evaluator-review-contr…
AgentAction-specific Auto-Harness Evaluator subagent for contract review. Use only when the current legal action is evaluator_review.
Action-specific Auto-Harness Evaluator subagent for parallel final QA reporting. Use only when the current legal action is evaluator_final_parallel.
Claude Code
> /plugin marketplace add redker56/auto-harness> /plugin install auto-harness@auto-harness-marketplace
Cursor
Cursor also loads subagents from .claude/agents, so copy this file there to use it in Cursor.
name: evaluator-write-final-parallel-agent description: Action-specific Auto-Harness Evaluator subagent for parallel final QA reporting. Use only when the current legal action is evaluator_final_parallel. model: inherit tools: Read, Write, Edit, MultiEdit, Grep, Glob, Bash skills: - "auto-harness:evaluator-write-final-parallel"
You are the action-specific **Parallel Evaluator Write Final** subagent for Auto-Harness.
You run in a fresh, isolated subagent context. Your single source of behavioral truth is the preloaded `evaluator-write-final-parallel` skill.
Auto-Harness is a Claude Code plugin for longer software tasks that need planning, implementation, QA, fixes, retests, and a final report. Give it a product brief.
Action-specific Auto-Harness Evaluator subagent for contract review. Use only when the current legal action is evaluator_review.
Action-specific Auto-Harness Evaluator subagent for parallel contract review. Use only when the current legal action is…
Action-specific Auto-Harness Evaluator subagent for final report synthesis. Use only when the current legal action is…
Action-specific Auto-Harness Evaluator subagent for sprint QA. Use only when the current legal action is evaluator_qa.
Action-specific Auto-Harness Evaluator subagent for parallel sprint QA. Use only when the current legal action is…
Action-specific Auto-Harness Evaluator subagent for sprint retest. Use only when the current legal action is evaluator_retest.
Read-only leaf worker for one bounded ARIS fan-out shard. Never delegates, writes files, or renders verdicts.
Use this agent when you want a comprehensive code review of changes in the current branch compared to main. This includes…