{"name":"--max-cost-usd","slug":"max-cost-usd","family":"cli","title":"CLI flags","noun":"CLI flag","description":"Help text for --max-cost-usd now explains its cost ceiling is checked before each run, not per single run","description_source":"entry","described_by":{"version":"2.1.269","anchor":"cli-eval-tools-max-cost-usd-help-text-clarifies-overrun-b"},"presence":{"first_seen":"2.1.198","removed_in":null,"in_current_build":true,"newest_mined":"2.1.308","builds":99,"mined_builds":149,"first_cited":null},"aliases":[],"entries":[{"version":"2.1.269","anchor":"cli-eval-tools-max-cost-usd-help-text-clarifies-overrun-b","heading":"CLI eval tool's --max-cost-usd help text clarifies overrun bound","line":"Help text for --max-cost-usd now explains its cost ceiling is checked before each run, not per single run","released_at":"2026-09-11 18:12:49","reason":"found in this entry's text, named in this entry"},{"version":"2.1.210","anchor":"eval-report-publishing","heading":"Eval Report Publishing","line":null,"released_at":"2026-07-14 19:39:21","reason":"found in this entry's text"},{"version":"2.1.207","anchor":"walnut-spire-plugin-eval-general-availability-in-development","heading":"Walnut Spire ( plugin eval General Availability) [In Development]","line":null,"released_at":"2026-07-10 22:25:09","reason":"found in this entry's text"},{"version":"2.1.198","anchor":"plugin-eval-command-early-access","heading":"Plugin Eval Command [Early Access]","line":null,"released_at":"2026-07-01 16:50:16","reason":"found in this entry's text"}],"entries_total":4,"docs":[{"source":"claude-code","path":"plugin-evals","title":"Test plugins with evals","documented":false},{"source":"claude-code","path":"plugins\/cli-reference","title":"Plugin commands reference","documented":false}],"docs_total":2,"gates":[],"related":[{"name":"--max-budget-usd","slug":"max-budget-usd","description":"Maximum dollar amount to spend on API calls before stopping (print mode only). Spend from [subagents](\/docs\/en\/sub-agents) counts toward the cap. When you return to a conversation with `--continue` or `--resume`, totals [restored from earlier runs](\/docs\/en\/agent-sdk\/cost-tracking#accumulate-costs-across-multiple-calls) don't count toward it. Once spend reaches the cap, spawning another subagent fails with `Budget limit reached`, and Claude Code stops background subagents that are still running; the cap-enforcement behaviors require Claude Code v2.1.217 or later"}],"url":"https:\/\/changelogs.core-directive.com\/reference\/cli\/max-cost-usd","family_url":"https:\/\/changelogs.core-directive.com\/reference\/cli.json"}