Portable Claude/Codex/WorkBuddy skill: AllinCMS content ops (raw → wiki → draft → adversarial review → publish → reflect). 6 rounds of adversarial review applied; Karpathy-style living wiki.
Vibe Science v5.5 ORO — Scientific research engine with adversarial review, tree search over hypotheses, and serendipity detection. Built natively for OpenAI Codex multi-agent architecture.
A standing red-team method for agent-built work: chartered adversary, mechanical trigger, written conditional verdicts. Worked example included.
Ask GPT from inside Claude Code. Adversarial code review via your ChatGPT subscription - no API key.
Four-phase plan hardening for Claude Code: DeepSeek-V4.1-Flash reviews the plan, then inspects the final code. Claude builds; DeepSeek grades.
A loop-engineering system for AI coding agents, delivered as a Pi package. Converge → specify → implement: parallel TDD development with dual-ring convergence gates, adversarial cross-source review, source-grounded citation verification, and prior-art collision search — honest coverage at every gate, never a silent green.
Evidence-first coding agent for Claude Code CLI. Port of burkeholland/anvil from GitHub Copilot CLI.
Adversarial AI review that returns a structured verdict: a score, findings classified by severity, and a clear pass/fail floor.
两仪 Liangyi · 跨厂商多 Agent 产品想法优化工作流
Four-phase plan hardening for Codex (the ChatGPT coding agent): DeepSeek-V4.1-Flash reviews the plan, then inspects the final code. Codex builds; DeepSeek grades.
Claude Code plugin: two AI models harden a plan, then swap jobs to build and grade it. Ships a read-only Codex wrapper, a PreToolUse guard against chained commands, role gates so the builder never grades its own work, and an egress boundary for fallback reviewers.
Portable read-only Agent Skill for deep pre-ship adversarial review of code changes, plans, and ship-blocker risks.
Role-based AI committee Codex Skill for complex decisions, adversarial critique, and evidence-driven verification.
Brainstorm product ideas and have a different model grade them. Whoever proposed an idea never decides whether it survives.
Cross-model delegation and adversarial review for CLI coding agents: one lead, six runtime adapters, and no change merges reviewed only by its own model family.
Claude Code plugin: universal radial-tree exploration engine. One tree skill + swappable presets (brainstorm / attack / design / code-audit) for divergent ideation, adversarial critique, and design-space exploration. 12 framings × hard-ban-on-incomplete-leaves × stable convergence.
Adversarial review tribunal for Claude Code — parallel attack lenses, findings tried by a skeptic, fixes re-attacked, zero-confirmed-defect gate, defect ledger.
Decision gate for AI-era work: adversarial review for code, research, and production decisions.
Quant research: early-breakout momentum on SP500 — 9.4% CAGR vs SPY's 7.9% on 26-year survivorship-bias-free backtest (1,081 historical constituents). Automated Alpaca paper trading. 305 tests. Not financial advice.
To associate your repository with the adversarial-review topic, visit your repo's landing page and select "manage topics."