H-mmer

H-mmer/pentest-agents

Agent Claude Code

XSS specialist covering reflected (H1 #60), stored (H1 #61), and DOM (H1 #62). Dispatcher passes subtype — 'reflected', 'stored', or 'dom' — in the task; falls back to inference from target. Use for parameter reflection, persisted inputs (comments/profiles/uploads/filenames), or client-side source→sink analysis.

H-mmer/pentest-agents

Agent Claude Code

XXE specialist (H1 #63). Use for testing XML parsing endpoints, file upload processors, SOAP services, SVG handlers, and any feature accepting XML input.

H-mmer/pentest-agents

Hook Claude Code

Runs when a subagent finishes, executing cost_hook.py and chain_pressure_hook.py via uv (2 commands). From H-mmer/pentest-agents.

H-mmer/pentest-agents

Hook Claude Code

Runs when the agent finishes a response, executing cost_hook.py via uv. From H-mmer/pentest-agents.

H-mmer/pentest-agents

Hook Claude Code

Runs when a session starts, running an inline shell check. From H-mmer/pentest-agents.

H-mmer/pentest-agents

Hook Claude Code

Runs before the agent uses a tool for Bash, Write and Edit tool calls, executing scope_hook.py, file_path_guard.py, cvss_version_guard.py and validity_guard.py via uv (4 commands). From H-mmer/pentest-agents.

H-mmer/pentest-agents

Hook Claude Code

Runs after a tool call finishes for Bash tool calls, executing cost_hook.py. From H-mmer/pentest-agents.

H-mmer/pentest-agents

Settings file Claude Code

Agent settings declaring 5 hook events (SubagentStop, Stop, SessionStart, PreToolUse) and 66 allowed tools.

H-mmer/pentest-agents

Skill Claude CodeCodex

Analyze recon output with AI to suggest high-value targets and attack strategies. Usage: /analyze.

H-mmer/pentest-agents

Skill Claude CodeCodex

Autonomous hunt orchestrator. INSATIABLE in --autonomous mode: enforces an EXHAUSTION CONTRACT (26 canonical hunter classes, surface probe A-I, depth-engine ≥25 attempts/class, wall-clock floor 90 min/target, PRE-COMPLETION GATE before any summary). No early stops, no clarifying questions, no auxiliary-agent…

H-mmer/pentest-agents

Skill Claude CodeCodex

Manage the engagement brain. Subcommands: 'init' to set up, 'brief ' for pre-flight, 'status' for overview, 'exhausted [target]' to see dead ends.

H-mmer/pentest-agents

Skill Claude CodeCodex

Build deep exploit chains — dispatches chain-builder agent. Given bug A, recursively walks the chain graph. Usage: /chain (then describe bug A).

H-mmer/pentest-agents

Skill Claude CodeCodex

Run the finding correlation engine to discover attack chains from individual findings.

H-mmer/pentest-agents

Skill Claude CodeCodex

Show cost tracking and ROI for this engagement.

H-mmer/pentest-agents

Skill Claude CodeCodex

Check if a vulnerability has already been reported. Searches platform hacktivity + local findings. Usage: /dupcheck e.g. /dupcheck XSS in search endpoint.

H-mmer/pentest-agents

Skill Claude CodeCodex

Full security assessment with brain coordination. Multi-phase, skips known-exhausted areas, builds on prior knowledge.

H-mmer/pentest-agents

Skill Claude CodeCodex

Active vulnerability hunting on a target. Loads scope, reads brain, detects tech stack, runs targeted tests with concrete payloads. Usage: /hunt target.com [--vuln-class idor|xss|ssrf|sqli|ssti|oauth|rce|race|graphql|upload|business-logic|llm-ai].