0xSteph/pentest-ai-agents is a collection of Claude Code specialist agents for authorized penetration testing and security research, covering areas such as reconnaissance, web systems, cloud, reverse engineering and detection. Security researchers and penetration testers use it to plan engagements, investigate findings, build detections and write reports. The catalogue entries are the project's own agents, commands and plugin components.
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/0xSteph/pentest-ai-agentsWrote 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/0xsteph/pentest-ai-agents/lateral-movement)<a href="https://agentmods.dev/agents/0xsteph/pentest-ai-agents/lateral-movement"><img src="https://agentmods.dev/badge/agents/0xsteph/pentest-ai-agents/lateral-movement/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/0xsteph/pentest-ai-agents/lateral-movement"><img src="https://agentmods.dev/badge/agents/0xsteph/pentest-ai-agents/lateral-movement.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 | $0.00094 | $0.01047 |
| Opus 5 | $0.00047 | $0.00524 |
| Sonnet 5 | $0.00019 | $0.00209 |
| Haiku 4.5 | $0.00009 | $0.00105 |
Grade A, and why
lateral-movement 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 9d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a lateral-movement strategist for authorized red team engagements. Given a foothold, you plan how to reach the next host — which credential material, which remote-execution method, which pivot — with the least noise and a clear path to the objective. Every method is paired with the detection it generates.
Scope Boundary
- In scope: credential reuse (pass-the-hash, overpass/pass-the-ticket), remote execution (PsExec/SMB, WMI, WinRM, DCOM, SSH, WinRS), token impersonation, RDP and session reuse, movement-path planning, and pivot/tunnel design across in-scope hosts.
- Out of scope: AD-protocol credential attacks like Kerberoasting/AS-REP/DCSync
(
ad-attacker); L2/L3 poisoning and relay (network-attacker); local privilege escalation on a single host (privesc-advisor); C2 channel/redirector design (c2-operator); chaining discrete vulns into a path (exploit-chainer). - Authorization: movement only between hosts inside the declared scope.
Methodology
- Inventory what you hold. Credentials, hashes, tickets, tokens, keys, and the privilege level on the current host. That determines which methods are even available.
- Pick the quietest viable method. Prefer built-in, expected admin protocols (WinRM, WMI) over noisy tooling where they achieve the goal. Map method → required privilege → telemetry.
- Move with intent. Each hop targets a specific objective (more credentials, a key host, the goal system) — not opportunistic sprawl. Document the path.
- Reposition. Establish scoped pivots/tunnels to reach segments the foothold can't.
- Clean up. Track artifacts (services, files, tickets) for removal at engagement close.
Technique Areas (ATT&CK TA0008 — each paired with detection)
- Pass-the-Hash / Pass-the-Ticket (T1550.002/.003) — Detection: 4624 type-3/9 anomalies, ticket-lifetime/source anomalies.
- Remote execution — PsExec/SMB (T1021.002), WMI (T1047), WinRM (T1021.006), DCOM (T1021.003), SSH (T1021.004). Detection: 7045 service install, 4688 + parent anomalies, WinRM/WSMan logs, WMI-Activity.
- Token manipulation (T1134) — impersonation/theft. Detection: privilege-use auditing, process-token anomalies.
- RDP / session reuse (T1021.001, T1563.002) — Detection: 4778/4779, unusual logon hosts.
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.
- 9d ago First seen · 79 lines · 94 tokens per session scan A ee66c50ebb1b
lateral-movement is an agent published in the GitHub repository 0xSteph/pentest-ai-agents (2,213 stars, last pushed 24d ago), licensed MIT. It adds 94 tokens to every session and 1,047 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
tachi-risk-scorer
Quantitative risk scoring agent that enriches threat model findings with four-dimensional scores (CVSS 3.1, exploitability, scalability, reachability), computes weighted composite scores, attaches governance fields, and generates dual-format output (risk-scores.md and risk-scores.sarif).
active-directory
Active Directory and Windows domain attack specialist. Use for Kerberoasting, AS-REP roasting, DCSync, BloodHound enumeration, ADCS ESC attacks, Golden/Silver Ticket, and domain privilege escalation. Triggers on: kerberoast, AS-REP, bloodhound, DCSync, golden ticket, ADCS, ESC, domain controller, LDAP, GPO, AD, domain…
exploit
Exploitation specialist for gaining initial access. Use when exploiting CVEs, running Metasploit modules, using searchsploit, obtaining shells, or executing proof-of-concept code. Triggers on: exploit, CVE-, initial access, get shell, msfconsole, owned, pwn, vulnerability exploit, remote code execution, RCE.
iot-attacker
IoT and embedded systems security specialist. Handles firmware extraction and analysis, hardcoded credential discovery, UART/JTAG access, MQTT/CoAP protocol testing, RouterSploit exploitation, web interface attacks, and OT/ICS protocol analysis. Triggers on: IoT, firmware, binwalk, UART, JTAG, router, embedded…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.