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.
npx skills add ADScanPro/Claude-AD --skill ad-opsec-telemetrygit clone --depth 1 https://github.com/ADScanPro/Claude-ADWrote 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/skills/adscanpro/claude-ad/ad-opsec-telemetry)<a href="https://agentmods.dev/skills/adscanpro/claude-ad/ad-opsec-telemetry"><img src="https://agentmods.dev/badge/skills/adscanpro/claude-ad/ad-opsec-telemetry/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/skills/adscanpro/claude-ad/ad-opsec-telemetry"><img src="https://agentmods.dev/badge/skills/adscanpro/claude-ad/ad-opsec-telemetry.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 | $0.00171 | $0.02398 |
| Opus 5 | $0.00086 | $0.01199 |
| Sonnet 5 | $0.00034 | $0.00480 |
| Haiku 4.5 | $0.00017 | $0.00240 |
Grade C, and why
ad-opsec-telemetry scanned grade C with 1 finding 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 9d 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
Dumping process memory of `lsass.exe` to extract credentials. How it starts
The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AD OPSEC and Telemetry
Every technique leaves a trace. The goal here is not evasion. It is knowing the noise profile of each action so you can document it for the client before the engagement, pick the quieter of two functionally equivalent techniques, and correlate what you did with what their SOC saw. For a defender, read the same tables backwards: they are the events to monitor and alert on.
Two rules of engagement throughout:
- Document the noise. Tell the client what each high-signal action generated, with the event ID and the source IP, so they can find it in their logs.
- Coordinate the loud ones. DCSync, mass spraying, coercion at scale, and LSASS dumps need explicit client sign-off or an end-of-engagement window when detection no longer matters.
Microsoft Defender for Identity (MDI) is the sensor that matters most in AD; it reads DC traffic directly and ships tuned detections for most of what follows.
Kerberoasting: Event 4769, RC4 (0x17)
Requesting service tickets for accounts with SPNs, to crack offline.
- Event 4769 (Kerberos service ticket requested) fires for each SPN targeted. The tell
is
Ticket Encryption Type = 0x17 (RC4-HMAC). Attackers request RC4 because the resulting hash cracks fastest, but a service that normally uses AES suddenly requested with RC4 is the classic signature. - MDI: "Suspected Kerberoasting attack" is on by default and triggers on the volume and RC4 pattern.
- Requesting all SPNs at once amplifies the signal. Targeting one high-value account is far quieter than roasting the whole domain.
GetUserSPNs.py corp.local/user:pass -dc-ip <dc_ip> -request -outputfile roast.txt
- MITRE: T1558.003 (Steal or Forge Kerberos Tickets: Kerberoasting).
- Defender watch: 4769 with 0x17 for accounts that otherwise use AES; a single principal requesting many distinct SPN tickets in a short window.
- Remediation: strong (25+ char) service-account passwords or gMSA; AES-only on service accounts; monitor 4769 by encryption type.
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.
- 9d ago First seen · 218 lines · 171 tokens per session scan C 36afc489d1be
ad-opsec-telemetry is a skill published in the GitHub repository ADScanPro/Claude-AD (179 stars, last pushed 15d ago), licensed MIT. It adds 171 tokens to every session and 2,398 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
deploying-active-directory-honeytokens
Deploys deception-based honeytokens in Active Directory including fake privileged accounts with AdminCount=1, fake SPNs for Kerberoasting detection (honeyroasting), decoy GPOs with cpassword traps, and fake BloodHound paths. Monitors Windows Security Event IDs 4769, 4625, 4662, 5136 for honeytoken interaction. Use…
deploying-active-directory-honeytokens
Deploys deception-based honeytokens in Active Directory including fake privileged accounts with AdminCount=1, fake SPNs for Kerberoasting detection (honeyroasting), decoy GPOs with cpassword traps, and fake BloodHound paths. Monitors Windows Security Event IDs 4769, 4625, 4662, 5136 for honeytoken interaction. Use…
conducting-internal-reconnaissance-with-bloodhound-ce
Conduct internal Active Directory reconnaissance using BloodHound Community Edition to map attack paths, identify privilege escalation chains, and discover misconfigurations in domain environments.
active-directory-full-attack-chain
Execute a complete Active Directory penetration test from initial enumeration to domain dominance. Use this skill for AD security assessments including LDAP enumeration, Kerberos attacks (Kerberoasting, AS-REP roasting), BloodHound attack path analysis, credential dumping with Mimikatz, lateral movement via…
ad-cs-esc1-abuse
Exploit Active Directory Certificate Services (AD CS) misconfigurations, specifically ESC1. By requesting a certificate based on a overly permissive template that allows the enrollee to supply a Subject Alternative Name (SAN), an attacker can impersonate highly privileged users (like Domain Admins) and seamlessly…
ad-recon
Active Directory reconnaissance skill — host discovery and comprehensive AD enumeration. Activate when the user wants to map an AD environment, enumerate users, groups, shares, trusts, SPNs, or BloodHound data before attacking. Also activate for phrases like "map the domain", "enumerate AD", "find AD users", "collect…