AgentKit
DocsKitsCLI ReferenceDesktop App

eval

ak eval triage-benchmark

Evaluate frozen finding triage against local verified labels

Use ak eval triage-benchmark for the operation described below. The command help records its arguments, effects, and options.

Command contract

Evaluate frozen finding triage against local verified labels

Synopsis

Evaluate frozen finding triage against local verified labels. Input must contain compact reviewed facts; raw scanner output is not accepted.

Effects: Reads local frozen replay and labels only; never calls a provider or runs review commands.

Exit status: 0 report generated; inspect safety and coverage 1 invalid input or configuration

ak eval triage-benchmark <input.json|-> [flags]

Examples

  ak eval triage-benchmark input.json --json
  ak eval triage-benchmark - --json

Options

  -h, --help             help for triage-benchmark
      --json             Emit machine-readable JSON (implies --no-interactive)
      --no-interactive   Disable interactive prompts (CI-safe)
  -q, --quiet            Suppress non-error output on stderr
  -V, --verbose          Extra diagnostic output on stderr (loses to --quiet)
  -y, --yes              Assume yes for all prompts

SEE ALSO

  • ak eval - Run controlled skill and agent evaluations