raptor-scan
25Command Claude Code
Scan a repository with Semgrep and CodeQL (alias for /scan).
Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating rules, sub-agents, and skills, and orchestrating security tool usage, we configure the agent for adversarial thinking, and perform research or attack/defense operations.
This repository also configures its own agents. See what raptor tells them →
Command Claude Code
Scan a repository with Semgrep and CodeQL (alias for /scan).
Command Claude Code
Web application security scanner (alpha) (alias for /web).
Command Claude Code
RAPTOR security testing assistant.
Command Claude Code
Unified review — query all layers (journal, coverage, context-map, annotations).
Command Claude Code
SAGE persistent memory: status, recall, browse, store, manage.
Command Claude Code
Software Composition Analysis — find vulnerable dependencies, gate CI, fix and pin.
Command Claude Code
Scan a repository with Semgrep and CodeQL.
Command Claude Code
Inspect per-model reliability across decision classes; answer natural-language questions about model competence.
Command Claude Code
Project threat model — show, initialise, lint, diff, report, build, refresh, export.
Command Claude Code
Map attack surface, trace data flows, hunt vulnerability variants.
Command Claude Code
Validate that vulnerability findings are real, reachable, and exploitable.
Command Claude Code
Show the running RAPTOR framework version.
Command Claude Code
Web application security scanner (alpha).
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: