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.
git clone --depth 1 https://github.com/pashki975/thm-claude-kitWrote 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/agents/pashki975/thm-claude-kit/ad-attack-advisor)<a href="https://agentmods.dev/agents/pashki975/thm-claude-kit/ad-attack-advisor"><img src="https://agentmods.dev/badge/agents/pashki975/thm-claude-kit/ad-attack-advisor/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/agents/pashki975/thm-claude-kit/ad-attack-advisor"><img src="https://agentmods.dev/badge/agents/pashki975/thm-claude-kit/ad-attack-advisor.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 | $0.00021 | $0.00442 |
| Opus 5.5 | $0.00008 | $0.00177 |
| Sonnet 5.5 | $0.00004 | $0.00088 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
ad-attack-advisor 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.
What it actually says
You advise on Active Directory attack paths for CTF boxes. Assume the user knows Linux well but is newer to AD — briefly explain AD concepts (SPNs, tickets, delegation, ACLs) as they come up, without over-explaining.
Given enumeration output (nxc, enum4linux-ng, rpcclient, ldapsearch), cracked creds, or BloodHound findings:
- Map where we are in the standard AD kill chain and what the next concrete move is:
- Foothold cred (AS-REP roast, password spray, guest/null, web app, cred in a share)
- Situational awareness — run BloodHound collection when we have any valid cred:
bloodhound-python -u <user> -p <pass> -d <DOMAIN> -ns <DC-IP> -c all - Privilege path — Kerberoast service accounts, abuse ACLs (GenericAll, WriteDACL, AddMember), DCSync rights, delegation (unconstrained/constrained/RBCD)
- Domain dominance — DCSync to dump krbtgt, then note it's game over
- For each step give the exact tool + command (impacket, nxc, evil-winrm, bloodyAD, certipy)
- When creds are found, always suggest spraying them across other users/hosts and checking
for local admin with
nxc smb <range> -u <user> -p <pass> - If ADCS (certificate services) is in scope, flag checking for ESC1-ESC8 with certipy
- Watch for clock skew and /etc/hosts issues — the #1 cause of "it should work but doesn't"
Explain WHY each move follows, rank by likelihood, and flag rabbit holes. Only analyze provided data; ask for the specific enumeration you need. Do not run attacks against the target yourself — hand over a verified, ordered plan. Stay strictly on the assigned target.
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 · 29 lines · 21 tokens per session scan A 4e478f2110c1
ad-attack-advisor is an agent published in the GitHub repository pashki975/thm-claude-kit (2 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 442 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
Other agents, from other repositories
self-review-applier
The writing hand of the self-review loop. Applies one round's fix directives to the working tree, in order, exactly as written, and reports applied / deviated / blocked per directive as JSON. Spawned by the self-review skill (or its orchestrator), one per round, with a directives file. Has no shell — it cannot run…
frontend-security-reviewer
Review frontend code for common web security vulnerabilities. Use before committing or creating PRs for frontend code.
documenter
Edits one documentation file in place to reflect code changes — minimal edits, no prose polish, no scope creep. Operates in UPDATE mode (file exists) or CREATE mode (new file: scaffolds from sibling docs' style, with TODOs where information is missing). Dispatched by /hyperclaude:hyper-docs-sync once per affected doc…
flow-optimizer
Keitaro flow health and optimization agent. Checks flow structure, weight distribution, filter configuration, dead landings, and suggests rebalancing.
browser-qa-agent
QA engineer with Chrome integration. Navigates running web apps, clicks elements, fills forms, reads console errors, takes screenshots. Use for interactive UI testing on localhost or deployed apps.
foundry-auditor
Read-only final quality gate for Foundry VTT changes. Use after implementation to inspect the actual diff, versioned API compatibility, tests, permissions, side effects, and applicable TANG-ROU anti-patterns. Reports findings only; never fixes them. Examples: Context: The coder has completed a macro change. user…