Judge Agent — Development agent for Claude Code
Read-only isolated agent that evaluates skill/agent execution quality.
How to install Judge Agent
Installs to ~/.claude/agents/walllmat-verdict-judge-agent.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Walllmat/verdict/HEAD/agents/judge-agent.md -o ~/.claude/agents/walllmat-verdict-judge-agent.md Restart Claude Code, or start a new session, for it to be picked up.
What Judge Agent does
name: judge-agent displayName: "Verdict Evaluator Agent" description: "Read-only isolated agent that evaluates skill/agent execution quality" tools:
- Read
- Glob
- Grep
- Bash (read-only commands only)
Verdict Evaluator Agent
Role
You are an impartial, evidence-based quality evaluator. Your sole purpose is to assess the execution quality of Claude Code skills and agents. You operate in strict read-only mode — you never modify files, write code, or take any actions beyond
Alternatives in Development
- Judge — You are a specialized reviewer for refactoring and code transformations 3.6k ★
- Theme PR Reviewer — Read-only reviewer for Graphite theme PRs — checks generated/source coherence, token quality, and contrast 452 ★
- Robin — Read-only, skeptical evidence auditor for a Superloopy criterion 109 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Ensemble Judge
Evaluates multiple competing solutions and selects the best one. Use after parallel worktree racing or when mu
Continuous Claude V2
Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without conte
Prompt Executor
Executes a prompt in an isolated worktree environment and captures results. Use when worktree path and prompt
Exec Critical
FRONTIER-DO tier at high effort. Execution agent for correctness-critical implementation in an isolated git wo
Exec Mechanical
SMALL tier at medium effort. Execution agent for mechanical, well-specified edits in an isolated git worktree
Vouch Judge
Isolated grounding judge for Vouch. Given a verification packet file (judge instructions, corpus evidence, num
Related Skills
Judge
Evaluate the execution quality of a skill or agent
Agent Aiengineer
Work as the AI & Agent Engineer agent — Builds and evaluates agent prompts, routing, tools, memory, and execut
Design Critique
UX heuristic review of Figma screens — evaluates against Nielsen's 10 heuristics, visual design quality, spaci