{"version":"2.1.269","anchor":"claude-plugin-eval-gains-a-concurrency-flag","canonical_anchor":"claude-plugin-eval-gains-a-concurrency-flag","heading":"claude plugin eval gains a --concurrency flag","tier":"use","area":"Plugin Eval","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.269\/e\/claude-plugin-eval-gains-a-concurrency-flag","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.269","markdown":"### `claude plugin eval` gains a `--concurrency` flag\n\n`claude plugin eval` gains a `--concurrency` flag to run up to 8 test cases at once\n\n**What**\n\nThe `claude plugin eval` command (which runs a plugin's test suite and produces a scored report) now supports a `-j, --concurrency <n>` option. It accepts a whole number from 1 to 8 (default 1) and controls how many agent runs execute at the same time. All of these runs share your account's rate limit, progress lines may interleave in the output, but results and the final report still keep the original case order.\n\nThe JSON report also now includes a `concurrency` field recording the value used for that run.\n\n**Why**\n\nThis lets larger eval suites finish faster by running multiple cases in parallel instead of one at a time, while keeping results easy to read in their original order.\n\n- Area: Plugin Eval\n- Names: `--concurrency`\n- Tier: Use it now\n- Useful: 5\/5\n- Signal: 2\/5"}