Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized penetration testing plan engagements, analyze recon, research exploits, build detections, audit STIGs, and write reports.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
pentest-ai-agents is a collection of 35 Claude Code subagents that turn Claude into an offensive security research assistant. Each agent carries deep domain knowledge in a specific area: recon, web, Active Directory, cloud, mobile, wireless, social engineering, payload crafting, reverse engineering, exploit chaining, detection engineering, forensics, and more.
Install the agent files. Open Claude Code. Describe your task. Claude routes to the right specialist automatically.
No servers, no Python deps, no setup beyond copying files.
Tightened scope guard: explicit hard-refusal list in _scope-guard.md covers DoS, mass scanning, unattended worms, false-flag operations, safety-of-life systems.
Findings DB v2: vulns.tool_used column for filtering findings by the tool that produced them; new indexes on cve and tool_used. Existing engagements migrate forward via db/migrate.sh.
Agent map diagram: visual flow from recon to closure mapped to agent names (see below).
Agent Map
flowchart LR
classDef plan fill:#1a2a4a,stroke:#5a7ab8,color:#eaf0ff
classDef recon fill:#1a3a2a,stroke:#5ab87a,color:#eaffea
classDef exploit fill:#3a1a1a,stroke:#b85a5a,color:#ffeaea
classDef post fill:#3a2a1a,stroke:#b8895a,color:#fff0ea
classDef defense fill:#1a3a3a,stroke:#5ab8b8,color:#eaffff
classDef report fill:#2a1a3a,stroke:#895ab8,color:#f0eaff
EP[engagement-planner]:::plan
OA[opsec-anonymizer]:::plan
TM[threat-modeler]:::plan
OS[osint-collector]:::recon
RA[recon-advisor]:::recon
VS[vuln-scanner]:::recon
WH[web-hunter]:::exploit
AS[api-security]:::exploit
BL[bizlogic-hunter]:::exploit
BB[bug-bounty]:::exploit
AD[ad-attacker]:::exploit
CS[cloud-security]:::exploit
MP[mobile-pentester]:::exploit
WP[wireless-pentester]:::exploit
LR[llm-redteam]:::exploit
SE[social-engineer]:::exploit
PO[phishing-operator]:::exploit
CT[ctf-solver]:::exploit
CR[credential-tester]:::exploit
PV[poc-validator]:::exploit
EG[exploit-guide]:::exploit
EC[exploit-chainer]:::exploit
AP[attack-planner]:::exploit
PC[payload-crafter]:::exploit
RE[reverse-engineer]:::exploit
PE[privesc-advisor]:::post
CB[container-breakout]:::post
C2[c2-operator]:::post
CI[cicd-redteam]:::post
SO[swarm-orchestrator]:::post
DE[detection-engineer]:::defense
FA[forensics-analyst]:::defense
MA[malware-analyst]:::defense
SA[stig-analyst]:::defense
RG[report-generator]:::report
EP --> OA --> OS
EP --> TM
OS --> RA --> VS
VS --> WH & AS & BL & BB & AD & CS & MP & WP & LR
SE --> PO
BB --> WH
PO --> PC --> C2
AD --> CR
AD --> PE
CS --> CB
CB --> PE
WH --> PV
AS --> PV
PV --> EC --> AP
EC --> EG
PC --> RE
RE --> MA
AP --> SO
C2 --> DE
SO --> RG
DE --> FA
MA --> RG
SA --> RG
CT -.solo.-> RG
CI -.pipeline.-> SO
Tier 1 (advisory) agents are routable from any task. Tier 2 (execution-capable) agents require a declared scope and live in the offensive operations cluster.
That's it. The script clones the repo to a temp dir, copies the agents to ~/.claude/agents/, and exits. Idempotent: safe to re-run for updates.
Then open Claude Code:
"Plan an internal network pentest for a 500-endpoint AD environment with a 2-week window."
Claude routes to the engagement planner agent and produces a phased plan with MITRE ATT&CK mappings.
Prefer to clone first?
git clone https://github.com/0xSteph/pentest-ai-agents.git
cd pentest-ai-agents && ./install.sh --global
Other install options:
./install.sh --project # Install for current project only
./install.sh --global --lite # Use Haiku for advisory agents (lower cost)
./install.sh --tools # Install underlying CLI tools (nmap, nuclei, ffuf, etc.)
./install.sh --help # All options
See INSTALL.md for step-by-step instructions, including first-time Claude Code setup.
Cheatsheet
Quick interactions once installed:
| Command | What It Does |
|---------|--------------|
| /recommend "phish a small SaaS team's IT department" | Picks the right agent and gives concrete next commands |
| /agents-for web | Lists every agent relevant to web testing (web-hunter, api-security, bug-bounty, bizlogic-hunter) |
| /agents-for cloud | Cloud-specific agents (cloud-security, cicd-redteam) |
| db/doctor.sh | Audits which underlying CLI tools you have, grouped by agent. Shows ✔/✘ and install hints. |
| db/doctor.sh --agent ad-attacker | Audit just the AD tooling stack |
| db/doctor.sh --json | Machine-readable output for piping into a script |
| install.sh --tools | Install the underlying tools via your package manager + pipx/go/cargo |
| findings.sh init <id> | Start a new engagement (persistent SQLite findings DB) |
| findings.sh stats | Engagement progress |
| findings.sh export | Full JSON export |
| bash handoff.sh | Markdown handoff report between sessions |
In Claude Code, just describing your task routes automatically:
"Plan an internal pentest for a 500-endpoint AD environment, 2-week window."
"I have a domain user, where do I look first in BloodHound?"
"Convert this SharpHound EXE into shellcode for an EDR test, with detection content."
"Reverse this firmware image and tell me what the cryptographic protocol looks like."
"Run a phishing simulation against acme-corp.com, set up GoPhish + Evilginx infrastructure."
Coverage
What the agents drive. Categories map to the same surface real adversaries operate across:
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
