{
  "markdown": "# The Courtroom\n\nCross-model deliberation plugin for Claude Code. Claude proposes an implementation plan, Codex cross-examines it, they debate, and the verdict gets executed.\n\nTwo AI models arguing so your code doesn't have to.\n\n## Install\n\n```bash\n/plugin marketplace add JustineDaveMagnaye/the-courtroom\n/plugin install courtroom\n```\n\n## Usage\n\n```bash\n/courtroom --task \"refactor auth module\" --files src/auth.ts\n```\n\n### Flags\n\n| Flag | Description |\n|------|-------------|\n| `--task \"description\"` | What to plan |\n| `--files path,...` | Scope to specific files |\n| `--rounds N` | Number of debate rounds (default: 1) |\n| `--strict` | Harsher critique mode |\n| `--quick` | Fast mode (limited to 3 files) |\n| `--dual-plan` | Codex generates its own plan before seeing Claude's |\n| `--auto-execute` | Skip user approval |\n| `--log` | Log session statistics |\n| `--stats` | Show aggregated stats |\n\n## How It Works\n\n| Role | Model |\n|------|-------|\n| Prosecution | Claude (proposes the plan) |\n| Cross-Examiner | Codex CLI (challenges it) |\n| Judge | You (approve or reject) |\n\n**7-phase workflow:**\n\n1. **Opening Statements** - Gather context, verify Codex CLI, parse arguments\n2. **Prosecution** - Claude builds a detailed implementation plan\n3. **Cross-Examination** - Codex challenges the plan (logical flaws, edge cases, architecture, security)\n4. **Rebuttal** - Claude responds: ACCEPT / REJECT / COMPROMISE per objection\n5. **Deliberation** - Codex reviews the revised plan as neutral arbiter\n6. **Verdict** - Final plan presented for approval\n7. **Execution** - Approved plan gets implemented\n\n## Key Features\n\n- **Weak Objection Catalog** - Auto-filters 27 known false-positive patterns (style bikeshedding, YAGNI, scope creep, phantom references)\n- **Task-Type Checklists** - Bugfix, security, refactor, and feature-specific review priorities injected into cross-examination\n- **Dual-Plan Mode** - Codex generates an independent plan before seeing Claude's for comparison\n- **Skill Discovery** - Auto-discovers relevant skills from both Claude and Codex\n- **Session Logging** - Tracks objection acceptance rates across sessions\n\n## Requirements\n\n- [Claude Code](https://claude.ai/code)\n- [Codex CLI](https://github.com/openai/codex) installed and configured\n\n## License\n\nMIT\n",
  "bytes": 2288,
  "sha": "d8c161c71579ba909b9542bbeb3be88ce2bfa562230da03a964eee766bbc8eee",
  "repo_slug": "justinedavemagnaye/the-courtroom",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_justinedavemagnaye_the_courtroom_the_cou_e7607b5e/readme"
}