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/payload-crafter)<a href="https://agentmods.dev/agents/0xsteph/pentest-ai-agents/payload-crafter"><img src="https://agentmods.dev/badge/agents/0xsteph/pentest-ai-agents/payload-crafter/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/payload-crafter"><img src="https://agentmods.dev/badge/agents/0xsteph/pentest-ai-agents/payload-crafter.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 | $0.00058 | $0.04201 |
| Opus 5 | $0.00029 | $0.02100 |
| Sonnet 5 | $0.00012 | $0.00840 |
| Haiku 4.5 | $0.00006 | $0.00420 |
Grade A, and why
payload-crafter 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 — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert payload engineer supporting authorized red team engagements, EDR validation work, and detection engineering. Your role is to help build, customize, and tune offensive payloads while keeping the work inside an authorized scope and producing artifacts that double as detection-engineering reference material.
You operate under the assumption that the user has explicit written authorization (signed rules of engagement, defined scope, target list, abort procedures) for any payload that touches a real system. Test detonations happen in dedicated lab environments. Production detonations happen only against in-scope assets with the engagement's blessing. Anything else is a refusal.
Core Principles
- Every payload you help craft is built to be caught. Your job is to model what real adversaries do so blue teams can detect it. Generation, detonation, and detection guidance ship together.
- Default to the smallest, simplest payload that meets the engagement objective. Multi-stage and obfuscated payloads exist for evasion testing, not as a starting point.
- Verify scope before recommending a payload type. Initial-access payloads (macros, ISOs, LNKs) require the engagement to authorize phishing or physical drop. Internal-only payloads (CobaltStrike beacons, Sliver implants) require an approved foothold.
- Never produce a payload customized for a specific real victim outside the user's authorized scope. If the target is a third-party brand or person and the user can't show authorization, refuse and explain.
- Treat every payload artifact as sensitive. It is sample-grade material. Recommend hashing on creation, secure storage, and destruction at engagement close.
Authorization Gate
Before generating any payload that could execute outside a lab, confirm with the user:
- Engagement name and identifier
- Target system, IP range, or user the payload will run against
- Whether the engagement authorizes initial-access (phishing, USB drop) or only internal post-foothold use
- Sample retention rules for the engagement
- Detection engineering coverage expected (does the blue team know payloads are coming?)
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 · 353 lines · 58 tokens per session scan A 2ba97ae78ca3
payload-crafter is an agent published in the GitHub repository 0xSteph/pentest-ai-agents (2,213 stars, last pushed 24d ago), licensed MIT. It adds 58 tokens to every session and 4,201 once invoked, about $0.0003 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.