agentic
01Command Claude Code
Full autonomous security workflow.
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.
Command Claude Code
Full autonomous security workflow.
Command Claude Code
Analyze existing SARIF findings with LLM.
Command Claude Code
Add, list, edit, or remove per-function annotations attached to source files.
Command Claude Code
Ask an LLM model a question — developer tool for cross-model queries and diagnosis.
Command Claude Code
Systematic hypothesis-driven security review of coverage gaps.
Command Claude Code
Black-box binary investigation — autonomous ranking, map, parser tracing, fuzz, graph, report, handoff, diagram.
Command Claude Code
CodeQL deep static analysis with dataflow validation.
Command Claude Code
List all available RAPTOR commands.
Command Claude Code
Autonomous crash root-cause analysis for C/C++ bugs.
Command Claude Code
Save a custom approach as a reusable skill.
Command Claude Code
CVE patch discovery — find, acquire, and diff the fix commit for a CVE.
Command Claude Code
CVE → Docker environment builder — agentic build + verify of a vulnerable app at its pre-patch version.
Command Claude Code
Describe a target — language mix, build system, catalog match, target-specific tool gaps, cost estimate. Read-only; no commands executed.
Command Claude Code
Generate Mermaid visual maps from /understand or /validate output directories.
Command Claude Code
Generate exploit proof-of-concepts for vulnerabilities (beta).
Command Claude Code
Dynamic instrumentation via Frida (alpha) - attach or spawn, hook with JS templates, capture runtime events.
Command Claude Code
Binary fuzzing with AFL++ integration.
Command Claude Code
Ghidra RE bridge — attach, import, diff, decompile, export findings.
Command Claude Code
Evidence-backed forensic investigation for GitHub repositories.
Command Claude Code
Generate secure patches for vulnerabilities (beta).
Command Claude Code
Manage RAPTOR projects — create, list, status, coverage, findings, diff, merge, report, clean, export.
Command Claude Code
Dynamic instrumentation via Frida (alpha) - attach or spawn, hook with JS templates, capture runtime events.
Command Claude Code
Binary fuzzing with AFL++ integration (alias for /fuzz).
Command Claude Code
Software Composition Analysis — find vulnerable dependencies, gate CI, fix and pin.
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: