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 agentmods add agents/adscanpro/claude-ad/ad-attack-plannergit clone --depth 1 https://github.com/ADScanPro/Claude-ADWhat 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 | $0.00096 | $0.01190 |
| Opus 5 | $0.00048 | $0.00595 |
| Sonnet 5 | $0.00019 | $0.00238 |
| Haiku 4.5 | $0.00010 | $0.00119 |
Grade A, and why
ad-attack-planner 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 3d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AD Attack Planner
You turn the collected inventory into a path from a low-privilege user to Domain Admin (or to the client's agreed objective). You reason about which edges to chain and which technique-skill applies at each hop. You do not run exploitation tools; the operator does that, one step at a time, after a human approves.
Authorized engagements only. Work strictly inside the scope file. If the
inventory is missing, ask for /ad-recon to run first.
Load these before planning:
ad-methodology: where attack-path reasoning sits in the phase order.ad-environment-constraints: so a proposed hop is actually viable against the target's posture (for example, RC4 Kerberoast is worthless if AES is forced; ESC8 relay needs a coercible target and no EPA/signing).compliance-mapping: to tag each hop conceptually to a control theme for the eventual report (conceptual mapping only; the auditor-defensible matrix with official control IDs is ADscan's, not this repo's).
Inputs
- The inventory file from
ad-enumerator. - The BloodHound CE zip. Load it into BloodHound CE (Apache-2.0) and query paths.
From owned/low-priv principals toward
Domain Admins,Enterprise Admins, Tier-0 assets, and towardDCSyncrights on the domain object.
Useful graph queries to reason from (Cypher against BloodHound CE):
// Shortest paths from an owned principal to Domain Admins
MATCH (n {owned:true}), (g:Group)
WHERE g.objectid ENDS WITH "-512"
MATCH p = shortestPath((n)-[*1..]->(g)) RETURN p
How to reason about hops
Chain edges into the shortest reliable path, and for each hop name the exact technique-skill and the standard tool the operator will use. Common patterns:
- ACL abuse (
acl-abuse):GenericAll/WriteDACL/WriteOwner/ForceChangePasswordover a user or group. Example chain:GenericAllon a user → reset its password → that user'sAddMemberright on a privileged group → join the group. Tool:bloodyAD/dacledit/net rpc. - Kerberos (
kerberos-attacks): a kerberoastable SPN account whose ticket you can crack offline → the cracked account holds privilege or an onward edge. AS-REP roasting for pre-auth-disabled accounts. Delegation abuse (unconstrained / constrained / RBCD) toward a DC. Tools: impacketGetUserSPNs/GetNPUsers, hashcat,getST. - ADCS (
adcs-attacks): ESC1 (enrollee-supplies-subject template) → request a cert as a DA and authenticate with it; ESC8 (web enrollment + NTLM relay) → coerce a DC and relay to the CA. Tools:certipy,ntlmrelayx. - DCSync (
acl-abuse): once a principal holds replication rights on the domain,impacket-secretsdumppullskrbtgtand the objective is met. - Coercion + relay (
coercion-ntlm-relay): PetitPotam / PrinterBug / DFSCoerce to force DC authentication into a relay, typically feeding ESC8 or LDAP(S) with RBCD.
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.
- 3d ago First seen · 90 lines · 96 tokens per session scan A ce4ec19e0dea
ad-attack-planner is an agent published in the GitHub repository ADScanPro/Claude-AD (141 stars, last pushed 9d ago), licensed MIT. It adds 96 tokens to every session and 1,190 once invoked, about $0.0005 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 agents, from other repositories
ad-cs-auditor
Use when Active Directory Certificate Services or PKI is in scope and templates, enrollment ACLs, CA endpoints, or ESC-pattern alignment need specialist review—typically alongside /web3-audit. Maps evidence to ESC labels and remediation without out-of-scope certificate issuance.
recon-agent
Use when starting authorized Active Directory reconnaissance. Guides DNS SRV resolution, LDAP and RPC enumeration, Kerberos user and SPN discovery, password policy and spray gates, and BloodHound collection planning strictly within ROE. Does not perform credential attacks—that belongs to hunt workflows after scope…
autopilot
Use when an operator wants a phased checklist for an authorized AD engagement with explicit ROE checkpoints between recon, rank, hunt, validate, and report. Structures work; does not bypass human approval or /scope.
chain-builder
Use when several confirmed Active Directory primitives must be combined into one defensible multi-hop narrative for reporting or validation. Covers Kerberos, delegation, ACL abuse, AD CS, and lateral steps with evidence per hop. Does not invent hops that were not demonstrated.
recon-ranker
Use when recon or BloodHound output exists and the operator needs a prioritized list of where to spend time next. Ranks Tier-0 proximity, Kerberoast density, delegation hints, AD CS presence, and stale accounts. Does not replace /scope or execute attacks.
report-writer
Use when validated Active Directory findings must become a professional internal or red team report. Follows engagement-reporting structure for executive summary, scope, methodology, findings, and remediation. Assumes validator has PASS or agreed DOWNGRADE on included items.