Plan Judge — Development agent for Claude Code
Independent reviewer that scores an implementation plan against the fixed plan-quality rubric and returns specific, actionable weaknesses.
How to install Plan Judge
Installs to ~/.claude/agents/smurphy6492-claude-workspace-config-plan-judge.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/smurphy6492/claude-workspace-config/HEAD/.claude/agents/plan-judge.md -o ~/.claude/agents/smurphy6492-claude-workspace-config-plan-judge.md Restart Claude Code, or start a new session, for it to be picked up.
What Plan Judge does
name: plan-judge description: Independent reviewer that scores an implementation plan against the fixed plan-quality rubric and returns specific, actionable weaknesses. Use as the judge step in the plan-improvement loop. It did not write the plan and evaluates it cold. tools: Read, Glob, Grep model: inherit
Plan Judge
Role
You are an independent senior reviewer. You did **not** write the plan you are scoring, and you have no memory of how it was produced — judge it exactly as writ
Alternatives in Development
- Thermo Nuclear Code Quality Review — Independent strict maintainability reviewer for a collected diff and changed-file contents 144 ★
- Mathodology Award Judge — Use for one independent blind judge seat scoring an award-level submission against contest rubric criteria 137 ★
- Readiness Reviewer — USE WHEN /repo-doctor --semantic runs 68 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Aidd Arch Judge
Scores AIDD architecture candidates against the fixed rubric, independently.
Gan Evaluator
GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and p
Adam
Self-improvement analyst. Reads the adam journal and transcript context, clusters observations, scores them ag
Resume Judge
Scores a resume or letter draft against the anchored rubric in templates/rubric-resume.md and returns per-dime
Martha Coach
Writes ONE small, targeted knowledge patch per improvement cycle for Martha (IMPROVE.md step 6). Reads the wea
Performance Judge
Production step 3 — scores every on-camera take (eyes, expression, energy, fluency) and picks the best takes.
Related Skills
Model Comparison
Local open-weight models (Qwen3.5-397B, MiniMax M2.5) vs cloud coding agents (Codex 5.3, Claude Code) on six w
Skill Eval Loop
Agent Skill: harden another skill from its automatic agent evals. Score every Claude Code, Codex and Gemini CL
Validate Research
Validate research document against FAR (Factual, Actionable, Relevant) rubric