From harness-evolver
Displays evolver progress charts, iteration counts, current and best scores, stagnation warnings if last 3 scores within 1%, regression detection, and LangSmith experiment URLs.
How this skill is triggered — by the user, by Claude, or both
Slash command
/harness-evolver:statusThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Show current evolution progress.
Show current evolution progress.
TOOLS="${EVOLVER_TOOLS:-$([ -d ".evolver/tools" ] && echo ".evolver/tools" || echo "$HOME/.evolver/tools")}"
EVOLVER_PY="${EVOLVER_PY:-$([ -f "$HOME/.evolver/venv/bin/python" ] && echo "$HOME/.evolver/venv/bin/python" || echo "python3")}"
$EVOLVER_PY $TOOLS/evolution_chart.py --config .evolver.json
After displaying the chart:
/harness:evolve with architect trigger.npx claudepluginhub raphaelchristi/harness-evolver --plugin harness-evolverShows current evolution run state including generation count, best score, bandit statistics, and island status.
Runs propose-evaluate-iterate loop to optimize and evolve AI agent performance using LangSmith evaluations and git worktrees for isolation. Requires .evolver.json setup.
View Self-Evolving Loop session status, history, memory metrics, skill evolution, reports, and tool dependencies using /evolving-status with flags like --detailed, --history, --memory.