Ensemble Judge — Development agent for Claude Code
Evaluates multiple competing solutions and selects the best one.
How to install Ensemble Judge
Installs to ~/.claude/agents/itachi-1824-claude-god-mode-ensemble-judge.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Itachi-1824/claude-god-mode/HEAD/agents/ensemble-judge.md -o ~/.claude/agents/itachi-1824-claude-god-mode-ensemble-judge.md Restart Claude Code, or start a new session, for it to be picked up.
What Ensemble Judge does
name: ensemble-judge description: Evaluates multiple competing solutions and selects the best one. Use after parallel worktree racing or when multiple approaches exist. Judges on correctness, complexity, testability, and maintainability. tools: Read, Grep, Glob, Bash model: opus effort: high color: yellow
You are an impartial judge evaluating competing implementations. You do NOT implement — you only evaluate and select.
Input
You will receive 2-5 competing solutions (code, diffs, or
Alternatives in Development
- Tech Stack Researcher — Use this agent when the user is planning new features or functionality and needs guidance on technology choice 1.5k ★
- Workflow Analyzer — Evaluates technical topics, proposals, or decisions across multiple dimensions with evidence-based scoring and 530 ★
- Checklist Deduper — Merges multiple batches of checklist items from checklist-generator into a single deduped checklist 115 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Brainstorm
Creative ideation — generates 2-3 approaches with trade-offs. Use when multiple valid paths exist or current a
Coder Alpha
Coder Alpha — correctness-first R coder. Prioritises well-tested, readable, conventional solutions. Invoked as
Technical Devils Advocate
Technical devil's advocate that challenges feature plans, strategies, and implementation approaches. Use proac
Lateral Thinking Expert
Expert in lateral thinking techniques specializing in creative problem-solving and unconventional approaches.
Adjudicator
Decides between competing outputs against stated criteria, restating the criteria BEFORE looking at the candid
Green Hat
Creative problem-solving across the full complexity spectrum. Finds solutions nobody proposed.
Related Skills
FastAPI Review
Review a FastAPI application for architecture, async correctness, dependency injection, Pydantic schemas, secu
Twin Sparrow Code Quality Skill
Review, refactor, and harden code for correctness, maintainability, testability, and operational safety across
Upstream Triage
Import upstream cmux PRs into c11 — agent evaluates desirability, judges difficulty, and writes the c11 versio