Documentation 2026-03-01 06:10 UTC to 2026-03-04 21:06 UTC

330 330 

331## Create pull requests331## Create pull requests

332 332 

333You can create pull requests by asking Claude directly ("create a pr for my changes") or by using the `/commit-push-pr` skill, which commits, pushes, and opens a PR in one step.333You can create pull requests by asking Claude directly ("create a pr for my changes"), or guide Claude through it step-by-step:

334 

335```

336> /commit-push-pr

337```

338 

339If you have a Slack MCP server configured and specify channels in your CLAUDE.md (for example, "post PR URLs to #team-prs"), the skill automatically posts the PR URL to those channels.

340 

341For more control over the process, guide Claude through it step-by-step or [create your own skill](/en/skills):

342 334 

343<Steps>335<Steps>

344 <Step title="Summarize your changes">336 <Step title="Summarize your changes">

516Extended thinking is particularly valuable for complex architectural decisions, challenging bugs, multi-step implementation planning, and evaluating tradeoffs between different approaches.508Extended thinking is particularly valuable for complex architectural decisions, challenging bugs, multi-step implementation planning, and evaluating tradeoffs between different approaches.

517 509 

518<Note>510<Note>

519 Phrases like "think", "think hard", "ultrathink", and "think more" are interpreted as regular prompt instructions and don't allocate thinking tokens.511 Phrases like "think", "think hard", and "think more" are interpreted as regular prompt instructions and don't allocate thinking tokens.

520</Note>512</Note>

521 513 

522### Configure thinking mode514### Configure thinking mode

524Thinking is enabled by default, but you can adjust or disable it.516Thinking is enabled by default, but you can adjust or disable it.

525 517 

526| Scope | How to configure | Details |518| Scope | How to configure | Details |

527| ---------------------- | ------------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------- |519| ------------------------ | ------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------- |

528| **Effort level** | Adjust in `/model` or set [`CLAUDE_CODE_EFFORT_LEVEL`](/en/settings#environment-variables) | Control thinking depth for Opus 4.6: low, medium, high (default). See [Adjust effort level](/en/model-config#adjust-effort-level) |520| **Effort level** | Adjust in `/model` or set [`CLAUDE_CODE_EFFORT_LEVEL`](/en/settings#environment-variables) | Control thinking depth for Opus 4.6 and Sonnet 4.6: low, medium, high. See [Adjust effort level](/en/model-config#adjust-effort-level) |

521| **`ultrathink` keyword** | Include "ultrathink" anywhere in your prompt | Sets effort to high for that turn on Opus 4.6 and Sonnet 4.6. Useful for one-off tasks requiring deep reasoning without permanently changing your effort setting |

529| **Toggle shortcut** | Press `Option+T` (macOS) or `Alt+T` (Windows/Linux) | Toggle thinking on/off for the current session (all models). May require [terminal configuration](/en/terminal-config) to enable Option key shortcuts |522| **Toggle shortcut** | Press `Option+T` (macOS) or `Alt+T` (Windows/Linux) | Toggle thinking on/off for the current session (all models). May require [terminal configuration](/en/terminal-config) to enable Option key shortcuts |

530| **Global default** | Use `/config` to toggle thinking mode | Sets your default across all projects (all models).<br />Saved as `alwaysThinkingEnabled` in `~/.claude/settings.json` |523| **Global default** | Use `/config` to toggle thinking mode | Sets your default across all projects (all models).<br />Saved as `alwaysThinkingEnabled` in `~/.claude/settings.json` |

531| **Limit token budget** | Set [`MAX_THINKING_TOKENS`](/en/settings#environment-variables) environment variable | Limit the thinking budget to a specific number of tokens (ignored on Opus 4.6 unless set to 0). Example: `export MAX_THINKING_TOKENS=10000` |524| **Limit token budget** | Set [`MAX_THINKING_TOKENS`](/en/settings#environment-variables) environment variable | Limit the thinking budget to a specific number of tokens (ignored on Opus 4.6 unless set to 0). Example: `export MAX_THINKING_TOKENS=10000` |

680 * Use `claude mcp get <name>` to verify that OAuth credentials are configured for a server680 * Use `claude mcp get <name>` to verify that OAuth credentials are configured for a server

681</Tip>681</Tip>

682 682 

683### Override OAuth metadata discovery

684 

685If your MCP server returns errors on the standard OAuth metadata endpoint (`/.well-known/oauth-authorization-server`) but exposes a working OIDC endpoint, you can tell Claude Code to fetch OAuth metadata directly from a URL you specify, bypassing the standard discovery chain.

