{"name":"--effort","slug":"effort","family":"cli","title":"CLI flags","noun":"CLI flag","description":"Set the [effort level](\/docs\/en\/model-config#adjust-effort-level) for the current session. Options: `low`, `medium`, `high`, `xhigh`, `max`, or `ultracode`. Available levels depend on the model. `ultracode` requests `xhigh` effort with [ultracode](\/docs\/en\/workflows#let-claude-decide-with-ultracode) turned on, and requires Claude Code v2.1.203 or later. Overrides the [`modelSettings`](\/docs\/en\/settings-reference#modelsettings) and [`effortLevel`](\/docs\/en\/settings-reference#effortlevel) settings for this session and does not persist","description_source":"docs","described_by":{"doc":"claude-code\/cli-reference","title":"CLI reference"},"presence":{"first_seen":"2.1.142","removed_in":null,"in_current_build":true,"newest_mined":"2.1.308","builds":145,"mined_builds":149,"first_cited":{"version":"2.1.38","released_at":"2026-02-10 00:06:12","spans":1}},"aliases":[],"entries":[{"version":"2.1.295","anchor":"sdk-spawns-cli-with-flagvalue-form-and-guards-values-st","heading":"Agent SDK passes options so values starting with a dash are not misread","line":"The Agent SDK now passes many options as `--flag=value`, so a value starting with a dash is no longer mistaken for another flag","released_at":"2026-10-08 18:22:58","reason":"found in this entry's text, named in this entry"},{"version":"2.1.281","anchor":"error-wording-for-sessions-hosted-by-the-desktop-app-no-sla","heading":"Error wording for sessions hosted by the desktop app: no slash commands","line":"Some error messages drop slash-command and flag advice when the session is hosted by a desktop app","released_at":"2026-09-23 17:01:17","reason":"found in this entry's text"},{"version":"2.1.267","anchor":"per-model-maxeffortlevel-cap-now-enforced-client-side-acro","heading":"Per-model \"maxEffortLevel\" cap now enforced client-side across settings","line":"maxEffortLevel now combines a global cap with per-model overrides across all settings files and clamps any explicit effort request","released_at":"2026-09-09 18:25:42","reason":"found in this entry's text"},{"version":"2.1.239","anchor":"session-effort-becomes-a-tagged-value","heading":"Session effort becomes a tagged value","line":"Effort is stored as a tagged object, and the effort setting is cleared when no specific level applies.","released_at":"2026-08-21 17:18:54","reason":"named in this entry, found in this entry's text"},{"version":"2.1.234","anchor":"early-flag-scan-no-longer-mistakes-tool-lists-and-directorie","heading":"Early flag scan no longer mistakes tool lists and directories for flags","line":"Tool lists and directories passed to flags are no longer misread as flags themselves at startup.","released_at":"2026-08-17 18:19:13","reason":"found in this entry's text"},{"version":"2.1.234","anchor":"spawned-processes-get-flag-value-when-the-value-looks-like-a","heading":"Spawned processes get --flag=value when the value looks like a flag","line":"Prompts and model names starting with a dash are no longer swallowed as options by subagents and background tasks.","released_at":"2026-08-17 18:19:13","reason":"found in this entry's text"},{"version":"2.1.228","anchor":"relaunching-claude-code-keeps-your-selected-model","heading":"Relaunching Claude Code keeps your selected model","line":"Restarting after an update keeps the model you picked instead of reverting to the default.","released_at":"2026-08-11 17:45:45","reason":"found in this entry's text"},{"version":"2.1.170","anchor":"effort-flag-passthrough-now-requires-all-three-models-launch","heading":"Effort Flag Passthrough Now Requires All Three Models Launched","line":null,"released_at":"2026-06-09 16:15:44","reason":"found in this entry's text"},{"version":"2.1.38","anchor":"effort-level-control","heading":"Effort Level Control","line":null,"released_at":"2026-02-10 00:06:12","reason":"found in this entry's text"}],"entries_total":9,"docs":[{"source":"claude-code","path":"cli-reference","title":"CLI reference","documented":true},{"source":"claude-code","path":"agent-view","title":"Manage multiple agents with agent view","documented":false},{"source":"claude-code","path":"env-vars","title":"Environment variables","documented":false},{"source":"claude-code","path":"model-config","title":"Model configuration","documented":false},{"source":"claude-code","path":"settings","title":"Claude Code settings","documented":false},{"source":"claude-code","path":"settings-example","title":"Example settings files","documented":false},{"source":"claude-code","path":"settings-reference","title":"All settings","documented":false},{"source":"claude-code","path":"whats-new\/2026-w20","title":"Week 20 \u00b7 May 11\u201315, 2026","documented":false},{"source":"claude-code","path":"workflows","title":"Orchestrate subagents at scale with dynamic workflows","documented":false}],"docs_total":9,"gates":[],"related":[],"url":"https:\/\/changelogs.core-directive.com\/reference\/cli\/effort","family_url":"https:\/\/changelogs.core-directive.com\/reference\/cli.json"}