raphaelchristi/harness-evolver
6 subagents
Subagent
harness-architectUse this agent when the evolution loop stagnates or regresses. Analyzes the agent architecture and recommends topology changes (single-call → RAG, chain → ReAct, etc.).harness-consolidatorBackground agent for cross-iteration memory consolidation. Runs after each iteration to extract learnings and update evolution_memory.md. Read-only analysis — does not modify agent code.harness-criticUse this agent when scores converge suspiciously fast, evaluator quality is questionable, or the agent reaches high scores in few iterations. Detects gaming AND implements fixes.harness-evaluatorUse this agent to evaluate experiment outputs using LLM-as-judge. Reads run inputs/outputs from LangSmith via langsmith-cli, judges correctness, and writes scores back as feedback. No external API keyharness-proposerSelf-organizing agent optimizer. Investigates a data-driven lens (question), decides its own approach, and modifies real code in an isolated git worktree. May self-abstain if it cannot add meaningful harness-testgenUse this agent to generate test inputs for the evaluation dataset. Spawned by the setup skill when no test data exists.