Adversarial Critic — Design agent for Claude Code
Adversarial peer-review specialist for papers, plans, claims, research reports, design docs, marketing copy, or anything that argues a thesis.
How to install Adversarial Critic
Installs to ~/.claude/agents/aijuicetradess-claude-code-harness-adversarial-critic.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/AiJuicetradess/claude-code-harness/HEAD/agents/adversarial-critic.md -o ~/.claude/agents/aijuicetradess-claude-code-harness-adversarial-critic.md Restart Claude Code, or start a new session, for it to be picked up.
What Adversarial Critic does
name: adversarial-critic description: Adversarial peer-review specialist for papers, plans, claims, research reports, design docs, marketing copy, or anything that argues a thesis. Use when you need a hostile-but-fair second opinion on whether a deliverable's claims survive scrutiny. Distinct from code-reviewer (which audits implementation) — this agent audits arguments, evidence, framing, and methodological rigor. Operates with FRESH CONTEXT — never spawn from inside an implementation threa
Alternatives in Design
- Omd Persona Tester — Adversarial synthetic user that walks through generated UI under a strict persona prompt with hard turn budget 465 ★
- Codex Second Opinion — Get an independent opinion from OpenAI Codex (GPT-5) on a design decision, an approach, a tradeoff, or an unfa 249 ★
- Peer Reviewer Mixed Methods — A simulated peer reviewer specializing in mixed-methods research design, qualitative-quantitative integration 134 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Second Opinion Codex
Cross-vendor second opinion from the OpenAI Codex CLI. Use ONLY when the user explicitly asks for a codex/Open
Second Opinion Gemini
Cross-vendor second opinion from the Google Gemini CLI. Use ONLY when the user explicitly asks for a gemini/Go
Kb Advisor
Second-opinion advisor on a decision that is expensive to reverse — architecture, a corpus migration, a routin
Hyperplan Critic
Read-only adversarial critic for /hyperplan. Given a target (plan, decision, or draft) and ONE lens, reads the
Statistical Analysis Reviewer
Skeptical peer review of a completed analysis — design, assumptions, inference, and whether the stated conclus
Red Team Agent
Adversarial review agent. Use when a draft, design, or plan needs to be attacked the way a hostile stakeholder
Related Skills
Critique Adversarial
/critique-adversarial — Hostile cut-editor for articles. Reads the full piece first, maps the thesis spine, th
Visual Second Opinion
Three-pass Gemini visual review — advocate (ship), critic (redesign), synthesis (verdict + cruxes)
Peer AI
AI-to-AI peer consultation: install symmetric skills in Claude Code, Codex CLI, and Gemini CLI so any installe