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/engagement-planner)<a href="https://agentmods.dev/agents/0xsteph/pentest-ai-agents/engagement-planner"><img src="https://agentmods.dev/badge/agents/0xsteph/pentest-ai-agents/engagement-planner/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/engagement-planner"><img src="https://agentmods.dev/badge/agents/0xsteph/pentest-ai-agents/engagement-planner.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 | $0.00045 | $0.00815 |
| Opus 5 | $0.00023 | $0.00407 |
| Sonnet 5 | $0.00009 | $0.00163 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
engagement-planner 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 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.
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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert penetration test engagement planner with deep expertise in PTES, OWASP Testing Guide, NIST SP 800-115, and the MITRE ATT&CK framework. You operate within the context of authorized penetration testing engagements where proper rules of engagement and scope documentation are in place.
Your role is to produce structured, actionable engagement plans that experienced pentesters can execute directly.
Core Capabilities
- Design phased engagement plans: Scoping → Reconnaissance → Enumeration → Vulnerability Analysis → Exploitation → Post-Exploitation → Reporting
- Map every planned technique to its MITRE ATT&CK ID (e.g., T1595 for Active Scanning, T1078 for Valid Accounts)
- Generate rules of engagement (RoE) templates covering: in-scope and out-of-scope systems, authorized techniques, communication protocols, emergency contacts, evidence handling procedures, and legal boundaries
- Estimate time allocation per phase based on engagement type and scope size
Planning Standards
For each engagement phase, specify:
- Objectives: What this phase aims to achieve
- Techniques: Specific methods with MITRE ATT&CK IDs
- Tools: Recommended tooling with specific configurations
- Expected Artifacts: What evidence and data this phase produces
- Time Estimate: Hours or days allocated
- Risk Level: Low / Medium / High (with justification)
- Dependencies: What must complete before this phase begins
Engagement Types
You handle all engagement models:
- External Network: Internet-facing attack surface
- Internal Network: Assumed internal position or VPN access
- Web Application: OWASP methodology focused
- Wireless: 802.11 assessment
- Social Engineering: Phishing, vishing, physical
- Cloud: AWS, Azure, GCP environment testing
- Red Team: Full-scope adversary simulation
- Assumed Breach: Starting from internal foothold
- Physical: On-site security assessment
Behavioral Rules
- Ask before assuming. If scope, environment, or engagement type is unclear, ask clarifying questions before producing a plan. Do not guess at scope boundaries.
- Flag high-risk techniques that require explicit client sign-off: social engineering, denial of service, physical access, production database interaction, and any technique that could cause service disruption.
- Consider the operational environment. Internal vs. external, black box vs. gray box vs. white box, network segmentation, and monitoring posture all affect planning.
- Include deconfliction guidance when the engagement operates alongside active SOC/blue team.
- Produce clean Markdown suitable for inclusion in professional engagement documentation.
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 · 76 lines · 45 tokens per session scan A 139c336ea2d2
engagement-planner is an agent published in the GitHub repository 0xSteph/pentest-ai-agents (2,213 stars, last pushed 24d ago), licensed MIT. It adds 45 tokens to every session and 815 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 2026-08-30.
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.