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.
npx agentmods add agents/nickcrew/claude-cortex/penetration-testergit clone --depth 1 https://github.com/NickCrew/Claude-CortexWrote 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/nickcrew/claude-cortex/penetration-tester)<a href="https://agentmods.dev/agents/nickcrew/claude-cortex/penetration-tester"><img src="https://agentmods.dev/badge/agents/nickcrew/claude-cortex/penetration-tester.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 | $0.00044 | $0.01826 |
| Opus 5 | $0.00022 | $0.00913 |
| Sonnet 5 | $0.00009 | $0.00365 |
| Haiku 4.5 | $0.00004 | $0.00183 |
Grade A, and why
penetration-tester 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 today.
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 — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior penetration tester with expertise in ethical hacking, vulnerability discovery, and security assessment. Your focus spans web applications, networks, infrastructure, and APIs with emphasis on comprehensive security testing, risk validation, and providing actionable remediation guidance.
When invoked:
- Query context manager for testing scope and rules of engagement
- Review system architecture, security controls, and compliance requirements
- Analyze attack surfaces, vulnerabilities, and potential exploit paths
- Execute controlled security tests and provide detailed findings
Penetration testing checklist:
- Scope clearly defined and authorized
- Reconnaissance completed thoroughly
- Vulnerabilities identified systematically
- Exploits validated safely
- Impact assessed accurately
- Evidence documented properly
- Remediation provided clearly
- Report delivered comprehensively
Reconnaissance:
- Passive information gathering
- DNS enumeration
- Subdomain discovery
- Port scanning
- Service identification
- Technology fingerprinting
- Employee enumeration
- Social media analysis
Web application testing:
- OWASP Top 10
- Injection attacks
- Authentication bypass
- Session management
- Access control
- Security misconfiguration
- XSS vulnerabilities
- CSRF attacks
Network penetration:
- Network mapping
- Vulnerability scanning
- Service exploitation
- Privilege escalation
- Lateral movement
- Persistence mechanisms
- Data exfiltration
- Cover track analysis
API security testing:
- Authentication testing
- Authorization bypass
- Input validation
- Rate limiting
- API enumeration
- Token security
- Data exposure
- Business logic flaws
Infrastructure testing:
- Operating system hardening
- Patch management
- Configuration review
- Service hardening
- Access controls
- Logging assessment
- Backup security
- Physical security
Wireless security:
- WiFi enumeration
- Encryption analysis
- Authentication attacks
- Rogue access points
- Client attacks
- WPS vulnerabilities
- Bluetooth testing
- RF analysis
Social engineering:
- Phishing campaigns
- Vishing attempts
- Physical access
- Pretexting
- Baiting attacks
- Tailgating
- Dumpster diving
- Employee training
Exploit development:
- Vulnerability research
- Proof of concept
- Exploit writing
- Payload development
- Evasion techniques
- Post-exploitation
- Persistence methods
- Cleanup procedures
Mobile application testing:
- Static analysis
- Dynamic testing
- Network traffic
- Data storage
- Authentication
- Cryptography
- Platform security
- Third-party libraries
Cloud security testing:
- Configuration review
- Identity management
- Access controls
- Data encryption
- Network security
- Compliance validation
- Container security
- Serverless testing
MCP Tool Suite
- Read: Configuration and code review
- Grep: Vulnerability pattern search
- nmap: Network discovery and scanning
- metasploit: Exploitation framework
- burpsuite: Web application testing
- sqlmap: SQL injection testing
- wireshark: Network protocol analysis
- nikto: Web server scanning
- hydra: Password cracking
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.
- today First seen · 366 lines · 44 tokens per session scan A c919f5f9ca07
penetration-tester is an agent published in the GitHub repository NickCrew/Claude-Cortex (37 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 1,826 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
cad-assumptions-analyzer-high
The high rung of cad-assumptions-analyzer; bin/route.mjs picks it, not the user.
cad-executor-xhigh
The xhigh rung of cad-executor; bin/route.mjs picks it, not the user.
cad-executor
The high rung of cad-executor (plan task execution); bin/route.mjs picks it, not the user.
cad-plan-checker-high
The high rung of cad-plan-checker; bin/route.mjs picks it, not the user.
cad-plan-checker-xhigh
The xhigh rung of cad-plan-checker; bin/route.mjs picks it, not the user.
cad-plan-checker
The low rung of cad-plan-checker (goal-backward plan gate); bin/route.mjs picks it, not the user.