Best practices for Claude Code changedbest-practices
Nearest release: v2.1.234, published 8 hours before this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Recorded here
Lines+9added
Lines−8removed
From line
83
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits24to this page, all time
The whole hunk
from line 83, old and new numbered
/
from line 83
8383 <Step title="Implement">
8484 Switch out of plan mode by approving the plan or pressing `Shift+Tab`, then let Claude code, verifying against its plan.
8585
86 ```txt title="claude (default mode)" wrap theme={null}
86 ```txt title="claude" wrap theme={null}
8787 implement the OAuth flow from your plan. write tests for the
8888 callback handler, run the test suite and fix any failures.
8989 ```
from line 92
9292 <Step title="Commit">
9393 Ask Claude to commit with a descriptive message and create a PR.
9494
95 ```txt title="claude (default mode)" wrap theme={null}
95 ```txt title="claude" wrap theme={null}
9696 commit with a descriptive message and open a PR
9797 ```
9898 </Step>
from line 188
188188### Configure permissions
189189
190190<Tip>
191 Use [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) to let a classifier handle approvals, `/permissions` to allowlist specific commands, or `/sandbox` for OS-level isolation. Each reduces interruptions while keeping you in control.
191 To get fewer prompts without giving up control, pre-approve the tools you trust with `/permissions` and let sandboxed commands run without asking with `/sandbox`. Switch to Manual mode when you want to approve edits and commands yourself.
192192</Tip>
193193
194By default, Claude Code requests permission for actions that might modify your system: file writes, Bash commands, MCP tools, etc. This is safe but tedious. After the tenth approval you're not really reviewing anymore, you're just clicking through. There are three ways to reduce these interruptions:
194On Pro, Max, and Team plans, auto mode is the [built-in starting permission mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) for interactive terminal and VS Code sessions: a separate classifier model reviews most actions instead of you and blocks only what looks risky, such as scope escalation, unknown infrastructure, or hostile-content-driven actions.
195195
196* **Auto mode**: a separate classifier model reviews commands and blocks only what looks risky: scope escalation, unknown infrastructure, or hostile-content-driven actions. Best when you trust the general direction of a task but don't want to click through every step
196In Manual mode, the built-in starting permission mode on other plans, Claude Code asks before actions that might modify your system: file writes, Bash commands, MCP tools. That's safe but tedious. After the tenth approval you're clicking through rather than reviewing. Two tools cut those interruptions in Manual mode and apply in auto mode as well:
197
197198* **Permission allowlists**: permit specific tools you know are safe, like `npm run lint` or `git commit`
198199* **Sandboxing**: enable OS-level isolation that restricts filesystem and network access, allowing Claude to work more freely within defined boundaries
199200
No line in this hunk matches that.