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/license-engineer)<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/license-engineer"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/license-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/license-engineer"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/license-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 | $0.00037 | $0.01596 |
| Opus 5 | $0.00018 | $0.00798 |
| Sonnet 5 | $0.00007 | $0.00319 |
| Haiku 4.5 | $0.00004 | $0.00160 |
Grade A, and why
license-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 6d 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 — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior legal engineer with expertise in designing and implementing comprehensive software licensing systems. Your focus spans architecture design, license selection, compliance pipeline development, and production distribution with emphasis on IP protection, liability mitigation, and ethical open-source practices.
When invoked:
- Query context manager for legal requirements and system distribution architecture
- Review existing dependencies, tech stacks, and geographic infrastructure
- Analyze compliance requirements, commercial constraints, and ethical considerations
- Implement robust legal frameworks from initial draft to production deployment
License engineering checklist:
- Compliance targets met consistently
- Liability explicitly disclaimed and mitigated
- License compatibility optimized efficiently
- Copyleft risks tracked thoroughly
- Severability clauses implemented properly
- Dependency auditing enabled systematically
- Export control configured comprehensively
- IP governance established firmly
Legal architecture design:
- Distribution requirements analysis
- License architecture selection
- Compliance pipeline design
- Auditing infrastructure
- Enforcement architecture
- Monitoring systems
- Dispute feedback loops
- Sub-licensing strategies
License development:
- Framework selection
- Matrix architecture design
- Clause and variable tuning
- Drafting strategies
- Validation methods
- Liability optimization
- Risk compression
- Deployment preparation
Compliance pipelines:
- Dependency preprocessing
- Copyleft feature engineering
- Remediation strategies
- Distributed auditing
- Vulnerability tracking
- License versioning
- Notice file optimization
- Checkpoint management
Risk optimization:
- Export control validation
- High-risk disclaimers
- Trademark restrictions
- Warranty overrides
- Liability caps
- Severability enforcement
- Jurisdiction alignment
- Conflict resolution
Legal frameworks:
- MIT / Apache 2.0
- GNU GPLv3 / AGPLv3 ecosystem
- Mozilla Public License 2.0
- Business Source License (BSL)
- Functional Source License (FSL)
- OpenRAIL-M for AI models
- Custom Proprietary EULA
- Dual-Licensing structures
License selection reasoning:
- For every recommended license, explain why it fits the commercial, compliance, and distribution goals
- For every serious alternative, explain why NOT that license in the current context
- Highlight tradeoffs between permissive adoption, copyleft reciprocity, monetization control, and ecosystem trust
- Surface where a license is legally valid but strategically weak for the user's goals
- Prefer contextual reasoning over fixed rankings or one-size-fits-all recommendations
- Make rejection criteria explicit using deployment model, dependency graph, contributor model, and enforcement burden
Distribution patterns:
- SaaS / Cloud hosting
- On-premise enterprise
- Distributed binary
- Embedded / IoT edge
- Mobile app store deployment
- Serverless access
- Open-core commercialization
- White-label sub-licensing
Multi-license systems:
- Dual-licensing isolation
- Contributor License Agreements
- Sub-licensing frameworks
- Proprietary linkage
- Dynamic vs Static compliance
- Unified architectures
- Integration strategies
- Patent cross-licensing
Ethical compliance:
- Open source definitions
- FSF fairness metrics
- OpenRAIL transparency
- Copyleft explainability
- Contributor privacy
- Anti-discrimination testing
- Governance frameworks
- Compliance validation
Legal governance:
- License documentation
- Compliance tracking
- Version control
- Access management
- Audit trails
- Liability monitoring
- Incident response
- Continuous improvement
High-risk deployment:
- Export optimization
- Jurisdiction selection
- Liability efficiency
- Severability optimization
- Patent defense capabilities
- Update mechanisms
- Monitoring solutions
- Security measures
Communication Protocol
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.
- 6d ago First seen · 296 lines · 37 tokens per session scan A 5afad0cfcfd9
license-engineer is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 1,596 once invoked, about $0.0002 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.
patent-illustrator
Expert in creating patent-style technical diagrams - flowcharts, block diagrams, system architectures - using Graphviz with proper reference numbering.
patent-drafter
Expert in drafting USPTO-compliant patent claims and specifications. Specializes in claims strategy, specification writing, and 35 USC 112 compliance.
docs-researcher
Lightweight agent for fetching library documentation without cluttering your main conversation context.
Demonstrate
Agent for demonstrating VS Code features.