Skip to main content
reopt Handbook
reopt Handbook
Claude Code Command MasterLabels and command selectionHow to read a detail guideComplete command listTerminal CLI Commands and Flags

Task guides

Core command basicsStarting and resuming workSkills and Custom CommandsAutomation and Web CommandsOperations and Safety CommandsCustom commands and skillsMCP connections and commands

Conversation and context

Cmd. /add-dirCmd. /backgroundCmd. /compactCmd. /contextCmd. /copyCmd. /exportCmd. /forkCmd. /importCmd. /initCmd. /memoryCmd. /recapCmd. /renameCmd. /resumeCmd. /rewindCmd. claude purge

Planning and execution

Cmd. /autofix-prCmd. /batchCmd. /desktopCmd. /goalCmd. /loopCmd. /planCmd. /remote-envCmd. /scheduleCmd. /tasksCmd. /teleportCmd. /workflows

Review and verification

Cmd. /code-reviewCmd. /runCmd. /run-skill-generatorCmd. /security-reviewCmd. /simplifyCmd. /verify

Models and settings

Cmd. /claude-apiCmd. /configCmd. /effortCmd. /fastCmd. /modelCmd. /output-styleCmd. /update-config

Permissions and integrations

Cmd. /agentsCmd. /hooksCmd. /ideCmd. /mcpCmd. /permissionsCmd. /pluginCmd. /reload-pluginsCmd. /reload-skillsCmd. /sandboxCmd. /skillsCmd. /web-setup

Status and diagnostics

Cmd. /debugCmd. /diffCmd. /doctorCmd. /fewer-permission-promptsCmd. /release-notesCmd. /team-onboarding

Display and input

Cmd. /colorCmd. /focusCmd. /keybindingsCmd. /powerupCmd. /statuslineCmd. /terminal-setupCmd. /themeCmd. /tui

Account and usage

Cmd. /upgradeCmd. /usageCmd. /usage-credits

Legacy

Cmd. /costCmd. /pr-commentsCmd. /reviewCmd. /statsCmd. /ultrareviewCmd. /vimCmd. /approved-toolsCmd. /commandsCmd. /extra-usageCmd. /settingsCmd. /tagCmd. /todos

Verification and history

Current verification scopeHandbook updatesRelease coverage historyEarlier verification recordsCommand change history
Handbook›Claude Code Command Master›Cmd. /effort
한국어KOEnglishEN

Cmd. /effort

Set or inspect model-specific reasoning effort.

Written and reviewed by Eric Han · Co-founder & CTO, reopt

Key takeaways

  • Set or inspect model-specific reasoning effort.
  • Check the input surface and availability before using the examples below.

Purpose

Set or inspect model-specific reasoning effort.

/effort [level|auto|status|ultracode [on|off]]

Availability

FieldValue
Input surfaceRunning CLI prompt
KindBuilt-in
StatusCurrent reference
Aliases—
Documented minimumNot specified
Reviewed against2026-10-23 · Claude Code 2.1.308

Use a level supported by the model. Opus 5.5, Sonnet 5.5, and Haiku 5.5 default to medium. The ultracode on and off arguments, and keeping the current level, require v2.1.284+.

Examples

/effort status
/effort ultracode off

Effects and persistence

Adjusts reasoning effort for the active model. Session-only values and saved defaults depend on the model, level, and input surface. Ultracode is a separate toggle, so turning it on or off leaves the effort level unchanged.

Inspecting or resetting effort

Use /effort status to inspect the active level. /effort auto returns to the model default. Supported levels differ by model; check the model configuration reference before selecting one.

Opus 5.5, Sonnet 5.5, and Haiku 5.5 default to medium; Opus 4.7 defaults to xhigh; other effort-capable models default to high. Haiku 5.5 (v2.1.293+) supports low through xhigh and max, like Opus 5.5 and Sonnet 5.5. Thinking cannot be turned off on Opus 5.5, Sonnet 5.5, Haiku 5.5, or the Fable models, so lowering effort is the way to reduce thinking there. A top-level effortLevel in user settings (the format /effort wrote before per-model modelSettings) still applies to Opus 5 and Fable 5.1, but Opus 5.5 and later models ignore it and start at their own default until you choose a level with /effort or the /model picker. A top-level effortLevel in project, local, or managed settings, or passed with --settings, applies to every model. From v2.1.280, the launch-default hold on Opus 4.7, Opus 4.8, and Fable 5 no longer overrides /effort in -p or the Agent SDK, project/managed/--settings effortLevel, or a per-model level.

Cautions

max is session-only. Ultracode is a separate toggle rather than an effort level: /effort ultracode (or ultracode on) turns it on for the session at the current level, /effort ultracode off turns it off, and Tab flips it in the /effort slider. The ultracode setting persists it, while --effort ultracode turns it on and also sets the level to xhigh. The on and off arguments, the slider toggle, and keeping ultracode on at levels other than xhigh require v2.1.284+; before that, /effort ultracode set the session to xhigh and /effort ultracode off failed with Invalid argument. From v2.1.284 the slider keys can be rebound with the effortSlider:decreaseEffort, effortSlider:increaseEffort, and effortSlider:toggleUltracode keybinding actions.

Official sources

  • Commands
  • Model Config
  • Haiku 5.5 Overview

Complete command list · Verification scope

Related docs

Plan and Environment Setup

Claude Code Complete Guide · Prepare Claude Code plans, installation, update policy, and a safe repository baseline.

Cmd. /model

Saves the selected model as the default for new sessions. Press s on a picker row, or use a supported -p invocation, for a session-only change.

Cmd. /fast

Switches the supported model's fast processing path. It is separate from reasoning effort and may have different billing or quota rules.

Verification Report

Claude Code Complete Guide · Verification checklist for the English Claude Code handbook locale.

Update Log

Claude Code Complete Guide · English edition changes for the Claude Code Complete Guide.

Cmd. /config

Open settings or apply direct key/value settings (/settings).

Cmd. /fast

Switches the supported model's fast processing path. It is separate from reasoning effort and may have different billing or quota rules.

On this page

PurposeAvailabilityExamplesEffects and persistenceInspecting or resetting effortCautionsOfficial sources