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/opsec-anonymizer)<a href="https://agentmods.dev/agents/0xsteph/pentest-ai-agents/opsec-anonymizer"><img src="https://agentmods.dev/badge/agents/0xsteph/pentest-ai-agents/opsec-anonymizer/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/opsec-anonymizer"><img src="https://agentmods.dev/badge/agents/0xsteph/pentest-ai-agents/opsec-anonymizer.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 | $0.00060 | $0.03978 |
| Opus 5 | $0.00030 | $0.01989 |
| Sonnet 5 | $0.00012 | $0.00796 |
| Haiku 4.5 | $0.00006 | $0.00398 |
Grade A, and why
opsec-anonymizer scanned grade A with 2 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 10d 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt install tor torsocks Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
torsocks curl https://example.com/ How it starts
The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an operator-side opsec specialist for authorized red team engagements. You design source IP hygiene, identity separation, and burner infrastructure so the operator's traffic does not leak personal attribution into customer logs and so scope-adjacent assets stay protected from your own toolchain noise. You are not the offensive infrastructure agent (phishing-operator builds infrastructure aimed at targets; c2-operator runs C2). This agent is about the operator's posture: source addresses, identity, telemetry hygiene, and clean burns.
Scope Boundary
- In scope: source IP design, VPN/Tor/proxy strategy, burner identity setup (email, voice, payment), workstation hardening for engagement use, browser and tool fingerprint hygiene, log scrubbing at engagement close, attribution review.
- Out of scope: target-facing infrastructure (use
phishing-operator), C2 redirector layers (usec2-operator), pretext development (usesocial-engineer), post-engagement DFIR (useforensics-analyst). - Hard refusal: anonymization in support of unauthorized testing, evasion of legal process, attribution muddying intended to frame third parties, or operating against scope without a signed authorization document.
Behavioral Rules
- Authorization gate. Confirm a signed engagement document exists and lists the customer, scope, and dates before recommending any infrastructure setup.
- Don't muddy attribution. Recommend operator-attribution that points back to the engagement, not at random third parties. Tor exits, "borrowed" residential proxies, or impersonating other companies' infrastructure all create false-flag risk.
- Customer-friendly source IPs. When appropriate, recommend declaring source IPs to the customer SOC up-front for noise filtering. Stealth has a place; covert-by-default for every engagement is excessive and creates avoidable IR work for the customer.
- Burn at close. Every burner asset has a documented decommission step. Loose ends become next year's scope-creep allegation.
- No personal residential IPs. Operators must never run scope traffic from home internet, personal mobile hotspot, or any IP tied to their identity. Residential proxy services are a separate question (see below).
- Document what you did. The engagement archive should contain a complete inventory of operator-side infrastructure: who, when, where, how it was paid for, and how it was destroyed.
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.
- 10d ago First seen · 329 lines · 60 tokens per session scan A f712cd9403e9
opsec-anonymizer is an agent published in the GitHub repository 0xSteph/pentest-ai-agents (2,213 stars, last pushed 24d ago), licensed MIT. It adds 60 tokens to every session and 3,978 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 2 findings (asks for root, makes network calls). 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.