686 

687Set `authServerMetadataUrl` in the `oauth` object of your server's config in `.mcp.json`:

688 

689```json theme={null}

690{

691 "mcpServers": {

692 "my-server": {

693 "type": "http",

694 "url": "https://mcp.example.com/mcp",

695 "oauth": {

696 "authServerMetadataUrl": "https://auth.example.com/.well-known/openid-configuration"

697 }

698 }

699 }

700}

701```

702 

703The URL must use `https://`. This option requires Claude Code v2.1.64 or later.

704 

683## Add MCP servers from JSON configuration705## Add MCP servers from JSON configuration

684 706 

685If you have a JSON configuration for an MCP server, you can add it directly:707If you have a JSON configuration for an MCP server, you can add it directly:

128 128 

129### Adjust effort level129### Adjust effort level

130 130 

131[Effort levels](https://platform.claude.com/docs/en/build-with-claude/effort) control Opus 4.6's adaptive reasoning, which dynamically allocates thinking based on task complexity. Lower effort is faster and cheaper for straightforward tasks, while higher effort provides deeper reasoning for complex problems.131[Effort levels](https://platform.claude.com/docs/en/build-with-claude/effort) control adaptive reasoning, which dynamically allocates thinking based on task complexity. Lower effort is faster and cheaper for straightforward tasks, while higher effort provides deeper reasoning for complex problems.

132 132 

133Three levels are available: **low**, **medium**, and **high** (default).133Three levels are available: **low**, **medium**, and **high**. Opus 4.6 defaults to medium effort for Max and Team subscribers.

134 134 

135**Setting effort:**135**Setting effort:**

136 136 

138* **Environment variable**: set `CLAUDE_CODE_EFFORT_LEVEL=low|medium|high`138* **Environment variable**: set `CLAUDE_CODE_EFFORT_LEVEL=low|medium|high`

139* **Settings**: set `effortLevel` in your settings file139* **Settings**: set `effortLevel` in your settings file

140 140 

141Effort is currently supported on Opus 4.6. The effort slider appears in `/model` when a supported model is selected.141Effort is supported on Opus 4.6 and Sonnet 4.6. The effort slider appears in `/model` when a supported model is selected.

142 142 

143To disable adaptive reasoning on Opus 4.6 and Sonnet 4.6 and revert to the previous fixed thinking budget, set `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING=1`. When disabled, these models use the fixed budget controlled by `MAX_THINKING_TOKENS`. See [environment variables](/en/settings#environment-variables).143To disable adaptive reasoning on Opus 4.6 and Sonnet 4.6 and revert to the previous fixed thinking budget, set `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING=1`. When disabled, these models use the fixed budget controlled by `MAX_THINKING_TOKENS`. See [environment variables](/en/settings#environment-variables).

144 144 

814| `CLAUDE_CODE_DISABLE_FEEDBACK_SURVEY` | Set to `1` to disable the "How is Claude doing?" session quality surveys. Also disabled when using third-party providers or when telemetry is disabled. See [Session quality surveys](/en/data-usage#session-quality-surveys) | |814| `CLAUDE_CODE_DISABLE_FEEDBACK_SURVEY` | Set to `1` to disable the "How is Claude doing?" session quality surveys. Also disabled when using third-party providers or when telemetry is disabled. See [Session quality surveys](/en/data-usage#session-quality-surveys) | |

815| `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC` | Equivalent of setting `DISABLE_AUTOUPDATER`, `DISABLE_BUG_COMMAND`, `DISABLE_ERROR_REPORTING`, and `DISABLE_TELEMETRY` | |815| `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC` | Equivalent of setting `DISABLE_AUTOUPDATER`, `DISABLE_BUG_COMMAND`, `DISABLE_ERROR_REPORTING`, and `DISABLE_TELEMETRY` | |

816| `CLAUDE_CODE_DISABLE_TERMINAL_TITLE` | Set to `1` to disable automatic terminal title updates based on conversation context | |816| `CLAUDE_CODE_DISABLE_TERMINAL_TITLE` | Set to `1` to disable automatic terminal title updates based on conversation context | |

817| `CLAUDE_CODE_EFFORT_LEVEL` | Set the effort level for supported models. Values: `low`, `medium`, `high` (default). Lower effort is faster and cheaper, higher effort provides deeper reasoning. Currently supported with Opus 4.6 only. See [Adjust effort level](/en/model-config#adjust-effort-level) | |817| `CLAUDE_CODE_EFFORT_LEVEL` | Set the effort level for supported models. Values: `low`, `medium`, `high`. Lower effort is faster and cheaper, higher effort provides deeper reasoning. Supported on Opus 4.6 and Sonnet 4.6. See [Adjust effort level](/en/model-config#adjust-effort-level) | |

