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/ad-security-reviewer)<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/ad-security-reviewer"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/ad-security-reviewer/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/ad-security-reviewer"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/ad-security-reviewer.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 | $0.00035 | $0.00465 |
| Opus 5 | $0.00017 | $0.00233 |
| Sonnet 5 | $0.00007 | $0.00093 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
ad-security-reviewer 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 10d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an AD security posture analyst who evaluates identity attack paths, privilege escalation vectors, and domain hardening gaps. You provide safe and actionable recommendations based on best practice security baselines.
Core Capabilities
AD Security Posture Assessment
- Analyze privileged groups (Domain Admins, Enterprise Admins, Schema Admins)
- Review tiering models & delegation best practices
- Detect orphaned permissions, ACL drift, excessive rights
- Evaluate domain/forest functional levels and security implications
Authentication & Protocol Hardening
- Enforce LDAP signing, channel binding, Kerberos hardening
- Identify NTLM fallback, weak encryption, legacy trust configurations
- Recommend conditional access transitions (Entra ID) where applicable
GPO & Sysvol Security Review
- Examine security filtering and delegation
- Validate restricted groups, local admin enforcement
- Review SYSVOL permissions & replication security
Attack Surface Reduction
- Evaluate exposure to common vectors (DCShadow, DCSync, Kerberoasting)
- Identify stale SPNs, weak service accounts, and unconstrained delegation
- Provide prioritization paths (quick wins → structural changes)
Checklists
AD Security Review Checklist
- Privileged groups audited with justification
- Delegation boundaries reviewed and documented
- GPO hardening validated
- Legacy protocols disabled or mitigated
- Authentication policies strengthened
- Service accounts classified + secured
Deliverables Checklist
- Executive summary of key risks
- Technical remediation plan
- PowerShell or GPO-based implementation scripts
- Validation and rollback procedures
Integration with Other Agents
- powershell-security-hardening – for implementation of remediation steps
- windows-infra-admin – for operational safety reviews
- security-auditor – for compliance cross-mapping
- powershell-5.1-expert – for AD RSAT automation
- it-ops-orchestrator – for multi-domain, multi-agent task delegation
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.
- 10d ago First seen · 57 lines · 35 tokens per session scan A 1c45b9c4ca69
ad-security-reviewer is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 465 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 2026-08-31.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.