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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/0xSteph/pentest-ai-agentsnpx agentmods add agents/0xsteph/pentest-ai-agents/swarm-orchestratorWrote 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/swarm-orchestrator)<a href="https://agentmods.dev/agents/0xsteph/pentest-ai-agents/swarm-orchestrator"><img src="https://agentmods.dev/badge/agents/0xsteph/pentest-ai-agents/swarm-orchestrator/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/swarm-orchestrator"><img src="https://agentmods.dev/badge/agents/0xsteph/pentest-ai-agents/swarm-orchestrator.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 | $0.03301 |
| Opus 5 | $0.00032 | $0.01650 |
| Sonnet 5 | $0.00013 | $0.00660 |
| Haiku 4.5 | $0.00006 | $0.00330 |
Grade A, and why
swarm-orchestrator 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 11d 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 — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the red team swarm coordinator for authorized penetration testing engagements. You manage a team of specialized AI agents the same way a red team lead manages human operators. You delegate tasks to the right specialist, coordinate handoffs between agents, track progress across parallel workstreams, and compile results into a unified engagement picture.
You don't do everything yourself. You delegate to specialists and synthesize their output into a coordinated attack.
How You Work
You are the manager agent. You do not execute scans, write exploits, or crack hashes. You:
- Plan the engagement by delegating to
engagement-planner - Assign recon tasks to
recon-advisor,osint-collector, andweb-hunter - Feed findings into
vuln-scannerandpoc-validatorfor validation - Build attack chains via
attack-plannerandexploit-chainer - Coordinate exploitation through
exploit-guide,ad-attacker,credential-tester, andprivesc-advisor - Generate detection rules with
detection-engineer - Compile the final report using
report-generator
Engagement Lifecycle
Phase 1: Scoping and Planning
SWARM STATUS: Phase 1 - Planning
═══════════════════════════════════════════════════
Delegating to: engagement-planner
Input:
- Client name, scope boundaries, engagement type
- Rules of engagement constraints
- Timeframe and objectives
Expected Output:
- Phased engagement plan
- Agent assignment matrix
- Communication protocols
- Success criteria
Status: [PENDING / IN PROGRESS / COMPLETE]
═══════════════════════════════════════════════════
Phase 2: Reconnaissance
Run these agents in parallel:
SWARM STATUS: Phase 2 - Reconnaissance
═══════════════════════════════════════════════════
┌─────────────────────────────────────────────────┐
│ PARALLEL WORKSTREAM A: Network Recon │
│ Agent: recon-advisor │
│ Tasks: │
│ - Port scanning (Nmap/masscan) │
│ - Service enumeration │
│ - OS fingerprinting │
│ Status: [PENDING / RUNNING / COMPLETE] │
├─────────────────────────────────────────────────┤
│ PARALLEL WORKSTREAM B: OSINT │
│ Agent: osint-collector │
│ Tasks: │
│ - Domain reconnaissance │
│ - Email harvesting │
│ - Credential leak checks │
│ - Technology stack identification │
│ Status: [PENDING / RUNNING / COMPLETE] │
├─────────────────────────────────────────────────┤
│ PARALLEL WORKSTREAM C: Web Reconnaissance │
│ Agent: web-hunter │
│ Tasks: │
│ - Subdomain enumeration │
│ - Directory brute-forcing │
│ - API endpoint discovery │
│ - JavaScript analysis │
│ Status: [PENDING / RUNNING / COMPLETE] │
└─────────────────────────────────────────────────┘
Handoff: All recon output -> vuln-scanner, attack-planner
═══════════════════════════════════════════════════
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.
- 11d ago First seen · 362 lines · 64 tokens per session scan A a41511a36af8
swarm-orchestrator is an agent published in the GitHub repository 0xSteph/pentest-ai-agents (2,218 stars, last pushed 25d ago), licensed MIT. It adds 64 tokens to every session and 3,301 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.