mantis-researcher

Perform triage and deep-dive security reviews of source code files.

731|84|Updated Jun 15, 2026
One-click install
npx skills add https://github.com/google/mantis --skill mantis-researcher
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mantis-researcher
Source: https://github.com/google/mantis/tree/main/mantis-researcher
Command: npx skills add https://github.com/google/mantis --skill mantis-researcher

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill addresses the challenge of performing consistent, scalable, and deep-dive security audits on large codebases by automating the triage and analysis of potential vulnerabilities.

Core Features & Use Cases

  • Wave-Based Swarm Analysis: Orchestrates rapid triage followed by deep-dive audits to maximize throughput and context efficiency.
  • Snapshot-Aware Auditing: Ensures all sub-agents operate on an immutable, pinned code snapshot to maintain consistency across parallel analysis tasks.
  • Use Case: Use this skill to perform a comprehensive security review of a new feature branch, identifying potential memory safety issues or logic flaws across multiple files while maintaining a clear audit trail of findings.

Quick Start

Invoke the mantis-researcher skill to begin an automated security audit of the current codebase based on the existing plan.

Frequently Asked Questions about mantis-researcher

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate deep-dive security code auditing for a large codebase?

Automate deep-dive security code auditing by orchestrating wave-based swarm analysis to perform rapid triage and identify memory safety, logical correctness, and interface violations across parallel sub-agent investigations.

What is snapshot-aware auditing and when do I need it for vulnerability analysis?

Snapshot-aware auditing pins an immutable code snapshot to ensure consistency across parallel analysis tasks, needed when running exhaustive call-site analysis and contract verification across multiple sub-agents.

Can I use automated code review to find memory safety and logical correctness issues?

Automated code review can find memory safety and logical correctness issues by integrating structural indices and threat models to provide exhaustive call-site analysis and contract verification.

What's the best way to perform consistent security reviews across parallel code analysis tasks?

Perform consistent security reviews across parallel tasks by operating on pinned code snapshots and orchestrating wave-based swarm analysis to maximize throughput and maintain context efficiency during vulnerability generation.

Does automated static analysis work with threat models for interface violation detection?

Automated static analysis works with threat models to detect interface violations by integrating structural indices for exhaustive call-site analysis and contract verification during deep-dive security reviews.