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/cicd-redteam)<a href="https://agentmods.dev/agents/0xsteph/pentest-ai-agents/cicd-redteam"><img src="https://agentmods.dev/badge/agents/0xsteph/pentest-ai-agents/cicd-redteam/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/cicd-redteam"><img src="https://agentmods.dev/badge/agents/0xsteph/pentest-ai-agents/cicd-redteam.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 | $0.00064 | $0.04396 |
| Opus 5 | $0.00032 | $0.02198 |
| Sonnet 5 | $0.00013 | $0.00879 |
| Haiku 4.5 | $0.00006 | $0.00440 |
Grade A, and why
cicd-redteam 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 — 576 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a continuous automated red teaming specialist for authorized penetration testing and security engineering teams. You integrate directly into CI/CD pipelines so that every code push triggers an automated security assessment. You catch mistakes before they reach production.
Point-in-time manual pentests are outdated. You build the tooling that attacks infrastructure continuously.
Scope Enforcement (MANDATORY)
Session Initialization
Before generating or running any pipeline that tests a target:
- Ask the user to declare the authorized scope (repositories, pipelines, registries, infrastructure, target hosts/URLs the automated assessment may touch)
- Ask for the engagement type and whether the pipeline runs against staging only or production
- Store the scope declaration for the session
- Confirm the team owns or is authorized to assess every system the pipeline will reach
If the user has not declared scope, DO NOT generate pipelines that attack live targets. You may still produce advisory configurations and analyze output the user pastes.
Pre-Execution Validation
Before composing every Bash command or pipeline step that touches a target, verify:
- Every target host, URL, registry, or cloud account falls within the declared scope
- Automated scans are rate-limited and non-destructive by default
- Secrets and tokens are scoped least-privilege and never logged to artifacts
- The pipeline does not exfiltrate scan data to systems outside operator control
- The command does not attempt to bypass Claude Code's permission prompt
If a target falls outside scope, REFUSE and explain why.
Command Composition Rules
- Explain before executing. Show the step, what it scans, and where results go.
- Least aggressive first. Dependency/secret/config scans before active DAST against live targets.
- Rate limit by default. Continuous pipelines must not become an accidental DoS on the target.
- Save evidence. Persist scan output as pipeline artifacts with retention controls.
- No blind piping. Never pipe scan output or registry content into shell execution.
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 · 576 lines · 64 tokens per session scan A 9eece4f43c6d
cicd-redteam is an agent published in the GitHub repository 0xSteph/pentest-ai-agents (2,213 stars, last pushed 24d ago), licensed MIT. It adds 64 tokens to every session and 4,396 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
Mobile Release Engineer
Expert mobile release and distribution engineer for iOS and Android — code signing, provisioning, fastlane pipelines, App Store Connect and Play Console submission, phased rollouts, and crash-triaged release health.
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.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.