railguard-securityagentsonly-scan

Official

Unconditionally run all 12 agents for raw findings.

AuthorNetflix-Skunkworks
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill provides a benchmark control variant that executes all 12 specialized security-analysis subagents unconditionally, enabling raw output collection for comparative benchmarking against orchestrated scans.

Core Features & Use Cases

  • Runs all 12 subagents in parallel without gates, dataflow tracing, FP analysis, or triage enrichment to produce raw findings for benchmarking.
  • Enables direct comparison of coverage, recall, precision, and cost between unconditional-agent scans and gated orchestrated scans.
  • Generates a consistent, reference set of findings suitable for dashboarding and metric tracking.

Quick Start

Execute the raw-agents scan against a repository to collect unfiltered results for benchmarking.

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: railguard-securityagentsonly-scan
Download link: https://github.com/Netflix-Skunkworks/railguard-skill/archive/main.zip#railguard-securityagentsonly-scan

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.