Automated harness evolution for AI agents. A Claude Code plugin that iteratively optimizes system prompts, routing, retrieval, and orchestration code using full-trace counterfactual diagnosis. Based on Meta-Harness (Lee et al., 2026).
raphaelchristi/harness-evolver
Agent
Use this agent when the evolution loop stagnates or regresses. Analyzes the agent architecture and recommends topology changes (single-call → RAG, chain → ReAct, etc.).
raphaelchristi/harness-evolver
Agent
Background agent for cross-iteration memory consolidation. Runs after each iteration to extract learnings and update evolutionmemory.md. Read-only analysis — does not modify agent code.
raphaelchristi/harness-evolver
Agent
Use 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.
raphaelchristi/harness-evolver
Agent
Use 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 keys needed.
raphaelchristi/harness-evolver
Agent
Self-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 value.
raphaelchristi/harness-evolver
Agent
Use this agent to generate test inputs for the evaluation dataset. Spawned by the setup skill when no test data exists.