Architecture Red Team — Security agent for Claude Code
adversarial reviewer for plans and architecture changes.
How to install Architecture Red Team
Installs to ~/.claude/agents/porkchop-phasekit-architecture-red-team.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/porkchop/phasekit/HEAD/.claude/agents/architecture-red-team.md -o ~/.claude/agents/porkchop-phasekit-architecture-red-team.md Restart Claude Code, or start a new session, for it to be picked up.
What Architecture Red Team does
name: architecture-red-team description: adversarial reviewer for plans and architecture changes. challenge assumptions, expose hidden coupling, scaling issues, security holes, weak acceptance criteria, and risky migrations.
You are skeptical and concrete.
Focus
- hidden coupling
- overengineering and underengineering
- security and public-internet exposure risks
- migration and rollback risk
- unclear ownership boundaries
- weak observability or ops planning
- insufficient tests fo
Alternatives in Security
- Gitnexus Security Boundary Reviewer — GitNexus security and trust-boundary reviewer 45.8k ★
- Mobile Reverser — Deep Mobile Security Red Team persona 548 ★
- Audit Deep — Deep single-subsystem audit that reasons about state over time (caches, upserts, migrations, concurrent scans) 335 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Adversary
Pre-implementation red-team analysis. Challenges plans BEFORE code is written — edge cases, security holes, sc
Critic Logic
Review code for logic bugs, unhandled edge cases, happy-path assumptions, input-validation gaps, and error-han
Verify Implementation
Independently reviews a finished implementation — a PR produced by implement-issue — against its issue's accep
Nextjs Verifier
Independently verifies a Next.js SDD implementation against acceptance criteria, lint, type checks, tests, bui
Plan Challenger
Adversarial plan review before implementation. Attacks plans across 5 dimensions (Assumptions, Missing Cases,
Red Team
Security red team specialist. Attacks the developer's stated security assumptions. Use proactively when code t
Related Skills
Assume
Challenge the hidden assumptions in a document
Obsidian Challenge
Red-team your current idea against your own vault history — finds contradictions, past failures, and flawed as
Brain Challenge
Red-team an idea or plan against the second brain's own history - surface contradictions, past failures, and f