Completion Judge — Development agent for Claude Code
name: completion-judge description: Decision-making agent for Self-Evolving Loop.
How to install Completion Judge
Installs to ~/.claude/agents/claude-world-director-mode-lite-completion-judge.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/claude-world/director-mode-lite/HEAD/agents/completion-judge.md -o ~/.claude/agents/claude-world-director-mode-lite-completion-judge.md Restart Claude Code, or start a new session, for it to be picked up.
What Completion Judge does
name: completion-judge description: Decision-making agent for Self-Evolving Loop. Evaluates validation results and decides next action (continue, evolve, or ship). color: cyan tools:
- Read
- Bash
- Grep model: haiku memory:
- user
Completion Judge Agent
You are the decision-making authority in the Self-Evolving Development Loop. You evaluate validation results and determine the optimal next step.
Activation
Automatically activate when:
- Validator skill completes valida
Alternatives in Development
- Owner Judge — Reviews proposed changes to VoiceStudio against the owner's documented standards 41.3k ★
- Senior Engineer P7 — P7 Senior Engineer Agent 19.5k ★
- Judge — You are a specialized reviewer for refactoring and code transformations 3.6k ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Habit Judge
Read-only verifier that scores a session, a diff, or a transcript against a habit set and returns an evidence-
PR Check Watcher
Watches a GitHub PR's CI checks to completion via gh pr checks --watch and reports a concise pass/fail summary
Completion Gate
Lie detector for agent claims — validates every completion claim has actual evidence. Default-FAIL mindset. Us
Coder Teammate
Code implementation teammate. Works in Agent Teams mode, communicates directly with evaluator-teammate. Claims
SwiftUI Modernization
Migrates legacy SwiftUI and UIKit to current APIs — ObservableObject to @Observable, NavigationView to Navigat
Completion Summary
Claude Code Sub-Agents - Completion Summary
Related Skills
Pua
Use when the user invokes /pua or asks for PUA mode, try-harder/retry help, change-approach coaching, completi
Ralph For Claude Code
by Frank Bria - An autonomous AI development framework that enables Claude Code to work iteratively on project
Lazycodex
The one and only agent harness for complex codebases. Project memory, planning, execution, and verified comple