evolve.md

evolve

Evaluate coding-agent plugins: static checks, trigger accuracy, behavioral evals, reports

Options

  -h, --help                    help for evolve
      --json                    emit machine-readable JSONL progress on stdout
      --layout string           repository layout: auto, marketplace, multi, or single (default "auto")
      --results-format string   format for results files and the EVALUATION rollup: json, jsonc, or yaml (default: config results_format or json)
      --root string             repository root to operate on (default: walk up from the current directory)
      --telemetry-dir string    write OpenTelemetry traces/metrics/logs as JSON to this directory (default: off; overrides OTEL_* env vars)
  -v, --verbose                 enable debug logging

SEE ALSO

• evolve completion - Generate the autocompletion script for the specified shell
• evolve doctor - Check each harness (CLI on PATH, credential) and each vendor's counting API
• evolve models - Print the effective model matrix with pricing, harnesses, and provenance
• evolve report - Regenerate EVALUATION.md and EVALUATION.json from the stored results
• evolve run - Run the eval tiers: static checks, trigger accuracy, behavioral evals
• evolve version - Print the build version
• evolve view - Browse the stored results in a web browser (filter, sort, snapshot)