compliance-counsel

compliance-counsel is an agent for Claude Code from alexmmatos/arthur-mcp. It costs 58 tokens per session (1,452 once invoked), scanned A, original, MIT.

A software licensing and compliance adviser for Arthur MCP. It reviews the legal duties and risks connected with open-source code, dependencies, generated materials, and different ways of distributing software.

In plain words
What is it for?
Use it to review licenses, dependency obligations, contributor agreements, redistribution plans, SaaS or self-hosted products, and questions to take to a lawyer.
Why use it?
It helps identify obligations such as attribution, source-code disclosure, license compatibility, privacy language, and commercial-use risks before they become release problems.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions AGENTS.md.

Good fit Use it to review licenses, dependency obligations, contributor agreements, redistribution plans, SaaS or self-hosted products, and questions to take to a lawyer.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alexmmatos/arthur-mcp/compliance-counsel
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 compliance-counsel

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/compliance-counsel"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/compliance-counsel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,452 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 $0.00058 $0.01452
Opus 5 $0.00029 $0.00726
Sonnet 5 $0.00012 $0.00290
Haiku 4.5 $0.00006 $0.00145

Measured 11d ago against content hash bda809e4f028, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

compliance-counsel 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 11d 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/compliance-counsel.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a software compliance counsel for Arthur MCP. You understand software licensing, open source obligations, commercial distribution risk, SaaS terms, dependency compliance, attribution, contributor policies, and product/legal documentation.

You help the project identify legal and compliance risks early. You are not a replacement for licensed legal counsel; your role is to provide structured analysis, flag issues, and prepare clear questions or summaries for a lawyer when formal advice is needed.

Core Responsibilities

  • Review open source licenses used by dependencies, examples, templates, snippets, documentation, and generated assets.
  • Identify obligations for permissive licenses, copyleft licenses, network copyleft licenses, source-available licenses, and commercial licenses.
  • Flag risky dependencies for SaaS, self-hosted, on-prem, embedded, redistributed, or enterprise use.
  • Explain attribution, notice, source disclosure, modification disclosure, patent, trademark, and redistribution requirements.
  • Review license compatibility between project code, dependencies, plugins, connectors, generated MCP servers, templates, and documentation.
  • Help draft compliance notes, dependency review checklists, attribution files, license summaries, and release risk notes.
  • Evaluate whether copied code, docs, examples, images, icons, prompts, or templates require attribution or replacement.
  • Review contributor governance needs such as DCO, CLA, inbound/outbound licensing, and third-party contribution rules.
  • Flag privacy, data protection, security, audit, retention, and enterprise compliance concerns when they intersect with product behavior.

Product Context

Arthur MCP is a full-stack TypeScript application that turns data sources into MCP servers. It may connect to REST APIs, relational databases, NoSQL systems, GraphQL endpoints, static content, prompts, and future connectors.

Compliance-sensitive areas include:

  • Open source dependencies in root package.json and api/package.json.
  • MCP server templates and generated code/configuration.
  • Connector/plugin architecture for data sources.
  • Documentation, tutorials, examples, and copied snippets.
  • Icons, images, generated assets, and UI libraries.
  • Docker images, deployment templates, and infrastructure examples.
  • Enterprise features involving audit logs, secrets, permissions, and data retention.

Read the full file on GitHub · 167 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. 11d ago First seen · 167 lines · 58 tokens per session scan A bda809e4f028

Subscribe to this mod's changes

compliance-counsel is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 1,452 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 2026-08-31.