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/commands/0xsteph/pentest-ai-agents/agents-for)<a href="https://agentmods.dev/commands/0xsteph/pentest-ai-agents/agents-for"><img src="https://agentmods.dev/badge/commands/0xsteph/pentest-ai-agents/agents-for.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.00680 |
| Opus 5 | $0.00012 | $0.00340 |
| Sonnet 5 | $0.00005 | $0.00136 |
| Haiku 4.5 | $0.00002 | $0.00068 |
Grade A, and why
agents-for 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 8d 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.
What it actually says
Filter the pentest-ai agent catalog by the domain or tag below and return a focused list.
Filter: $ARGUMENTS
Match against this taxonomy. A single argument may match multiple tags (e.g., "ad" matches both "active-directory" and "windows"). Return every agent that matches.
recon → recon-advisor, osint-collector, vuln-scanner
osint → osint-collector
web → web-hunter, api-security, bug-bounty, bizlogic-hunter, vuln-scanner
api → api-security, web-hunter, bug-bounty
ad / active-directory / windows → ad-attacker, credential-tester, privesc-advisor, recon-advisor
cloud / aws / azure / gcp → cloud-security, cicd-redteam
mobile / android / ios → mobile-pentester, reverse-engineer
wireless / wifi / bluetooth → wireless-pentester
social / phishing / se → social-engineer, phishing-operator
exploit / exploitation → exploit-guide, exploit-chainer, poc-validator, payload-crafter
payload / shellcode → payload-crafter, malware-analyst, reverse-engineer
re / reverse / reversing → reverse-engineer, malware-analyst, ctf-solver
malware / ir → malware-analyst, forensics-analyst, detection-engineer
forensics / dfir → forensics-analyst, malware-analyst
detection / blue / siem / sigma → detection-engineer, threat-modeler
threat / threat-model / stride → threat-modeler
stig / compliance / hardening → stig-analyst
priv-esc / privilege-escalation → privesc-advisor
creds / credentials / passwords / hash / cracking → credential-tester
business-logic / bizlogic → bizlogic-hunter
ci / cd / devsecops / pipeline → cicd-redteam
plan / planning / scope / roe → engagement-planner
report / reporting / writeup → report-generator
ctf / htb / hackthebox / tryhackme → ctf-solver
swarm / multi-agent / orchestrate → swarm-orchestrator
Output format:
**Agents for "<filter>"**:
| Agent | Why it matches | Tier |
|-------|----------------|------|
| <name> | <one-line relevance> | 1 or 2 |
| <name> | <one-line relevance> | 1 or 2 |
**Suggested first command** (in your shell):
> "<a one-line prompt the user can paste into Claude Code that will route to the top match>"
Tier 1 = advisory only. Tier 2 = can compose and execute commands with scope confirmation.
Tier 2 agents: recon-advisor, vuln-scanner, web-hunter, ad-attacker, exploit-chainer, poc-validator, bizlogic-hunter.
If the filter doesn't match anything in the taxonomy, return the closest matches, list the unmatched filter, and suggest 2–3 nearby tags from the taxonomy above.
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.
- 8d ago First seen · 60 lines · 24 tokens per session scan A 50c992b51f72
agents-for is a command published in the GitHub repository 0xSteph/pentest-ai-agents (2,203 stars, last pushed 23d ago), licensed MIT. It adds 24 tokens to every session and 680 once invoked, about $0.0001 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 commands, from other repositories
bypass-403
Probe a 403/401 endpoint with the most-paid bypass tricks (header injection, path encoding, method swap, WAF fingerprint, vendor-specific). Wraps byp4xx when installed; otherwise runs a built-in matrix of 38+ techniques. Usage: /bypass-403 | /bypass-403 -l.
autopilot
Run autonomous hunt loop on a target — scope check → recon → rank surface → hunt → validate → report with configurable checkpoints. Usage: /autopilot target.com [--paranoid|--normal|--yolo].
triage
Quick 7-Question Gate triage on a finding before writing a report. Kills N/A submissions before they happen. Faster than /validate — for quick go/no-go decisions. Usage: /triage.
token-scan
Meme coin and token security scan — checks for rug pull vectors (hidden mint, honeypot, fee manipulation, LP lock bypass, authority retention, bonding curve exploits, fake renounce, sandwich amplification). Manual 8-class grep audit (with an optional automated scanner if present). Usage: /token-scan [--chain solana].
memory-gc
Inspect or rotate hunt-memory JSONL files (audit.jsonl, patterns.jsonl, journal.jsonl). Caps file size and keeps N rotated backups so memory does not grow unbounded.
secrets-hunt
Hunt leaked credentials in a filesystem path, git history, JS bundles from a recon run, or an entire GitHub org. Wraps trufflehog (verifies live keys against issuer APIs), noseyparker (fast on huge histories), and gitleaks (default rule pack). Falls back to a regex grep if no scanner is installed. Usage: /secrets-hunt…