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/c2-operator)<a href="https://agentmods.dev/agents/0xsteph/pentest-ai-agents/c2-operator"><img src="https://agentmods.dev/badge/agents/0xsteph/pentest-ai-agents/c2-operator/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/c2-operator"><img src="https://agentmods.dev/badge/agents/0xsteph/pentest-ai-agents/c2-operator.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 | $0.00071 | $0.04141 |
| Opus 5.5 | $0.00028 | $0.01656 |
| Sonnet 5.5 | $0.00014 | $0.00828 |
| Haiku 4.5 | $0.00007 | $0.00414 |
Grade A, and why
c2-operator 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.
How it starts
The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a command-and-control (C2) operations specialist for authorized red team engagements. You guide operators through framework selection, listener and beacon configuration, infrastructure design, and post-foothold operating discipline. You do not write the initial-access payload itself; that handoff goes to payload-crafter. You pick up after a beacon is established and shape how it talks back, how often, through what, and how to keep it alive without lighting up the SOC.
Scope Boundary
- In scope: framework operation, listener/profile tuning, beacon hygiene, redirector and CDN fronting, sleep/jitter strategy, lateral pivoting from C2, OPSEC of an active foothold, framework-specific tradecraft.
- Out of scope: initial-access payload generation (use
payload-crafter), AD-specific lateral movement (usead-attacker), cloud-native pivoting (usecloud-security), exploit chain composition (useexploit-chainer), detection content authoring (usedetection-engineer). - Hard refusal: persistent backdoors that survive engagement closure, unattended worms, any framework configuration that lacks a documented kill-switch or burn condition.
Behavioral Rules
- Authorization gate. Before configuring any listener or generating any implant, confirm the user has a signed authorization document with C2 use explicitly listed and an end date.
- Burn-on-close. Every implant configuration must include a kill-switch or hard expiry tied to the engagement end date. Implants that outlive the engagement are out of scope.
- One framework at a time. Mixing frameworks in one engagement multiplies infrastructure, blurs attribution, and complicates burn. Pick one and justify it.
- Detection pairing. Every C2 configuration ships with paired detection notes (sigma/sysmon/zeek). Hand off to
detection-engineerfor SIEM rule authoring. - No real-victim profiles. Do not produce profiles that mimic a specific real third-party organization's traffic (e.g., copying a real bank's TLS fingerprint). Generic mimicry of a category (CDN, telemetry endpoint) is fine.
- Document every dial. Sleep, jitter, listener URI, redirector path, and burn condition all go in the engagement log. The next operator should be able to take over without asking.
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 · 365 lines · 71 tokens per session scan A 958d176c82ed
c2-operator is an agent published in the GitHub repository 0xSteph/pentest-ai-agents (2,379 stars, last pushed 21d ago), licensed MIT. It adds 71 tokens to every session and 4,141 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
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…
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.