agents-for
01Command
List pentest-ai agents relevant to a domain or tag (web, ad, cloud, mobile, recon, etc.).
127 tagged cybersecurity, measured the same way as everything else here.
Browse within: ai-security 58devsecops 52agentic-security 30attack-trees 30bug-bounty 18llm-security 18open-source 18appsec 17exploit-validation 15AI Safety 13active-directory 13active-directory-security 13devtools 13docker 13
Command
List pentest-ai agents relevant to a domain or tag (web, ad, cloud, mobile, recon, etc.).
Command
Update the project memory with what was accomplished in this session.
Command
Recommend the right pentest-ai agent and concrete next steps for a freeform task description.
Command
Command "recon" from Zyrexnn/Cybermes, covering /recon, what this does, usage, steps and step 1: subdomain enumeration.
Command
Command "report" from Zyrexnn/Cybermes, covering /report, pre-conditions, usage, what this generates and platform selection.
Command
Command "web3-audit" from Zyrexnn/Cybermes, covering /web3-audit, usage, step 0: pre-dive kill signals, find accounting variables and find all early returns in critical functions.
Command
Define the attack profile for an engagement — select which attack categories and skills to use. Saves to .pentest-attacks.json. If run before /pentest:pentest, the orchestrator will respect the selection. If run standalone, does not launch a pentest.
Command
Define or update engagement scope — saves scope to disk without launching a pentest. Can be run before or during an engagement. If a pentest is active and the target changes drastically, warns the operator and suggests a new engagement.
Command
Activate pentest mode — displays ASCII art, configures session isolation, collects engagement scope, then OWNS the engagement: pre-flight, recon, planning (via the pentester-orchestrator planner), executor dispatch, a time-budget quota loop, aggregation, and report generation.
Command Claude Code
Execute implementation with Architect checkpoints at critical phases - Streamlined v2.
Command Claude Code
Create PRD with Triad governance (PM + Architect + Team-Lead sign-offs) - Streamlined v2.
Command Claude Code
Generate tasks with triple sign-off (PM + Architect + Team-Lead) - Streamlined v2.
Command Claude Code
Generate 50-100 ad copy variants from pain point research, then create renderable ad images.
Command Claude Code
Convert LinkedIn post engagers (likes, comments) into qualified leads and send personalized cold emails.
Command Claude Code
Find relevant podcasts, verify host emails, and send personalized cold outreach to get booked as a guest.
Evaluris-Solutions/claude-active-directory
Command
Active Directory offensive phase — credential attacks (spray if allowed), AS-REP and Kerberoast workflows, NTLM relay opportunities, delegation abuse paths, ACL-based escalation, AD CS template abuse, lateral movement within ROE. Usage: /hunt corp.local.
Evaluris-Solutions/claude-active-directory
Command
Active Directory reconnaissance — DNS SRV/LDAP DC discovery, LDAP user and group enumeration, Kerberos pre-auth and AS-REP candidates, SPN discovery for Kerberoasting, SMB signing and null session policy, password policy, trust relationships, BloodHound/SharpHound collection prep. Requires ROE. Usage: /recon…
Evaluris-Solutions/claude-active-directory
Command
Rules of engagement — verify authorized domains, DCs, subnets, accounts, destructive actions, and exclusions before testing. Usage: /scope or /scope corp.local.
Command Claude Code
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
Command Claude Code
Execute the implementation planning workflow using the plan template to generate design artifacts.
Command Claude Code
Create or update the feature specification from a natural language feature description.
Command
Pre-merge security gate on the current branch — runs secrets, SAST and dep-vuln checks on changed code, honors documented exceptions, returns a hard PASS/FAIL verdict.
Command
Hypothesis-driven threat-hunt session scaffolding — scope, hypothesis formulation, data-source binding, query handoff to siem-query, IOC input via ioc-hunter, and structured writeup with findings and handoffs to detection-engineer.
Command Claude Code
Run cs-security-analyst (AT workflow) against the Perfect Storm 8-vector crisis scenario and produce a 12-check mock comparison scorecard.