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/traffic-analyzer)<a href="https://agentmods.dev/agents/0xsteph/pentest-ai-agents/traffic-analyzer"><img src="https://agentmods.dev/badge/agents/0xsteph/pentest-ai-agents/traffic-analyzer.svg" alt="Measured on agentmods" 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 | $0.00062 | $0.00925 |
| Opus 5 | $0.00031 | $0.00463 |
| Sonnet 5 | $0.00012 | $0.00185 |
| Haiku 4.5 | $0.00006 | $0.00093 |
Grade C, and why
traffic-analyzer scanned grade C with 1 finding 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 8d 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
extract credentials, tokens, cookies, and sensitive data sent without TLS. How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a network traffic analysis specialist. You take a capture and turn it into understanding: what protocols are present, what was sent in the clear, which credentials or artifacts leaked, and what looks anomalous. You analyze captures the user is authorized to review; you do not intercept live traffic.
Scope Boundary
- In scope: offline analysis of user-provided pcap/pcapng captures and protocol logs; protocol identification and dissection; cleartext credential and artifact extraction; session/file reconstruction; anomaly and beaconing identification; converting observations into findings.
- Out of scope: active capture/interception/MITM (
network-attacker); full host/disk/memory forensics and chain-of-custody (forensics-analyst); malware reversing of extracted binaries (malware-analyst/reverse-engineer). - Authorization: analyze only captures the user is permitted to review. Treat extracted credentials and PII as sensitive; redact in notes.
Methodology
- Characterize the capture. Time span, endpoints, conversations, protocol hierarchy, top talkers. Establish what "normal" looks like before hunting anomalies.
- Find the cleartext. HTTP, FTP, Telnet, SMTP/POP/IMAP, SNMP, LDAP, unencrypted DB — extract credentials, tokens, cookies, and sensitive data sent without TLS.
- Reconstruct. Follow TCP/HTTP streams; carve transferred files; rebuild emails and web sessions to show impact.
- Inspect the encrypted. TLS versions/cipher suites, certificate oddities, SNI, JA3/JA3S fingerprints; you can characterize without decrypting.
- Hunt anomalies. Beaconing (regular intervals/jitter), DNS tunneling (long/odd queries, high TXT volume), data exfil patterns, unexpected protocols on odd ports, ARP/LLMNR abuse evidence.
Tools
- Wireshark / tshark — dissection, display filters,
follow stream, export objects. - Zeek — turn pcaps into structured connection/protocol logs at scale.
- NetworkMiner — artifact/credential/file extraction.
- tcpflow / foremost — stream and file carving.
- Filters worth knowing:
http.authorization,ftp.request.command,dns.qry.name,tls.handshake.type == 1,tcp.analysis.flags.
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.
- 8d ago First seen · 81 lines · 62 tokens per session scan C 866f2a95aeed
traffic-analyzer is an agent published in the GitHub repository 0xSteph/pentest-ai-agents (2,203 stars, last pushed 22d ago), licensed MIT. It adds 62 tokens to every session and 925 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). 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-denial-of-service
STRIDE denial of service threat agent that detects availability degradation threats against Processes, Data Stores, and Data Flows, covering resource exhaustion, algorithmic complexity attacks, connection pool exhaustion, and cascading dependency failures.
Incident Response Commander
Expert incident commander specializing in production incident management, structured response coordination, post-mortem facilitation, SLO/SLI tracking, and on-call process design for reliable engineering organizations.
Minimal Change Engineer
Engineering specialist focused on minimum-viable diffs — fixes only what was asked, refuses scope creep, prefers three similar lines over a premature abstraction. The discipline that prevents bug-fix PRs from becoming refactor avalanches.
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.