818| `CLAUDE_CODE_ENABLE_PROMPT_SUGGESTION` | Set to `false` to disable prompt suggestions (the "Prompt suggestions" toggle in `/config`). These are the grayed-out predictions that appear in your prompt input after Claude responds. See [Prompt suggestions](/en/interactive-mode#prompt-suggestions) | |818| `CLAUDE_CODE_ENABLE_PROMPT_SUGGESTION` | Set to `false` to disable prompt suggestions (the "Prompt suggestions" toggle in `/config`). These are the grayed-out predictions that appear in your prompt input after Claude responds. See [Prompt suggestions](/en/interactive-mode#prompt-suggestions) | |

819| `CLAUDE_CODE_ENABLE_TASKS` | Set to `false` to temporarily revert to the previous TODO list instead of the task tracking system. Default: `true`. See [Task list](/en/interactive-mode#task-list) | |819| `CLAUDE_CODE_ENABLE_TASKS` | Set to `false` to temporarily revert to the previous TODO list instead of the task tracking system. Default: `true`. See [Task list](/en/interactive-mode#task-list) | |

820| `CLAUDE_CODE_ENABLE_TELEMETRY` | Set to `1` to enable OpenTelemetry data collection for metrics and logging. Required before configuring OTel exporters. See [Monitoring](/en/monitoring-usage) | |820| `CLAUDE_CODE_ENABLE_TELEMETRY` | Set to `1` to enable OpenTelemetry data collection for metrics and logging. Required before configuring OTel exporters. See [Monitoring](/en/monitoring-usage) | |

72 72 

73<Note>Running [`/statusline`](#use-the-statusline-command) with a description of what you want configures all of this for you automatically.</Note>73<Note>Running [`/statusline`](#use-the-statusline-command) with a description of what you want configures all of this for you automatically.</Note>

74 74 

75These examples use Bash scripts, which work on macOS and Linux. On Windows, you can run Bash scripts through [WSL (Windows Subsystem for Linux)](https://learn.microsoft.com/en-us/windows/wsl/install) or rewrite them in PowerShell.75These examples use Bash scripts, which work on macOS and Linux. On Windows, see [Windows configuration](#windows-configuration) for PowerShell and Git Bash examples.

76 76 

77<Frame>77<Frame>

78 <img src="https://mintcdn.com/claude-code/nibzesLaJVh4ydOq/images/statusline-quickstart.png?fit=max&auto=format&n=nibzesLaJVh4ydOq&q=85&s=696445e59ca0059213250651ad23db6b" alt="A status line showing model name, directory, and context percentage" data-og-width="726" width="726" data-og-height="164" height="164" data-path="images/statusline-quickstart.png" data-optimize="true" data-opv="3" srcset="https://mintcdn.com/claude-code/nibzesLaJVh4ydOq/images/statusline-quickstart.png?w=280&fit=max&auto=format&n=nibzesLaJVh4ydOq&q=85&s=728c4bd06c8559cb46ddffffad983373 280w, https://mintcdn.com/claude-code/nibzesLaJVh4ydOq/images/statusline-quickstart.png?w=560&fit=max&auto=format&n=nibzesLaJVh4ydOq&q=85&s=f9d28e0f8f48f695167dd1d632a6cf4f 560w, https://mintcdn.com/claude-code/nibzesLaJVh4ydOq/images/statusline-quickstart.png?w=840&fit=max&auto=format&n=nibzesLaJVh4ydOq&q=85&s=57a2803a18cafe8cf1aa05619444f20c 840w, https://mintcdn.com/claude-code/nibzesLaJVh4ydOq/images/statusline-quickstart.png?w=1100&fit=max&auto=format&n=nibzesLaJVh4ydOq&q=85&s=52cdd52865842f0cda24489dd5310d3b 1100w, https://mintcdn.com/claude-code/nibzesLaJVh4ydOq/images/statusline-quickstart.png?w=1650&fit=max&auto=format&n=nibzesLaJVh4ydOq&q=85&s=f8876ea1f72bf40bd0aeec483ee20164 1650w, https://mintcdn.com/claude-code/nibzesLaJVh4ydOq/images/statusline-quickstart.png?w=2500&fit=max&auto=format&n=nibzesLaJVh4ydOq&q=85&s=6b1524305c7c71122cde65d0c3822374 2500w" />78 <img src="https://mintcdn.com/claude-code/nibzesLaJVh4ydOq/images/statusline-quickstart.png?fit=max&auto=format&n=nibzesLaJVh4ydOq&q=85&s=696445e59ca0059213250651ad23db6b" alt="A status line showing model name, directory, and context percentage" data-og-width="726" width="726" data-og-height="164" height="164" data-path="images/statusline-quickstart.png" data-optimize="true" data-opv="3" srcset="https://mintcdn.com/claude-code/nibzesLaJVh4ydOq/images/statusline-quickstart.png?w=280&fit=max&auto=format&n=nibzesLaJVh4ydOq&q=85&s=728c4bd06c8559cb46ddffffad983373 280w, https://mintcdn.com/claude-code/nibzesLaJVh4ydOq/images/statusline-quickstart.png?w=560&fit=max&auto=format&n=nibzesLaJVh4ydOq&q=85&s=f9d28e0f8f48f695167dd1d632a6cf4f 560w, https://mintcdn.com/claude-code/nibzesLaJVh4ydOq/images/statusline-quickstart.png?w=840&fit=max&auto=format&n=nibzesLaJVh4ydOq&q=85&s=57a2803a18cafe8cf1aa05619444f20c 840w, https://mintcdn.com/claude-code/nibzesLaJVh4ydOq/images/statusline-quickstart.png?w=1100&fit=max&auto=format&n=nibzesLaJVh4ydOq&q=85&s=52cdd52865842f0cda24489dd5310d3b 1100w, https://mintcdn.com/claude-code/nibzesLaJVh4ydOq/images/statusline-quickstart.png?w=1650&fit=max&auto=format&n=nibzesLaJVh4ydOq&q=85&s=f8876ea1f72bf40bd0aeec483ee20164 1650w, https://mintcdn.com/claude-code/nibzesLaJVh4ydOq/images/statusline-quickstart.png?w=2500&fit=max&auto=format&n=nibzesLaJVh4ydOq&q=85&s=6b1524305c7c71122cde65d0c3822374 2500w" />

