Adversarial, ship/no-ship code review of a git diff or branch — runs against any LLM (API or local CLI agent) and returns structured findings

Adversarial PR/code review tool — structured, skeptical scrutiny for CI

Production-grade CLI for auditing AI prompts. Detects invisible characters, homoglyph attacks, and adversarial Unicode poisoning in your development workflow.

Multi-LLM adversarial review council - an AXI

Pi skill package for adversarial-qa.

Adversarial cooperation plugin for OpenCode - dialectical Actor-Critic TDD workflow based on Block AI research

Governance substrate for AI coding agents — adversarial PR review, drift-detected rules, tamper-evident audit, and closed-loop outcome routing for Claude, Codex, Gemini, and OpenCode

Red-team adversarial security testing for ArtemisKit LLM evaluation toolkit

Deterministic multi-model adversarial code review orchestration for Pi.

AI red-teaming for the AI agents & LLM apps you own: stress-test them with adversarial models to find security failures (prompt injection, tool misuse / excessive agency, data leakage, jailbreaks, denial-of-wallet), auto-patch (blue team), retest, and get

Command-triggered red/blue adversarial review for ANY plan (not quant-specific). /plan-adversarial <plan>: arms a gate that requires the agent to derive two independent subagents (red=attack, blue=defend), have them converge on a consensus plan with NO th

Claude Code adversarial multi-agent workflows — 11 slash commands covering the full software lifecycle

Language-neutral conformance vectors, an adversarial mock mint, and a grader for LNURLcash (LUD-25) implementations

Multi-model AI verification with adversarial critique. No AI can verify itself — so they verify each other.

Adversarial code review plugin

Position-driven adversarial debate CLI — host supplies opposing stances, arena runs the debate across local model CLIs (Claude, Codex, Gemini, OpenAI, Kimi).

Adversarial security testing for AI agent handoffs

Stress-test product ideas with adversarial agents, synthetic users, and court-style critique.

Adversarial review for code, MCP configs and system prompts — every finding carries a repro path and confidence; unreproducible ones are marked suspected, never confirmed.

NodeJS multi-tool adversarial review gate for coding agents.