ad-scope

ad-scope is a command for coding agents from ADScanPro/Claude-AD. It costs 37 tokens per session (461 once invoked), scanned A, original, MIT.

A command for defining the boundaries of an authorized Active Directory security assessment. Active Directory is Microsoft’s system for managing users, computers, and permissions across an organization.

In plain words
What is it for?
Preparing a documented scope before testing an organization’s Windows domain, including a limited reachability check of the specified domain controller.
Why use it?
Security work can become unsafe or unauthorized when the tested systems and allowed actions are unclear. This records the approved domains, servers, credentials, targets, restrictions, and timing for other commands to follow.

Command

Part of the Claude-AD plugin — 8 skills, 3 commands, 3 agents shipped together

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.

agentmods
npx agentmods add commands/adscanpro/claude-ad/ad-scope
Clone the repo
git clone --depth 1 https://github.com/ADScanPro/Claude-AD

Or install Claude-AD, the plugin that ships this one along with the rest of its 8 skills, 3 commands, 3 agents.

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 ad-scope

README.md
[![agentmods](https://agentmods.dev/badge/commands/adscanpro/claude-ad/ad-scope.svg)](https://agentmods.dev/commands/adscanpro/claude-ad/ad-scope)
Your own site
<a href="https://agentmods.dev/commands/adscanpro/claude-ad/ad-scope"><img src="https://agentmods.dev/badge/commands/adscanpro/claude-ad/ad-scope.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 461 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00037 $0.00461
Opus 5 $0.00018 $0.00230
Sonnet 5 $0.00007 $0.00092
Haiku 4.5 $0.00004 $0.00046

Measured 4d ago against content hash f9cbac91ac50, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ad-scope 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 4d 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.

commands/ad-scope.md · 43 lines

What it actually says

Define the scope for an authorized Active Directory assessment.

Domain: $1 DC IP (if given): $2

Authorized engagements only. This file is what every later step trusts as its boundary. Fill it from what the client authorized in writing; do not widen it.

Do the following:

  1. If any of these are missing, ask the operator for them before writing:

    • Domain(s) / forest and their functional level, if known.
    • DC IP(s) and DC FQDN(s).
    • Initial credentials you are cleared to use (user + password or hash, or a Kerberos ccache). Note the privilege level (assume low-priv unless told).
    • In-scope hosts / subnets and anything explicitly out of scope.
    • The objective (for example, path to Domain Admin) and any actions the client forbids (no password resets, no coercion, no DCSync, business-hours only).
    • Engagement window and a client point of contact for stop/rollback.
  2. Do a light reachability check only against the DC IP the client gave you, and do not scan anything not yet in scope:

    nxc smb $2 2>/dev/null || echo "DC not reachable / not yet provided"
    
  3. Write a scope file the other commands will read, at ./ad-engagement/scope.md (create the directory). Record everything above plus the date and the operator. Keep credentials only as the engagement requires and note where they are stored; do not paste secrets anywhere they should not live.

  4. Print a short confirmation of the recorded scope and the explicit out-of-scope and forbidden-action list, so it is visible before recon starts.

Do not enumerate or exploit here; scope only. Next step is /ad-recon $1.

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. 4d ago First seen · 43 lines · 37 tokens per session scan A f9cbac91ac50

Subscribe to this mod's changes

ad-scope is a command published in the GitHub repository ADScanPro/Claude-AD (141 stars, last pushed 9d ago), licensed MIT. It adds 37 tokens to every session and 461 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 2026-08-30.

Related

Other commands, from other repositories

hunt

Active Directory offensive phase — credential attacks (spray if allowed), AS-REP and Kerberoast workflows, NTLM relay opportunities, delegation abuse paths, ACL-based escalation, AD CS template abuse, lateral movement within ROE. Usage: /hunt corp.local.

Evaluris-Solutions/claude-active-directory · 0 tokens

recon

Active Directory reconnaissance — DNS SRV/LDAP DC discovery, LDAP user and group enumeration, Kerberos pre-auth and AS-REP candidates, SPN discovery for Kerberoasting, SMB signing and null session policy, password policy, trust relationships, BloodHound/SharpHound collection prep. Requires ROE. Usage: /recon…

Evaluris-Solutions/claude-active-directory · 0 tokens

autopilot

Phased autonomous checklist for AD engagements within ROE — not unsupervised internet-wide scanning. Usage: /autopilot corp.local --normal.

Evaluris-Solutions/claude-active-directory · 0 tokens

chain

Build multi-hop Active Directory attack paths — combine AS-REP, Kerberoast, delegation, ACL abuse, AD CS, lateral steps into one narrative. Usage: /chain.

Evaluris-Solutions/claude-active-directory · 0 tokens

intel

Domain controller and Windows Server build intel — patch level, known abuse techniques relevant to version, planning prioritization. Usage: /intel corp.local.

Evaluris-Solutions/claude-active-directory · 0 tokens

scope

Rules of engagement — verify authorized domains, DCs, subnets, accounts, destructive actions, and exclusions before testing. Usage: /scope or /scope corp.local.

Evaluris-Solutions/claude-active-directory · 0 tokens