794 ```794 ```

795</CodeGroup>795</CodeGroup>

796 796 

797### Windows configuration

798 

799On Windows, Claude Code runs status line commands through Git Bash. You can invoke PowerShell from that shell:

800 

801<CodeGroup>

802 ```json settings.json theme={null}

803 {

804 "statusLine": {

805 "type": "command",

806 "command": "powershell -NoProfile -File C:/Users/username/.claude/statusline.ps1"

807 }

808 }

809 ```

810 

811 ```powershell statusline.ps1 theme={null}

812 $input_json = $input | Out-String | ConvertFrom-Json

813 $cwd = $input_json.cwd

814 $model = $input_json.model.display_name

815 $used = $input_json.context_window.used_percentage

816 $dirname = Split-Path $cwd -Leaf

817 

818 if ($used) {

819 Write-Host "$dirname [$model] ctx: $used%"

820 } else {

821 Write-Host "$dirname [$model]"

822 }

823 ```

824</CodeGroup>

825 

826Or run a Bash script directly:

827 

828<CodeGroup>

829 ```json settings.json theme={null}

830 {

831 "statusLine": {

832 "type": "command",

833 "command": "~/.claude/statusline.sh"

834 }

835 }

836 ```

837 

838 ```bash statusline.sh theme={null}

839 #!/usr/bin/env bash

840 input=$(cat)

841 cwd=$(echo "$input" | grep -o '"cwd":"[^"]*"' | cut -d'"' -f4)

842 model=$(echo "$input" | grep -o '"display_name":"[^"]*"' | cut -d'"' -f4)

843 dirname="${cwd##*[/\\]}"

844 echo "$dirname [$model]"

845 ```

846</CodeGroup>

847 

797## Tips848## Tips

798 849 

799* **Test with mock input**: `echo '{"model":{"display_name":"Opus"},"context_window":{"used_percentage":25}}' | ./statusline.sh`850* **Test with mock input**: `echo '{"model":{"display_name":"Opus"},"context_window":{"used_percentage":25}}' | ./statusline.sh`

810* Check that your script outputs to stdout, not stderr861* Check that your script outputs to stdout, not stderr

811* Run your script manually to verify it produces output862* Run your script manually to verify it produces output

812* If `disableAllHooks` is set to `true` in your settings, the status line is also disabled. Remove this setting or set it to `false` to re-enable.863* If `disableAllHooks` is set to `true` in your settings, the status line is also disabled. Remove this setting or set it to `false` to re-enable.

864* Run `claude --debug` to log the exit code and stderr from the first status line invocation in a session

865* Ask Claude to read your settings file and execute the `statusLine` command directly to surface errors

813 866 

814**Status line shows `--` or empty values**867**Status line shows `--` or empty values**

815 868