ad-overview

ad-overview is a skill for Claude Code, Codex from PurpleAILAB/Decepticon. It costs 31 tokens per session (671 once invoked), scanned A, original, Apache-2.0.

A catalogue of playbooks for assessing and attacking Microsoft Active Directory, the system many organizations use to manage Windows users, computers, and permissions. It covers tools and techniques such as BloodHound analysis, Kerberoasting, certificate-service checks, and credential extraction.

In plain words
What is it for?
Use it during authorized penetration tests or security assessments to ingest BloodHound data, find risky accounts and permissions, inspect certificate services, check replication rights, and review possible compromise paths.
Why use it?
It groups common Active Directory security checks and attack paths into a repeatable workflow. This helps security testers identify routes from an existing foothold to broader domain control.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

About the project

Decepticon is an autonomous red-team agent that coordinates AI agents, security tools, sandboxes, and supporting services for authorized cybersecurity assessments. Security researchers and red teams can run it through its Docker stack, cloud service, command-line interface, or Python SDK, with the catalogue entries representing its available skills.

PurpleAILAB/Decepticon · 5,450 stars · on GitHub · decepticon.red

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 skills/purpleailab/decepticon/ad
Any agent
npx skills add PurpleAILAB/Decepticon --skill ad
Clone the repo
git clone --depth 1 https://github.com/PurpleAILAB/Decepticon

Made for: Claude Code, Codex.

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-overview

README.md
[![agentmods](https://agentmods.dev/badge/skills/purpleailab/decepticon/ad.svg)](https://agentmods.dev/skills/purpleailab/decepticon/ad)
Your own site
<a href="https://agentmods.dev/skills/purpleailab/decepticon/ad"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/ad.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 671 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 5.1 $0.00031 $0.00671
Opus 5 $0.00015 $0.00336
Sonnet 5 $0.00006 $0.00134
Haiku 4.5 $0.00003 $0.00067

Measured 6d ago against content hash ee514281eb3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ad-overview 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • ad — 89% identical, 20 lines differ
packages/decepticon/decepticon/skills/standard/ad/SKILL.md · 54 lines

What it actually says

AD Operator Skill Catalog

Playbooks

Skill Use for
/skills/standard/ad/bloodhound-query/SKILL.md Ingest + common Cypher queries
/skills/standard/ad/kerberoasting/SKILL.md Roast SPN users, crack with hashcat
/skills/standard/ad/asrep-roasting/SKILL.md dontreqpreauth users
/skills/standard/ad/adcs-esc1/SKILL.md ESC1 template abuse → domain admin
/skills/standard/ad/dcsync/SKILL.md Replication rights → krbtgt dump
/skills/standard/ad/laps/SKILL.md LAPS local admin password extraction
/skills/standard/ad/netexec/SKILL.md NetExec (formerly CrackMapExec) cheatsheet — SMB/WinRM/LDAP/MSSQL modules

Workflow

  1. Collect: bash("bloodhound-python -u user -p pass -d DOMAIN -c all --zip")
  2. bh_ingest_zip("/workspace/bh.zip")
  3. dcsync_check — if any principal, that's instant domain compromise
  4. kg_query(kind="user") and filter for hasspn=true → Kerberoast queue
  5. kg_query(kind="user") and filter for dontreqpreauth=true → AS-REP roast
  6. ADCS: bash("certipy find -u user -p pass -dc-ip X -json") then adcs_audit
  7. plan_attack_chains to see graph-computed domain compromise paths

Crown jewels to add

kg_add_node(kind="crown_jewel", label="Domain Admins group")
kg_add_node(kind="crown_jewel", label="krbtgt account")
kg_add_node(kind="crown_jewel", label="DC: DC01.corp.local")
Files

What ships with it

11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 54 lines · 31 tokens per session scan A ee514281eb3d

Subscribe to this mod's changes

ad-overview is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,450 stars, last pushed 6d ago), licensed Apache-2.0. It adds 31 tokens to every session and 671 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.