Plan Judge Agent — Testing & QA agent for Claude Code
Judges a whole set of step plans as a set — does it actually reach a finished product.
How to install Plan Judge Agent
Installs to ~/.claude/agents/dujar-agent-workbench-plan-judge-agent.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/dujar/agent-workbench/HEAD/agents/plan-judge-agent.md -o ~/.claude/agents/dujar-agent-workbench-plan-judge-agent.md Restart Claude Code, or start a new session, for it to be picked up.
What Plan Judge Agent does
name: plan-judge-agent description: Judges a whole set of step plans as a set — does it actually reach a finished product? Checks coverage against the spec, phase completeness, dependency order, undeclared file collisions between parallel steps, gaps between steps, and whether anything is left over at the end. Writes plan-judgment.md. Run after plan-agent, in a loop until SHIPPABLE. tools: Read, Glob, Grep, Bash, Write model: opus effort: high
You start with no memory of the conversatio
Alternatives in Testing & QA
- Arbiter — You are a specialized validation agent 3.6k ★
- Fable Verifier — Cold verifier for finished fable deliverables 837 ★
- Spec Compliance Judge — Use this agent when you need to determine whether a solution correctly implements a specific part of a specifi 173 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Spec Critic
Adversarial reviewer for implementation plans and specs. Evaluates whether a plan will actually work when hand
Sf Scout
Read-only wave-0 reconnaissance for a Salesforce change. Use before any edit to map impacted metadata, the dep
Spec Planner
Implementation planning specialist that breaks down architectural designs into actionable tasks. Creates detai
Gate Strategist
Plans GATE preparation back from the exam date: hours available against needed, subject order by marks per hou
Dependency Verifier
Verify that external dependencies, APIs, specs, and tools actually behave as documented. Use when you need to
AI Team Producer.Agent
AI team producer agent (Remy). Use when: planning sprints, creating PROJECT_BRIEF.md, triaging bugs, merging P
Related Skills
Burndown Full
Drive a partially-executed plan to 100% coverage across the whole repo — enumerate, batch-execute, prove compl
Implement Phase
Autonomously execute a whole roadmap phase - resolve features to specs, create missing ones, then loop impleme
Phase295 Kick Builder
Phase 2.95 Builder Prompt — Performance, Platform Reach & UX Completeness