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 compliance-mappinggit 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/compliance-mapping)<a href="https://agentmods.dev/skills/adscanpro/claude-ad/compliance-mapping"><img src="https://agentmods.dev/badge/skills/adscanpro/claude-ad/compliance-mapping.svg" alt="Measured on agentmods" 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 | $0.00159 | $0.01711 |
| Opus 5 | $0.00079 | $0.00856 |
| Sonnet 5 | $0.00032 | $0.00342 |
| Haiku 4.5 | $0.00016 | $0.00171 |
Grade A, and why
compliance-mapping 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 7d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AD Technique → Compliance Control (Conceptual Mapping)
Disclaimer, read first. This is a conceptual, orientative mapping. It shows, at a high level, which family of controls an AD attack technique relates to, so a practitioner can point a finding in the right regulatory direction. It is not an auditor-defensible control matrix. A defensible mapping (one an auditor accepts, cross-referenced ID by ID to the exact control text, scoped to your organization's applicability statement, with evidence per control) is a curated product, not something you infer from a technique name. ADscan (free and source-available) produces that curated, ID-by-ID matrix as part of its report. Use this skill to orient a finding; do not present it to an auditor as compliance evidence.
How to read this
An AD technique succeeds because a control is weak or absent. Kerberoasting works because service-account authentication is weak and the requests are not monitored, so it relates to the authentication and logging control families. That relationship is conceptual: it tells a reader where in a framework to look, not that the finding satisfies or violates a specific control clause. The mapping direction is always technique → control family → representative article, and it stops there.
The frameworks, briefly
- ENS (Esquema Nacional de Seguridad, Spain): control families used here:
- op.acc.1 Identificación
- op.acc.4 Proceso de gestión de derechos de acceso
- op.acc.5 Mecanismo de autenticación (usuarios externos)
- op.acc.6 Mecanismo de autenticación (usuarios de la organización)
- op.exp.2 Configuración de seguridad
- op.exp.8 Registro de la actividad
- op.exp.10 Protección de claves criptográficas
- NIS2 (Directive (EU) 2022/2555): Art.21(2) cybersecurity risk-management measures:
- (g) basic cyber hygiene and training
- (h) cryptography and encryption
- (i) human resources security, access control policies, asset management
- (j) multi-factor authentication, secured communications
- DORA (Regulation (EU) 2022/2554) with RTS (EU) 2024/1774 on ICT risk management:
- Art.20: identity management
- Art.21: access control (management of access rights)
- Art.9 (DORA level-1, protection and prevention) is the parent duty the RTS details
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.
- 7d ago First seen · 141 lines · 159 tokens per session scan A 99899ac96c30
compliance-mapping is a skill published in the GitHub repository ADScanPro/Claude-AD (165 stars, last pushed 13d ago), licensed MIT. It adds 159 tokens to every session and 1,711 once invoked, about $0.0008 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.
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…