red-agent

Adversarial red team analysis of branch comparison for PR review.

Adversarial red team analysis of a diff file for PR review.

Adversarial red team analysis of staged git changes for PR review.

Adversarial red team analysis of working directory changes for PR review.

Red team analysis with interactive fix selection. Identifies issues, generates fix options, and lets you choose which fixes to apply.

You orchestrate the red team analysis with fix planning. Your role is to:

You orchestrate the end-to-end fix execution for red team findings. Your role is to:

Lightweight agent that checks if PAL MCP is available and lists available models.

You are the PR ANALYSIS COORDINATOR - the firewall between the main session and adversarial PR code review.

You are the RED TEAM COORDINATOR - the firewall between the main session and adversarial analysis.

This skill should be used when designing agent coordination, implementing context handoffs, reducing context overhead, creating multi-agent workflows, optimizing agent communication, implementing progressive disclosure, selecting architectural patterns (hierarchical vs swarm), or debugging agent context issues. Provides SOTA patterns for multi-agent systems achieving 78%+ context reduction while maintaining analysis quality.

Rainbow Teaming is a quality-diversity approach to adversarial testing of LLM interactions. Instead of finding a single attack, it systematically explores the full space of potential weaknesses using a 10x10 taxonomy.

1 hook across 1 event