agents-for — Claude Code command: find pentest agents
The agents-for command for Claude Code filters the pentest-ai-agents catalog by domain or tag and lists matching agents with their access tiers.
MIT ★ 2,482 updated 2026-10-06
.claude/commands/agents-for.mdWhat agents-for does
Pass a domain or tag such as web, cloud, or forensics. The command returns matching agents from its taxonomy, with a short relevance note and a tier. A single input can match more than one tag: ad, for instance, maps to both Active Directory and Windows.
The output also suggests a first command to route work to the top match in Claude Code. Tier 1 agents provide advice. Tier 2 agents can compose and execute commands after scope confirmation; the listed examples include web-hunter and vuln-scanner. Confirm the scope before an agent runs commands.
To install it for Claude Code, place the command file at .claude/commands/agents-for.md. The other installation paths listed are for Codex, GitHub Copilot, and Gemini CLI.
What it helps with
- find pentest agents by security domain
- match a security tag to relevant agents
- check which matching agents can execute commands
Example prompts for the agent
- Find agents for a web application review using the
webtag. - Show agents for an AWS infrastructure assessment with the
cloudfilter. - Find agents for incident investigation using
forensics.
How to install agents-for
Manually: put the files in place
.claude/commands/agents-for.mdCall it with /agents-for. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/agents-for.mdCall it with /prompts:agents-for. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/agents-for.prompt.mdManually: put the files in place
.gemini/commands/agents-for.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about agents-for
How do I install agents-for in Claude Code?
Save the command file at .claude/commands/agents-for.md.
What does agents-for do?
It filters the pentest-ai-agents catalog by a domain or tag, then lists matching agents with their relevance and tier.
Can one filter return agents from multiple tags?
Yes. The ad filter matches both Active Directory and Windows, and the command returns every matching agent.
Source text
agents-for.md · MIT
--- description: List pentest-ai agents relevant to a domain or tag (web, ad, cloud, mobile, recon, etc.). argument-hint: <domain or tag> --- 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.
© 0xSteph · MIT · 0xSteph/pentest-ai-agents