Test Judge — Testing & QA agent for Claude Code
Read-only judge of the RED test drafts of one plan unit.
How to install Test Judge
Installs to ~/.claude/agents/menot-you-plugin-test-judge.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/menot-you/plugin/HEAD/agents/test-judge.md -o ~/.claude/agents/menot-you-plugin-test-judge.md Restart Claude Code, or start a new session, for it to be picked up.
What Test Judge does
name: test-judge description: Read-only judge of the RED test drafts of one plan unit. Merges the drafts into one test set that covers every acceptance line and every RED line, and writes the tests that no draft wrote. tools: Read, Grep, Glob model: opus effort: max
You merge the test drafts of one unit of a plan into one test set. You do not write files or run a command that changes state.
Rules
- Your inputs are the unit that the brief names and the drafts that the brief gives.
Alternatives in Testing & QA
- Arbiter — You are a specialized validation agent 3.6k ★
- Omd Final QA — Read-only final-gate critic 465 ★
- TDD Specialist — Test-Driven Development specialist for Elixir/Phoenix projects using ExUnit 76 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Sdd Planner
Drafts plan.md and tasks.md for one spec, once, from an approved spec.md, the constitution, and the code the s
Feos Tester
FEOS S5 test-first agent. Use before implementing a task to write failing tests derived from the story's accep
Test Suite Builder
Synthesis agent that merges the validated requirements, planner artifacts, and coverage matrix into one test s
Factory Tester
Agent Factory role — writes the FAILING test FIRST for one unit, confirms it is RED against current code, and
Audience Doc Author
Drafts or refines an audience-tailored doc (README, release notes, MkDocs pages, or any doc governed by spec/p
Test Developer
Writes failing tests from a story's acceptance criteria before any production code exists (the RED phase). Use
Related Skills
Flutter Test
Run Flutter/Dart tests, report failures, and incrementally fix test issues. Covers unit, widget, golden, and i
ClaudeStrike
ClaudeStrike brings Claude to the Kali command line. Built for operators, it writes commands, runs tools, and
Graftree
Tree-structured, test-first, multi-model solving for hard coding problems. Splits a problem into sub-tasks, wr