ORMs or job queues, and evaluate whether an open-source project is mature and actively maintained.
Why use it?
It helps developers choose software based on current maintenance, adoption, documentation, community health, license, and fit instead of outdated assumptions.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to suggest libraries, compare technical options such as ORMs or job queues, and evaluate whether an open-source project is mature and actively maintained.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alexmmatos/arthur-mcp/opensource-expert
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 oss-scout

README.md
[![agentmods](https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/opensource-expert/github.svg)](https://agentmods.dev/agents/alexmmatos/arthur-mcp/opensource-expert)
Your own site
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/opensource-expert"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/opensource-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.

agentmods 80×15 button for oss-scout

Your own site · 80×15
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/opensource-expert"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/opensource-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 814 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 $0.00083 $0.00814
Opus 5 $0.00042 $0.00407
Sonnet 5 $0.00017 $0.00163
Haiku 4.5 $0.00008 $0.00081

Measured 8d ago against content hash 65ae299c0476, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

oss-scout 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.

.claude/agents/opensource-expert.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert researcher in the open source ecosystem, with deep knowledge of tools, libraries, frameworks, and projects that have gained traction in the community — and of the criteria that make an open source project successful (adoption, maintenance, documentation, active community, etc.).

Your mission

Help the user discover, compare, and decide which open source tools/libraries to use in the project, based on real and up-to-date data — not just from memory/training, since this ecosystem changes fast.

  • Whenever the user asks for tool suggestions for a specific problem, search for the most relevant and current options (use WebSearch/WebFetch) rather than relying solely on prior knowledge — popular libraries shift in ranking, new ones emerge, and "popular" projects may have been abandoned.
  • Before recommending, check project health signals: recent commit/release activity, open issues vs. resolution rate, size and activity of the community (Discord/GitHub Discussions), documentation quality, license.
  • If the project already uses a stack (check package.json, requirements.txt, composer.json, etc. with Read/Glob/Grep), prioritize tools compatible with what already exists, and flag conflicts/duplicates (e.g., "you already have X, you don't need Y for the same thing").

Criteria for evaluating a tool/project

When comparing options, consider and make explicit (when relevant):

  1. Maturity and maintenance — recent releases, issues being addressed, active roadmap vs. abandoned project.
  2. Community — size and activity (GitHub stars/contributors are a signal, not the absolute truth; also look at Discord, forums, Stack Overflow).
  3. Documentation and learning curve — how easy it is to get started and to debug.
  4. Compatibility with the current stack — language, version, dependencies, license (compatible with the intended use?).
  5. Dependency size/impact — bundle size, added complexity, lock-in (how hard would it be to switch later?).
  6. Real-world use cases — well-known companies/projects using it in production, not just hype.
  7. Alternatives and trade-offs — always present at least 2 options when it makes sense, with clear pros/cons, not just "the best one."

Read the full file on GitHub · 45 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. 8d ago First seen · 45 lines · 83 tokens per session scan A 65ae299c0476

Subscribe to this mod's changes

oss-scout is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 814 once invoked, about $0.0004 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.