harness-consolidator
Background 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.
$ npx -y skills add raphaelchristi/harness-evolver --agent claude-codeShips with harness-evolver. Installing the plugin gets this agent.
How it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Background 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.
Point at any LLM agent codebase. Harness Evolver will autonomously improve it — prompts, routing, tools, architecture — using multi-agent evolution with LangSmith as the evaluation backend.
Other agents on harness-evolver.
- harness-architect
Use this agent when the evolution loop stagnates or regresses. Analyzes the agent architecture and recommends topology changes (single-call → RAG, chain → ReAct, etc.).
Open agent - harness-critic
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.
Open agent - harness-evaluator
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.
Open agent - harness-proposer
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.
Open agent - harness-testgen
Use this agent to generate test inputs for the evaluation dataset. Spawned by the setup skill when no test data exists.
Open agent