Envoy Adversarial Review — Design skill for Claude Code
Run a Codex review that challenges the implementation approach and design choices.
How to install Envoy Adversarial Review
Installs to ~/.claude/skills/transmutelabs-catalyst-envoy-adversarial-review/SKILL.md
mkdir -p ~/.claude/skills/transmutelabs-catalyst-envoy-adversarial-review && curl -fsSL https://raw.githubusercontent.com/TransmuteLabs/Catalyst/HEAD/commands/envoy-adversarial-review.md -o ~/.claude/skills/transmutelabs-catalyst-envoy-adversarial-review/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Envoy Adversarial Review does
description: Run a Codex review that challenges the implementation approach and design choices argument-hint: '[--wait|--background] [--base ] [--scope auto|working-tree|branch] [focus ...]' disable-model-invocation: true allowed-tools: Read, Glob, Grep, Bash(node:*), Bash(git:*), AskUserQuestion
Run an adversarial Codex review through the shared plugin runtime. Position it as a challenge review that questions the chosen implementation, design choices, tradeoffs, and assumptions. I
Alternatives in Design
- Figma — Fetch design context, screenshots, and assets from Figma for implementation 14.6k ★
- Explanatory Output Style — Educational output mode with insights about implementation choices 14k ★
- Design Review Workflow — by Patrick Ellis - A tailored workflow for enabling automated UI/UX design review, including specialized sub a 3.7k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Vibe Wise MCP
Universal MCP server port of VibeWise: design-first gate for any coding agent (Claude Code, Cursor, Codex, Ant
AR
Run adversarial review on the current design.
Adversarial Review
Devil's advocate: challenge every design decision and assumption
J Frontend
Frontend consultation — frameworks, design systems, and web patterns. Use when building with React, Next.js, S
Design Handoff Review
Review a design-handoff implementation for character-level text fidelity and orphaned input bindings against t
Dld Review
Review Detailed Design (DLD) for implementation readiness
Related Agents
Kimi Challenge
Use this agent when Claude wants Kimi to run an adversarial review that challenges the implementation approach
Envoy Runner
Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper roo
Orchestration Design Reviewer
Pre-implementation design gate for security-sensitive infrastructure. Defines trust boundaries and impossible